initial commit

.chainlit/config.toml

@@ -0,0 +1,72 @@
+[project]
+# If true (default), the app will be available to anonymous users.
+# If false, users will need to authenticate and be part of the project to use the app.
+public = true
+
+# The project ID (found on https://cloud.chainlit.io).
+# The project ID is required when public is set to false or when using the cloud database.
+#id = ""
+
+# Uncomment if you want to persist the chats.
+# local will create a database in your .chainlit directory (requires node.js installed).
+# cloud will use the Chainlit cloud database.
+# custom will load use your custom client.
+# database = "local"
+
+# Whether to enable telemetry (default: true). No personal data is collected.
+enable_telemetry = true
+
+# List of environment variables to be provided by each user to use the app.
+user_env = []
+
+# Duration (in seconds) during which the session is saved when the connection is lost
+session_timeout = 3600
+
+# Enable third parties caching (e.g LangChain cache)
+cache = false
+
+# Follow symlink for asset mount (see https://github.com/Chainlit/chainlit/issues/317)
+# follow_symlink = false
+
+# Chainlit server address
+# chainlit_server = ""
+
+[UI]
+# Name of the app and chatbot.
+name = "Chatbot"
+
+# Description of the app and chatbot. This is used for HTML tags.
+# description = ""
+
+# The default value for the expand messages settings.
+default_expand_messages = false
+
+# Hide the chain of thought details from the user in the UI.
+hide_cot = false
+
+# Link to your github repo. This will add a github button in the UI's header.
+# github = ""
+
+# Override default MUI light theme. (Check theme.ts)
+[UI.theme.light]
+    #background = "#FAFAFA"
+    #paper = "#FFFFFF"
+
+    [UI.theme.light.primary]
+        #main = "#F80061"
+        #dark = "#980039"
+        #light = "#FFE7EB"
+
+# Override default MUI dark theme. (Check theme.ts)
+[UI.theme.dark]
+    #background = "#FAFAFA"
+    #paper = "#FFFFFF"
+
+    [UI.theme.dark.primary]
+        #main = "#F80061"
+        #dark = "#980039"
+        #light = "#FFE7EB"
+
+
+[meta]
+generated_by = "0.6.402"

Dockerfile

@@ -0,0 +1,11 @@
+FROM python:3.9
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
+WORKDIR $HOME/notebooks
+COPY --chown=user . $HOME/app
+COPY ./requirements.txt ~/app/requirements.txt
+RUN pip install -r requirements.txt
+COPY . .
+CMD ["chainlit", "run", "app.py", "--port", "7860"]

README.md

@@ -1,11 +1,2 @@
----
-title: Artists Of Data Science Chainlit
-emoji: 🚀
-colorFrom: gray
-colorTo: pink
-sdk: docker
-pinned: false
-license: apache-2.0
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# podcast-magic
+Final Project for LLMOps Cohort

chainlit.md

@@ -0,0 +1,14 @@
+# Welcome to Chainlit! 🚀🤖
+
+Hi there, Developer! 👋 We're excited to have you on board. Chainlit is a powerful tool designed to help you prototype, debug and share applications built on top of LLMs.
+
+## Useful Links 🔗
+
+- **Documentation:** Get started with our comprehensive [Chainlit Documentation](https://docs.chainlit.io) 📚
+- **Discord Community:** Join our friendly [Chainlit Discord](https://discord.gg/k73SQ3FyUh) to ask questions, share your projects, and connect with other developers! 💬
+
+We can't wait to see what you create with Chainlit! Happy coding! 💻😊
+
+## Welcome screen
+
+To modify the welcome screen, edit the `chainlit.md` file at the root of your project. If you do not want a welcome screen, just leave this file empty.

data/final-hh.txt

@@ -0,0 +1,296 @@
+The Final Data Science Happy Hour.mp3
+
+Harpreet: [00:00:09] What's up, everybody? Welcome. Welcome to the artist Data Science. Happy hour is Friday, December 2nd. It is the final hours of data science. Happy hour. Man is the last one. The background. We got a little bit of Lupe Fiasco going on. I used to listen to this track to pump myself up before all the happy hours when when I was doing it for the first time. Just because being so public on LinkedIn that she was scary, man, that she was scary but did it anyways, man. Did anyways. And it was great. I haven't done many important things in my life, but I could say this is hands down one of the most important things I've ever done, not only for myself, but for all the people that have taken part in this and just seeing their careers grow and their networks grow and all that. So this is hands down the most important thing I've done in my entire life, professionally at least. You know, having a wife and kids and stuff, that's pretty important. But couldn't have done all of this without you guys. So shout out to everybody here that's been, you know, A-1 since day one. You know, I wish David Langley was here, man. I mean, back in the pandemic days, he was like one of the OGs. I was here all the time. But yeah, shout out to everybody that's made this amazing and amazing experience for me. I appreciate all you guys, Every one of you. Yeah, man. Last one. Last one. All right. Vincent Harper is 5 minutes away from a divorce.
+
+Harpreet: [00:01:24] Yeah, I had to cover my ass there. Yes, Wife and kids, obviously more more important there. But no, honestly, man, professionally is probably the most hands down, most important thing. Just the network I've built and the network you guys have built in, the connections that just happened from people being here. It's amazing. So thank you guys for taking time out of your schedules every single week to join me for over two years. And I think the first happy hour was October, October something, 2020 was like the middle of the pandemic. And these rooms to be popping, man, we'd have like 50 people in here, everybody just looking for a connection [00:02:00] and wanted to hang out. And that was awesome. People from all over the world to man. I mean, it was like middle of the night for some people. And you guys were joining and I absolutely loved it. But we're here. We're here for one last one. Thank you, my friends, for joining in Big week this week, man, a lot of stuff going on. I haven't got a chance to play with the but open A's chat GPT is a is awesome I just I read some of these prompt I just have to read this because it was hilarious. I thought it was the funniest thing ever. So I'm going to read this this this prompt here. Somebody had prompted GPT chat GPT to write a biblical verse in the style of King James Bible explaining how to remove a peanut butter sandwich from a VCR. And here it goes.
+
+Harpreet: [00:02:44] This is GPT response to that. And it came to pass that a man was troubled by peanut butter sandwich for it had been placed within his VCR and he knew not how to remove it. And he cried out to the Lord saying, Oh Lord, how can I remove this sandwich from my VCR for it is stuck and will not budge? And the Lord spoke to him saying, Fear not my child, for I shall guide thy hand and show thee that way. Take that butter knife and carefully insert it between the sandwich and the VCR and gently pry them apart and the end. With patience and perseverance, the sandwich shall be removed and I VCR shall be saved. And the man did, as the Lord commanded. And lo and behold, the sandwich was removed. And the Lord said, Verily, I say, and to be seek not to put the peanut butter sandwiches in the VCR for it is not a suitable place for such things. Rather, keep that sandwich in the refrigerator or on thy plate where they belong. And the man heeded the Lord's words. And from that day forth he kept his sandwiches in their proper place and was safe from trouble. And, well, amen. I thought that was the most hilarious thing ever. Gpt chat GPT with the jokes. Also PyTorch version version 2.0 released this week. That's huge. What else is going on, man? What else is popping off this week? Kenji man, good to see you done globetrotting even even bouncing all over the world. Man. How are you been?
+
+Speaker2: [00:03:58] Yeah, I think right you can [00:04:00] make me check out for breathe. This is some monumental moment. I know. I've been. I've been really good back at home in Hawaii for a couple of weeks. It was a lot of travel to Italy, Spain all over the place. But I'm happy. Things are kind of calming down now. And we can I can take a little bit of time to celebrate, I guess maybe the the the end and the and the new beginnings here.
+
+Harpreet: [00:04:28] Yeah. Yeah, absolutely, man. Monica, good to see you again. How are you doing, Monica?
+
+Speaker3: [00:04:35] I'm really good. How are you?
+
+Harpreet: [00:04:37] Oh, great, man. Great. Just loving it. Loving God. You know, the next baby is on the way. Coming in just, you know, a week or two, literally any. Any moment. So that's about to get hectic. So? So. Yeah, man. How you been? What's new with you?
+
+Speaker3: [00:04:54] I'm so working for myself. Full time nerd nourishment. Doing, like, event reviews, putting together some stuff in the future. Kind of playing around with some ducks this month. I got a duck Advent calendar, so I'm just playing around with different technologies and such. Gearing up for the new year.
+
+Harpreet: [00:05:18] Yeah. That's awesome. Joe and Matt, good to see you all here again. What's going on, y'all? Also shouting, buddy. Yeah.
+
+Speaker2: [00:05:25] Good to be here.
+
+Harpreet: [00:05:27] Yeah, it's dual mikes. I love it, man.
+
+Speaker2: [00:05:29] Yeah. Yeah, that's right. We've improved the setup over time. Yeah, things are good, man. We're just kicking it. Matt's going to be on the East Coast tomorrow, so. Yep. So in New York. Hit me up. Anyone else coming to Ethan? Aaron's happy hour Wednesday.
+
+Harpreet: [00:05:44] Oh, Dan in New York.
+
+Speaker2: [00:05:46] That's a big fat now. All right, cool.
+
+Harpreet: [00:05:48] Wish I could be there, man. Shout out. Shout out to everybody else in the room as well. Coast of Eric. Matt Blaze in the building. Matt. Blaze. What's going on, man? Good to see you, David. Fair. And I'll be [00:06:00] Balaji. Good to have you all here. So let's let's kick off the discussion, man. Vin, what's going on? Listen, you Vin's always been my go to guy. I'm gonna go to one last time for the happy hour here to kick off some discussions. Go for it, man.
+
+Speaker2: [00:06:12] Oh, I wasn't ready. I thought. I thought somebody else could be take. All right. Oh, what's new? Yeah, that's interesting. That's kind of new. Meltdowns. New. That's well, not really new, But if I think the guy just taught us yesterday or the day before yesterday, if your company melts down, do not go on live television with a really smart interviewer. Fine. Like the dumbest interviewer you can. If you're going to do an interview, do that one. Because I have a feeling that's coming for some data science companies where I don't think we will lose people a ton of money, but we're going to have some ethical challenges coming up. So yeah, if that's one of you, if that ends up being one of your companies, don't don't do what he did, that that was bad. I think attorneys call that incriminating yourself, especially Andrew Ross Sorkin. I've actually met the guy before. He's actually really smart. Yeah. Not the guy you want asking questions in that way. So.
+
+Harpreet: [00:07:14] What what was what went down? I haven't I haven't seen this or heard of it. I've been kind of disconnected from the news. But what happened over the last I mean, I know about the small town, but this particular interview was some chemo.
+
+Speaker2: [00:07:27] Yeah, he went on CNBC at the New York Times. I think it's pitch book or something like that. It's what they call the event. And he decided to pick the smartest person on earth, basically from a financial standpoint to interview him and somebody who has maybe a negative one tolerance for BS and just and he came out with no idea what he was going to say, except I had no idea what was going on. It wasn't me. It wasn't malicious. I should have done better. I was just an idiot, [00:08:00] you know, because he allegedly stole like $600 Million and yeah, it looks bad. And he had it looks like a shell. Companies were involved in offshore accounts and people are calling him the new Bernie Bernie Madoff. So it's never good when the guy who interviewed him was the same guy like interviews Warren Buffett at the shareholder meeting and also, like wrote the book Too Big to Fail. And it's like a very popular financial columnist. Like not the guy you want to be. Actually, he's a perfect guy you want to talk to if you want to get busted. So that's awesome. So I swear this was a setup. It had to have been so somebody a little bit more funny if it was like carted him off in cuffs, like, right after the interview. Okay. All right. So, yeah, it's been fun. Cb a chat bot and not a person.
+
+Speaker2: [00:08:51] At this point it's probably just some like homeless dudes, like curly hair. That's it's actually him. Anyway, yeah, but what you're saying is it's going to be you're going to think tech companies or A.I. companies are going to be doing the same kind of song and dance. I think we're like one or two years away from a few perp walks. From just security standpoint, that's where we're going to mess up, is we're going to oversell something to somebody who is powerful enough to bring accountability, because that seems to be what happens is you either lose companies money or you make like a hedge fund go under because you sell them your your A.I. technology and it fails catastrophically and people lose billions and suddenly handcuffs come out and SEC shows up. So I think that's coming for us. I think we're going to have a security breach here in the next couple of years that get somebody put in jail. And we're also going to have a very public meltdown with some oversold, I think. And that's going to be the next one where people [00:10:00] lose a ton of cash or something. Mission critical fails infrastructure wide and, you know, like a power grid goes offline or goes offline for a month or, you know, something critical goes down where somebody has to go to jail. And I think that's coming.
+
+Harpreet: [00:10:17] Who would go to jail in that case? Would it be like an I c data scientist who is writing the code department manager? Like who? Who's responsible.
+
+Speaker2: [00:10:25] Culpable, I.
+
+Harpreet: [00:10:26] Guess, at that point?
+
+Speaker2: [00:10:27] Depends how good the CEO is throwing people under the bus, because that's that's truly the the differentiating factor is if the CEO is high quality that throwing somebody else under the bus then. It'll be that other person. But more likely than not, I think we're going to be seeing some examples made of sea levels, especially startup founders. I think that's where it's going. It'll probably be a startup, not a big company.
+
+Harpreet: [00:10:52] Like what type of startups? Like like startups that are leveraging maybe some type of generative model. Maybe they're building their startup on top of like GPD or you're just not I don't want to implicate anyone.
+
+Speaker2: [00:11:03] You're asking, I get wild, but I can't do that. That's that's the kind of thing that, you know, they send lawyers after me for. I can't Yeah. Could actually say, you know, names of anybody that would have a public infrastructure contract, but that might be where you want to look.
+
+Harpreet: [00:11:20] Yeah. Shout out to Greg Coco in the building as well as Keith McCormick. Christian Steinhardt, good to have all your heels here, Jennifer. Nadine as well, Sanker St of Austin and Eric Sims. This is great, man. It's like a family reunion. I love this shit, man. Excited to have all y'all here. Yeah. So I'm curious like, okay, so there's a lot of companies coming out that are probably going to be leveraging, you know, these generative models like GPT or stable diffusion or things like that. What's like the what's the. We're talking about infrastructure. I'm curious, what's like the infrastructure or MLPs look like in in that scenario? If anybody has if that question even makes sense, I don't know. Just kind [00:12:00] of refine at this point.
+
+Speaker2: [00:12:01] No, I'm like talking about critical infrastructure, like your power grid, your water, these stuff that we would have serious issues if they went down Internet backbones, you know, company like Amazon's cloud infrastructure or any of the hyperscalers who use because you have to use something like that to manage anything that big. And if if a startup manages to convince a power grid that they're worth having and you should buy my AI, it will never fail and it'll optimize your power grid. Not say anybody's done that or anybody that may have done that is fraudulent. I'm just saying that would be the kind of thing that would get you put in handcuffs if it was power, water, you know, nuclear power plant, just any of those types of critical infrastructure. And there have been companies who are beginning to get into that space where they're using models to do power grid. You know, it's a load balancing, I think, or something like that. I can't remember what the early use cases they're pitching are, but that's the I think that would get you into a lot of trouble really quick.
+
+Harpreet: [00:13:14] Cost them. Go for it.
+
+Speaker4: [00:13:16] So at some level, this all comes down to responsible engineering, right? Like that. That shit doesn't go away. It doesn't matter if we're now in the artificial intelligence age or whatever, whatever you want to call it. Right. So what is responsible engineering and at what point, especially with things like critical infrastructure, at what point are you saying that stability is more important than optimization or stability is more important than maximization of some kind of profit or time or reduction of cost? The thing that I wonder is that how much are we reliant on, you know? Government based agencies that are working on essentially [00:14:00] monitoring and handing out these tenders. How much are we relying on them to actually know what they're buying as opposed to rely on the people who know what they're selling? Right. It's a struggle finding experts to work in government sector because it's a lot of people not as interesting, right? Like, oh, you don't get to do the AI or the robotics. You get to manage five tenders and figure out which one gets to do the AI and robotics while you sit there with all of your expertise and years of experience and, you know, don't get any of that fun cake. I think that's that's an interesting struggle to to have, right. Like, how do we make that job more interesting or do we just rely on the common sense and the engineering discipline of people that are in the private sector that are designing all of these things? Yeah, I'm not sure, but at the end of the day, responsible engineering doesn't really go away, does it?
+
+Harpreet: [00:15:02] Greg, Go for it.
+
+Speaker5: [00:15:06] Well, I wanted to. It's probably going to change gears for a little bit so it can. You want to build up on what what is being said. I'll let you go first and then I'll I'll come back.
+
+Harpreet: [00:15:17] Ken, go for it.
+
+Speaker2: [00:15:18] Yeah, sure. Real quick. I mean, I think some things like this have already really happened. It's just that. There weren't necessarily massive legal repercussions. If we look at what happened with Zillow, I think it was last year, earlier this year, where they mishandled how their entire machine learning infrastructure is is designed to work. They also didn't account for how a black swan event would impact their entire business. If we think about it in the term of what machine learning, what AI is not resilient to it is events that we haven't seen before and we can conceptualize with COVID [00:16:00] or with any of these types of things. And so I think it could be like an oversight. We don't understand what's going on, but it could just be something that is outside the realm of what we believe possible. That could break a lot of things that are in existence right now and cause really negative, dire consequences. So I think it's just interesting to look at it from that perspective, too. It's not just like bad oversight and the present or overpromising or whatever it might be, but it's also this idea that, hey, this again, a black swan type event could happen.
+
+Speaker2: [00:16:35] And we don't know necessarily how a lot of the things that are out there will respond to that. Well, aren't you having like a volcano eruption over in Honolulu right now or. Oh, Honolulu. Come on, it's another island. I'm fine. What I'm saying is it's like, Yeah, but yeah, it could happen. It happens, you know? I feel like, yeah, we're ready for that. So hard to be ready for things like that. Exactly. And I don't know how you're in a different island, Right? What challenge are you in? Well, I'm. I'm on Oahu. Which is where? Honolulu, Hawaii. Like the big island is where the volcano is. No volcanoes on this one. Luckily, my girlfriend did go there today to go check out the volcano, which seems insane to me. So, ah, the pictures on Instagram. I mean, we live not that far from Yellowstone, which if that thing blew up, I mean, we'd just be like, really bad shape. Anyway, it's a Preppers of Data Science episode here, so it's awesome.
+
+Harpreet: [00:17:29] Greg Go for it.
+
+Speaker5: [00:17:32] Yeah. So, so I mean, I'm sorry for joining a little bit later. You probably have gotten all your kudos Harpreet for how you've, you've helped the community and over the past, what, two years, right? Two years. So, yeah, Congrats, dude. Like, I have this shirt for you today. That's why you turned me into. I'm a machine learning model.
+
+Harpreet: [00:17:57] I love.
+
+Speaker2: [00:17:57] It.
+
+Speaker5: [00:17:59] Hopefully, [00:18:00] you know, I go. I go, you know, apply things, but what am I going to do? And did address me? And we know more of these meetups, right? Going to going to be messed up. But yeah, thanks, Harpreet man, it's been great. Like, especially for me, like. I talk about it sometimes, man, but I've been hit by imposter syndrome for years when it comes to, like, adventuring and AI or science and things like that. And you've made me feel comfortable. It made me feel okay to ask them questions. And we're going to miss that man. I'm going to miss that a lot. So. And you guys, too, man, like these familiar faces, right? I'm looking forward to continuing to talk to you guys. Then you get 10 minutes with Van. With Van or Joe, your mind, your head starts to get so big. You know, I talked to Ken like this guy showed me a paper that changed my life on how to read papers fast. Dude, I never told you that, but this is amazing. Eric With with Monica. I mean, you guys are all amazing men, sir. Russell But, you know, Costa, this guy is like a monster in knowledge. And, you know, it'd be good to kind of like, from time to time to keep in touch. But anyways, I digressed. Let me go back. So I got this, like. Funny thing, it might sound crazy, but I feel like there's something happening in the AI world, especially when we think about big machine learning models like GPT four is coming. Look at Chad GPT that just came out there. I feel like there's this thing and then you don't want to maybe think about that, which is do you guys feel like there's going to be this AI grid being formed where it's going straight to consumers? For example, it'll be where I have a utility bill every month where I can tap into any kind of AI feature I added on my phone or add it on my device and I tell it, Hey, be checking my pulse and tell me what's going on.
+
+Speaker5: [00:19:56] And then it's like a 2% bill that is sent to me [00:20:00] every day. And then this grid. I feel like the big dogs are fighting to own that grid. It's like a power grid, giant power grid where you're supplying these quick to onboard Low-code no code kind of features on your devices and everything straight to the consumers because right now when you think about GPT, when you think about all of these big models, it's kind of like B2B type thing, like it enables smaller startups to make money with consumers but now is like, are the big powerhouses looking to launch these things straight to consumers where they can pay that small fee, where it's not hurting their pockets, but they become increasingly dependent on these small things to make them be lazy and not think about those things. We usually think about like paying my bills, like checking my walks, like why am I feet or my feet hurting? Things like that. Like, do you guys feel like this is where we're going with these giant models being born? Is are we going into the age of. Big machine learning model power grid that will support our everyday lives. Simple question for anybody.
+
+Harpreet: [00:21:09] I want to jump to Serge on this first. But I mean, and then, you know, if anybody else, I guess, goes to Eric Keith, I'd love to hear from you and anybody else, really. But I would argue, man, I think we're already there. We just pay with our data. I think to a certain extent, I think we're already there and we're already paying for it. Like, I don't know if if like, if you guys updated the latest zoom. Right. Everybody raise your hand. You'll notice that Zoom will pick up and it'll suggest an action. And that's, you know, that's computer vision there. I don't know if you've updated the new zoom or not, but if you raise your hand, something will come up in Alaska. If you want to raise your hand, that's that's right there for us. And, you know, I think it's infiltrated. That's the that's the reason I really started.
+
+Speaker2: [00:21:51] Like, hopefully that was a great prank. I really enough.
+
+Harpreet: [00:21:54] No. Did not work for you. No.
+
+Speaker2: [00:21:56] No. You made everyone raise their hand as well. I mean, I'm sure you have [00:22:00] to clap really, like, really aggressive, you know, space. If you make a super frown, it'll put a frown emoji.
+
+Harpreet: [00:22:10] But yeah, I think we're already there. That's part of the reason why I think I started pursuing. Just learning more about deep learning is because we use it every single day without even realizing it. Meanwhile, people are just thinking that, you know, deep learning is not useful, it's not interesting or whatever. Like you can't get business value from it. There's all these companies like making all this money from it. It's useful stuff, but I'll pause. I want to hear from my search on this and then, then, then we'll go to Keith. I'd love to hear from you. And then Kosta started to go for it.
+
+Speaker6: [00:22:39] I, I apologize, but I even forgot the question at this point. Gets you started talking about. You know.
+
+Speaker5: [00:22:48] I can quickly recap for you, sir. I can quickly recap for you. Are we moving towards some sort of like powerhouses fighting to get a hold of this, what we call what I call, like the huge machine learning power grid, where that goes straight to consumers, Right? So you may say Harpreet what you said about Zoom, giving you the capability to respond to you raising your hand. That's probably a model that's controlled by Zoom. But are we going in the age where you're going to have a few utility powers, like, you know, like few companies that give you power to your house that will own this, you know, AI grid where you can tap into to pay bills every month and say or do you feel like we're going in that direction?
+
+Speaker6: [00:23:27] Yeah, yeah. I think that could happen. Consolidation and in AI services, you know the companies you know like that already have cloud services. They have all these AI models off the shelf and these could fail and, and they're all interconnected. And of course they're being used by companies that offer third party home services, you know, like security systems and, you know, the very same systems that are already owned by Google and Amazon, [00:24:00] you know, that provide services like Alexa and what's the name, Ring and all those. Of course, they're already very intrusive. And they they could they could in a way. Well, not only their their extension of their power and they concentrate that power, but, you know, once they fail, people are going to lose trust in the technology. And if if they don't fail, they're just going to keep becoming more powerful. I, I don't think I like that, which is why I don't I don't have any of those things. I don't have an Alexa, I don't have a ring, doorbell or anything like that. I guess at some point people are going to start calling me like a mennonite or something like that.
+
+Harpreet: [00:24:48] Keith Let's go free. Go to you. And anybody else wants to jump in here? Matt I'd love to to hear what you got to say. Just go ahead and raise your hand, not, you know, don't raise your hand here.
+
+Speaker2: [00:24:57] But yeah, so I don't know if I have any kind of brilliant futurism insight here on Greg's idea, but I did it did resonate with me with something that I heard at MWC this this week. So I thought I would just share that. So I went to the. The keynote by the automotive VP. I don't know who else might have been in Vegas this week. It seems like all of humanity was in Vegas this week. But when I was listening to this keynote, I kind of figured that it would be autonomous vehicles and stuff, which is always an interesting topic, but they spent quite a bit of time on something that's very much like the Apple Watch or Smart home type stuff that Serge was just talking about. The idea is that pretty much all of the car companies are going to want to do software updates over the air, but also something that I feel naive that I didn't see this coming. That once you've got that happening because like Tesla does that now, I believe they do software updates over there, but [00:26:00] it becomes a marketplace because the car companies will want to sell you things through this, through this marketplace. And of course, the insurance companies would want to get involved because then they can give folks option of usage based pricing. So it's really interesting. And they spent it was a 90 minute keynote, so they had a lot of stuff to do, including to get clients to come up on stage. But they spent 20 to 30 minutes on this whole this whole thing. And it was really it was really something. Your car being turning into something kind of like your Apple Watch.
+
+Harpreet: [00:26:41] Vince, let's hear from you.
+
+Speaker2: [00:26:46] I think it's going to be kind of like in the streaming market right now where you have way too many different players and nobody wants to have eight different platforms and ten different platforms. I don't want to have to subscribe to Amazon, Google, Microsoft, Meta, Twitter and every other, etc. that you can think of, plus all the business ones. And you know it's going to turn into one of those things where. Just it's a cluttered marketplace. There's not going to be a really critical differentiator and trying to have all of them to get the one thing that each one does great is going to be really difficult to to get widespread adoption, because what everybody's what you're kind of talking about is a super platform or a super app. And that developed in China because there was one choice. You know, China sort of allows monopolies to to exist. But in the US we're just such crazy, fast followers that you're going to have as soon as one company figures out how to make some cash on this, you'll have 15 within a year or 18 months. And that's something that we do really badly, is [00:28:00] we don't do best in class, best in breed, and then go to market.
+
+Speaker2: [00:28:05] We just go to market with what we have to be first. And that allows a ton of people to come in. And because nobody really has the best product out there or has enough consolidation to be the choice, the super app. So we have all these kind of pseudo competitors that don't really compete with each other on quality. They're just kind of hanging out and they're willing to take whatever they can get. But I think longer term where you're talking about, you know, just downloading and being able to use A.I., it's going to be good because we are really bad at looking forward in the future and figuring out if I do this today, what does that mean for me in a year or three years? And especially with health care, that's going to be a huge application. And if you tie that to things like insurance prices and, you know, other different not social credit, but almost like health credit, where, you know, if I eat this donut, am I good? I'm going to work out an extra end times, you know, whatever. Am I good? Can we do that? And having a lot of data about that, just being able to say, yeah, no, you can have a donut, you're good, you know, have a cookie, enjoy yourself or Yeah, that beer is okay or No, that's your seventh beer.
+
+Speaker2: [00:29:23] What are you doing, idiot? And then there's consequences for it where you're looking at potentially paying higher car insurance or potentially having health insurance be impacted long term by repeated stupid decisions. You know, then all of a sudden the extreme behaviors and then personal freedom. So we're going to we've got a lot of iterations to go to get to the point where we have a good relationship with online social media. And I think we've got a long, long way to go with that. But there's going to be benefits along the way. We're just [00:30:00] continually going to have to churn through. Somebody throws something to market and doesn't think about how it's going to wreck a ton of other things. Then we have to clean up after it for two or three years and then the next one hits just as we're starting to get control of the last one. I think we've got a lot of these waves still to go Before we settle down into something that's a good relationship with technology.
+
+Harpreet: [00:30:25] Then. Thank you. Just a quick comment coming here from LinkedIn, from Akmal Syed. If you guys are in Oakville, you should you should follow him. He's he's awesome. Great content. I did an interview with him a month or so ago. He says this happens with BMW. They sell heated seats on a monthly subscription. And I just found that to be absurd. That is absolutely that is absurd. Let's go to Joe and Matt, then. Let's go to Kosta, then Ken and then Russell. I'd love to hear from you on this as well. So after Ken, if you wouldn't mind just putting your hand up, so don't forget to get to you. Go for it.
+
+Speaker2: [00:31:00] Yeah. It seems to me right now like these models are still too brittle for these general purpose use cases. At the same time, this is probably going to be some new start ups business model within the next couple of years or when there's a next big startup wave, the same ones that go to jail that we were talking about earlier. That's the next thing after their current startups go under. And then yeah, just like then I'm really interested to think about the long term ethical implications, right? Like we're just dealing with the ethical implications of Twitter and Facebook being such a part of our lives for the last. The big models remind me a lot of where crypto was a few years ago with a lot of the hype and I think a lot of the promise. It's obviously got a different flavor, but it does remind me a lot of the same sort of early enthusiasm with it. So, you know, so we'll see. I mean, unlike crypto, I don't think anything related to money just tends to attract like kind of scammy douche bags. And so, you know, hopefully that's not the case with these models, but don't count them out anywhere where there's lots [00:32:00] of money is going to be lots of dorks. So yeah, it's awesome. Couple anyway, then we'll have to talk about this in a couple of years now. Yeah. We got to remember this conversation and look back to it. Yeah, it.
+
+Harpreet: [00:32:15] Is. It is recorded the last half hour.
+
+Speaker2: [00:32:17] We have proof. We talked about that.
+
+Harpreet: [00:32:20] Ronit on LinkedIn saying with him Web3 that could be a possibility where transparency is the biggest foundation and user control, how much data they'd like to share. Let's go to Kosta then Ken, then Russell. I'd love to hear from anyone else. And if you're watching and got questions or comments on LinkedIn, I'm keeping an eye out, so let me know. Kosta Go for it.
+
+Speaker4: [00:32:41] So, so one of the things within the medtech industry, right, is you have this thing called regulation, right? You have TGA, you've got the FDA, you've got all these regulatory bodies that are extremely stringent. So if I want to go and make a device that you have to wear invasively non-invasively and have to use that for some kind of medical health reason, I have to go through a bucket load of scrutiny, a bucket load of scrutiny. I'm talking like your first first one could take a couple of years to get through all of the regulatory requirements. Right. But the crazy, wild, insane thing is those are only for acute parts of human health. If you really think about it right? Whereas I could build an app that manages sleep or claims to manage weight loss or claims to manage all of these other systemic things in our lives. And this comes from a like cereal user. I've used every sleep app under the sun. I've used a bunch of different fitness and weight loss apps and all of these things, right? But none like how much of them are actually as good as they purport to be. Right. It's very difficult to really nail down. Okay. Which of these are good? Which of these are [00:34:00] absolutely bogus. Like, I've tried some sleep tracking apps that I look at their their summer graph and I just look at that going, that's B.S., right? Like, there's just no way that that's the summer graph that's coming out of an overnight sleep like that.
+
+Speaker4: [00:34:12] Right. And there are others that are reasonably good for the technology that they have at hand, Like there's little technological limitations on what you can do. Now, that degree of data that we're playing with. At what point do we realize that we're playing with fire when we're talking about behavioral things that, hey, this app got me into this behavior that got me to do X, Y, Z, and that's creating all sorts of health complications for people down the track, Right? If we're not sensible on how we build these apps, if we're not well informed on how we build these apps, we can actually have a net really negative impact on the wider health implications, right? Because sleep and weight are huge. Like, you know, if you don't get that right, there's huge co-morbidities later on in life with all sorts of things like links to Alzheimer's, links to all sorts of other stuff. I'm not a medical expert, but you know, at the end of the day, they don't go through any of the scrutiny, any of the, you know, regulatory zeal that you would otherwise see for things that are supposed to be impacting people's health, yet they're impacting epidemic levels of health, like entire demography, you know, scale of things. So it's a little bit crazy to me that that doesn't happen. And I think we kind of come back full circle to the discussion we were having before, right, is how do we get like I see health, like human health as essential infrastructure, right? Like at the end of the day, it's as essential as, say, electricity or gasoil or water, right? So I've been meaning to check this one at you guys.
+
+Speaker4: [00:35:46] Is there is this concept of charted engineering. Right. And it's kind of really only really alive in the civil engineering and the power of electronics, like [00:36:00] the power electrical engineering thing, where you cannot be a civil engineering firm building a bridge or a building without having a chartered engineer to sign off on the site plans. Right on the design, you need a chartered engineer to sign off on all of these things now. Is that something or is there something similar? Obviously, that's a slow addition, like it slows down the speed of releasing software, but is that something that we should start to have an appetite for? Is there another way around it that we can do without without losing the agility of software? I just yeah, I don't know. Is there a value for that in our world, particularly with AI? Right. Like software, you can build software that's so innocuous and small that you maybe don't need it. But when it comes to AI, when we're starting to see second order and third order effects, it makes me start to think.
+
+Harpreet: [00:36:58] Ken, let's hear from you. Shout out to everybody else that just joined. Ben. Good to have you here. What's up, Ben? Yusuf, JT, Patrice, Eric, Antonio. Good to have all you all here. Go for it, Ken.
+
+Speaker2: [00:37:11] Because I don't know if I can answer your question. I was going to take it a slightly different angle, actually going the opposite direction up the chain. And when we talk about how, for example, like an app market or a service market market, it's very fractured. Right? The thing to me and I think the thing that's most interesting to people who are are actually going to truly change our future is the platform. Right. So you look at how Apple, they they basically dominate the platform of apps they control the faucet of where people can can go in and look. And I think we see it in the news very clearly with Facebook and Mark Zuckerberg realizing that he truly missed the boat when creating the initial platform to be able to disperse these things on. And so I think you look at [00:38:00] the metaverse, for example, his his work with that is to control the platform where all of this is dispersed. And I think that's going to have such a massive implication on if there is one platform or a unifying platform that controls everything that goes out, all all of these services together, whatever it might be.
+
+Speaker2: [00:38:18] That's going to be interesting when we talk about the not that the other things weren't interesting, but that's like the scariest and I wouldn't say the most looming threat, but it's the most complex issue. I mean, you look at the car example that was brought up before each individual car company. By definition, they have their own platforms to launch services in a different sphere, where we have phones, where we have whatever, like headgear, metaverse devices, that's still evolving. And if someone completely controls that. That essentially unifies a lot of power, all of these advanced technologies in a more singular place. I don't think we'll ever have the, like, software type of monopoly like we do in like like we see with WeChat in China. But I think a hardware type monopoly can enable some of the really scary and looming effects of a more software monopoly. So I think I don't really know where that's going, but I think it's important to bring up and think about as well as as we approach this in the future.
+
+Harpreet: [00:39:26] Russell, let's go to you and then Russell. Let's go to a Ben.
+
+Speaker2: [00:39:33] Thank you, Humphrey. So, jumping back to Greg's original question, I've been very surprised. We go to one master model that's going to feed everything simply because there's so much competition in business. I think people want their own version or their own section of something, and they'll market that. Their model is, you know, five points better than another model for [00:40:00] various different reasons. And they'll try to target this to different parts of society. So they'll say, you know, if you're if you're young and hip, you know, you want to go for this model rather than this model because this is for the boomers and all of this kind of marketing language. And moreover, I think the biggest problem with business is that far too many businesses prioritize profit rather than service or product quality. So money tends to be what drives many of these decisions. And I think the same is likely to happen in all business, including the newer businesses, the development of of AI and ML models, etc.. Then moving on to some of those points, I think yeah, certainly some of these I made a couple of comments there. As you know, smartwatches have been great, but they're not perfect. I have a smartwatch and I put some sleep apps on it. I agree with you guys. I think it's more hokum than not. And I'd put that up to the 90% hokum there. You know, I, I sleep well sometimes, but mostly don't. And I lie awake at night and just stay still and try and almost meditate so much. And it tells me that I've had REM sleep for five cycles, though I sleep, I No, it's not. I think there's just some kind of a sequence there that if you're still for a certain amount of time, it splits things up and tells you you're doing things you're not.
+
+Speaker2: [00:41:29] And I've not found one that persuaded me. Otherwise I don't use them now, but also some moral and ethical dilemmas for smartwatches, you know, because it tracks your movements and the things that you do. So I made one point that if you sign up to an insurance policy for anything and you don't make a declaration, so you made a declaration that you're in perfect health, but your watch picks up, you've got some minor heart murmur and then you need to make a claim. And the insurance [00:42:00] company can can access your data that's provided from this smart wearable that goes to a service. It's Apple Watch or Samsung or it or anything like that. If they can access it and then use that to refuse to pay out. That to me is an ethical moral dilemma. And I'm making a a significant difference in my assessment from someone that is willfully trying to misuse an insurance policy than someone that legitimately does not know they have an issue. It's not been diagnosed. They were honest at the time. That to me should not be an issue. But I imagine insurance companies wanting to maximize their. I probably would investigate that as a routine. So there's some severe moral and ethical dilemmas there, I think. And then rounding this back to Greg's question again, I think a single master model could probably help prevent that, but I don't think that's going to come anytime soon. I think we're quite a long way from that because of business, competition, etc..
+
+Harpreet: [00:43:04] Russell, thank you so much. So Greg's question was about this this future where, you know, only a few big super power companies can build this AI model power grid, So similar to like, you know, how we have utilities and services right now, water service, telephone service, so on and so forth. Is there a future where we have A.I. services where we just tap into a little bit and then kind of pay to use that? Greg Hopefully.
+
+Speaker5: [00:43:31] Yeah. So it's kind of like direct to consumer and, you know, I can afford to subscribe to a few to gain societal advantage, right? Check on my health when I run, when I'm at work and I'm stressed and it's guiding me and I pay a monthly bill on and I become increasingly dependent on these kind of like little features that I can on board, on my devices or sensors that I put on myself and things like that, where only a few power grid [00:44:00] service suppliers can supply these, where they're skipping the line. Like, right today you see big models like GPT enabling other start ups that then create services for either other businesses or consumers. But I'm thinking about this power grid that goes straight to consumers like you and I, and we're just becoming independent, like increasingly dependent on that to survive, to be to have societal advantages and things that I do see a future like that, then I guess that's what my question was in. Mark, I'm happy to see you too. I'd love to hear your thoughts on that as well. Yes, it's dystopian of The Matrix for Erik.
+
+Speaker2: [00:44:38] So so Greg, I think this I think there is and I think the future maybe I'll just speak to my building a monolith from the business side because I think it has to exist on the business side before it goes to the consumer or to the home side. So a fun maybe a bit of a provocative question or a fun question to ask this group. Who is the smartest data scientists in this meeting right now? And like, there's a lot of really, really smart people here, some pretty profound people with a lot of experience. But the point I'm trying to make is if we actually pooled all of our experience where we are, we're a team of 26 people. I could probably bring in panels of people to find out that we have gaps. Not not an individual like we as a group have gaps in data science loss functions. We don't know methods, We don't know failure points we don't know. And so what that means is you will have a business that becomes a monolith. The open source won't be able to keep up with a number of failure modes or the shared knowledge. And so it will be a business that's collecting all of them. And so I think we'll start moving away from building the build it yourself, which most of us on this call we lived during the build it yourself era.
+
+Speaker2: [00:45:50] And eventually, when it comes to time to value, that will continue to be accelerated to the point that I like to talk about Jarvis for everyone. So in the future we [00:46:00] will have Jarvis for everyone, and that will be a very helpful thing to have at home. And some people might think that begins to sound dystopian. One fun theme to think about. There's some complicated ethical discussions around personification or proactive learning. So one example would be my kids are me. As a parent. I'm frustrated that it's so gross. There's people eating in the TV room again in my home, knows that I'm in charge. My wife and I are in charge, and my home suggests that I can turn off the TV the next time that happens, which is actually a really fascinating thing. So the home suggests that that means the home is proactive enough to know it can collect the data or it's already collected the data and it can execute on a model. There is no data science like it was all no code, I think escapes to automatic speech. But maybe Gregg react to anything I've said or I think the key thing I think about is experience. Capture becomes a black hole where no individual data scientists, even today, they're already losing the fight with experience capture with these bigger a companies out there.
+
+Harpreet: [00:47:09] Mark, let's go to you. Good to see you here, Mark.
+
+Speaker6: [00:47:12] Let's good first of all, excited to be here. And just want to highlight how amazing I think you created and carried on for a while. That's the last one. But I know you're doing me doing greater things going forward. But to respond to to Gray's questions and Ben's comments, I recently went to Transform X Conference Live, and I can probably probably find the episodes, the talks on YouTube, but they had a lot of the people who were like CTOs or CEOs of like Google and like open air and all these things. And the argument they're making is that we've always had these big models. The thing is like, when do we release them to the public because there's so much responsibility and ethical concerns regarding that. One thing [00:48:00] that they describe kind of what a future is. And that's why I kind of jumped in because like Greg had a really nice analogy of kind of like this I kind of power grid. Is that similar to what we have for like the App Store or the Google Android store where you have this platform and people build businesses on top of that. We're going to be seeing the argument they made is that we're going to be seeing that these massive AI platforms that no one really compete with just how much compute it takes to build them and stuff like that are going to be platforms that people build on top of. So that was an interesting thing coming from that talk. I mean, it's well beyond me to even have like, here's my opinion on how the future is and more so repeating what they're saying in those talks. But it was interesting to hear lot of those leaders saying that it wasn't that this happening. Now it's more so they decided to open this up now, which is a slightly different thing, knowing that like with these large companies, they've always had these kind of capabilities as a matter of how they commoditize and make a market out of it.
+
+Harpreet: [00:49:01] Yes, Listening to the Machine Learning Street Talk podcast, I think it was the most recent one that had Aiden Gomez, CEO of CO here, one of the authors on Attention is All You Need. And he was talking about just that, trying to build a platform where people can build build on top of. Thank you very much, Mark. We'd love to hear from anyone else, man. Anybody else wants to to jump in here, please let me know. Anybody else got a question? Your comment?
+
+Speaker5: [00:49:27] I got I got a follow up question for for Ben. You put something about Jarvis there and it's in It's interesting, right? So you talk about like everyone will have a Jarvis at home. You know, my concern is that how how affordable, how accessible will it be? Right. Like, typically, you see when you see technologies like that, it's always like available to only a few. And then over time it becomes more affordable. Then you have this lag in terms of like people have access to new technology that can help them improve their lives. So how do you see this kind of [00:50:00] commercialized in kind of like on an even playing field without affecting pockets of society versus affecting the most, you know, things like that?
+
+Speaker2: [00:50:10] That's a that's a good question, I think. Jarvis For everyone, I see that as being relatively affordable, almost like Alexa. But the the fun one to think about is the home droid. So the home droid will start out being extremely expensive, like it's $1,000,000 and this will be the home droid that'll do your dishes. But just like the iPhone, version's coming down. The old version of the home droids used maybe more accessible in, but eventually you might get to a point where you can have a home droid that is less than 100,000 to do things to quickly pick up clean, walk the like it. There's some very weird realities we could get into because yeah, hopefully that's a bomb into the group to just open up. What is it okay to have a home droid? What does the is can the droid be stateful with memory? If it's stateful with memory, that means your your kids will form an emotional connection with it that Hey, Sally, how was school? Sally was hard. Billy was mean again. Oh, that Billy like that. That becomes an ethical concern because what does the Droid say and how does that influence your kid's development? And just like you take a dog back to the pound, do the kids grieve you upgrading the Droid? You know, if I don't know, is that question too weird for the group?
+
+Harpreet: [00:51:32] There's there's an episode of I.
+
+Speaker2: [00:51:34] Guess Greg's question was Greg started the Greg started like sorry.
+
+Harpreet: [00:51:40] There's the there's an episode of the Black Mirror show where it was that like a home assistant, a personal home assistant that lived inside of this like Alexa type of device. But the home assistant was actually a upload of that person's psyche. So it was like that person's digital clone [00:52:00] that had all the same thoughts and feelings. And that's why that home assistant knew that person so well. Trippy episode. I'll see if I could figure out the the title or.
+
+Speaker2: [00:52:09] It was also in Silicon Valley. The billionaire had a robot that would talk to his kid and put in a bed, but it was so the billionaire wouldn't have to talk to his kid. He's like, Oh, not my fault. You have to go to bed now. So I'd get it for that, I guess.
+
+Harpreet: [00:52:24] Kozlov US go to you shout everybody else that's joining see everybody in the room. Just want to say hi to to the new people. Yousef is here. Good to see here, Yusuf. Yusuf as I've been liking his content. Good friend, of course, I believe as well um go for it cause the.
+
+Speaker4: [00:52:42] Yeah. I think we we reaching too far for an example. I mean, I don't think we have to reach all that far for, for an example of this kind of thing. Right. Like take, they take it back to health care, Right. The latest and greatest in surgical technologies is available in certain places. And at the other end of the spectrum. Nowhere near. You're nowhere near. Right. Like and as we go, I think the difference is we like maybe a hundred years ago, 120 years ago, we were creating more fundamental technologies like steel, right? Like we were we were talking about steel, we were talking about train tracks. We were talking about things that by nature were lower abstraction. Right. And the ability to jump from. Essentially, for example, from data to insight. Right. To be able to jump from data to insight was a lot smaller of a jump back then. So it was a lot more accessible because more people were in a position to take advantage of it in the first place. Right. But now those kinds of abstractions that we're leaping forward with new technologies, particularly with AI and things like that, and the people that are enabled to use it early on are already at a head start. So you're going to see that gap in technology. So you're right, like health tech, for example, you create something great. Only a few people are going to be able [00:54:00] to afford it. Java is only a few people going to be able to afford it at first.
+
+Speaker4: [00:54:03] Eventually, more people will catch up. But that I think the lag between the first what's called the people that are early to the system and then the people that eventually get access to it for accessibility reasons, that lag is actually growing as technologies are able to abstract more things and enable us to live in a in a more impactful, real world kind of way. Right. I don't know if that changes with the nature of software versus hardware, but when you're talking about home assistants like hardware, there is a real manufacturing cost that comes into it, whereas with software it's a little bit more ubiquitous. We're able to create it on Android phones at work, even on, you know, really low, low cost hardware. How much of it is linked to hardware? How much of it is linked to software is an open question to me. But the other side of it is that, yeah, I think the more that we enable, the more that you need to be in a position to actually make use of that. For it to actually be a viable early usage. I'm rambling a little bit because I've just completely sidetracked into that whole thing about how much of it is because we're hardware that we can't, like, afford something versus software, right? Like we've got mouse droids and one side of the world that I mean, I say mouse droids, I mean robot vacuum cleaners. But on the other side of the world, we're still using broomsticks, right?
+
+Speaker5: [00:55:25] Yeah.
+
+Speaker4: [00:55:26] And to be honest, we still use broomsticks after the mouse droids, because let's be honest, they're like 90% of the job, right?
+
+Speaker5: [00:55:34] So. So, Ben, you said something about like. Like, like a potential for, like, your daughter grieving. Right? If you're deprecate this robot they've attached themselves to and I'm going to say something that may sound mean or put me in trouble, I don't know. But my wife is in health care and she talked about often getting assistance to older folks. And maybe this is like one of the consumers that could be [00:56:00] a success story for these kind of like assistance simply because the lifespan of an assistant is longer than the person using it. Right. So, you know, when the person passes away, you don't have to deal with like legal implications of somebody getting so sad because now their friend is no longer with them to help them cope through the day. Right. So maybe we've already found like successful use cases with these in health care for the folks who are at the later stage of their timeline life, where they can leverage these robots to cope with life until they pass on. And now you can get rid of any implications of your really killing their mental state as a kid. Now that you have to take the robot away, kind of like taking the dog away from them and now they're traumatized forever and things like that. I don't know what your thoughts are there.
+
+Speaker2: [00:56:52] Yeah, I guess they want to be worried about grief, especially if we're on hospice or something. But one thought, Greg, is we already experienced grief with objects. When I sold my AMG Mercedes seven years ago, I was sad for many, many, many, many months. And so you can think about objects like that. You've had our own, like if it gets broken or stolen or something like you don't get over it tomorrow. And so I think there's different stages of emotional attachment that we can have to non sentient things. And this just takes us into a new category. But I think grief is part of life. All of my kids have had pets and all of their pets have died and shocking ways like, like some things. My my daughter's tortoise was attacked by a neighbor's dog and and we had to euthanize it. And so, like, that's life it's and there's this theme. If if you live a life with love, then you're guaranteed to experience the limits of our grief. Okay.
+
+Harpreet: [00:57:58] Shout out to Mexico. Salma Kiko [00:58:00] here a second ago. Kiko, what's going on? Uh. Waikiki is definitely the smartest data scientist in the room, for sure. Imagine if all of us did actually come together and make a company or start working together. That'd be very, very interesting. Very interesting. Greg, great, great discussion kicking off there, man. Absolutely. Love it. Any follow up thoughts or questions or anything? Kenji said would fire him on the first.
+
+Speaker5: [00:58:24] I would love to hear Michiko about that. You know that that that that dystopian things that we're discussing.
+
+Harpreet: [00:58:30] So let's go to let's go to Patrice first. I had to.
+
+Speaker5: [00:58:33] Go in Oh, but you sorry.
+
+Harpreet: [00:58:34] And we'll let Michiko warm.
+
+Speaker3: [00:58:37] I'm hoping you'll say a little bit more about what's next to you, but for you, Harpreet. But I'm wondering if that might be if it's not what you're planning a next thing. Like there's a there's a. Scott Page has this theory of diversity that he's explained, like those old fashioned Scantron tests where there's like, you put your answer in, then there's holes. And like when you have a specialist in something, they know all about their type of thing. And the idea is like, there's a diversity of knowledge. If you bring in people who have domain expertise, experience, expertise, all different kinds of like diversity in what their knowledge bases are. But wouldn't that be fun if if this were the last artist of data science, But there were some way to have a future form of that collective knowledge that you've facilitated here? And I have one question for you. If did you think like did you have a conscious approach to putting this group together or was it more organic? Like, I'm going to get a bunch of people together and see what happens? [01:00:00] How did you make this happen if you have anything on that that you want to share?
+
+Harpreet: [01:00:05] Yeah. Scott Pace. Scott, you page is awesome, by the way. I've actually interviewed him on the podcast. There's an episode with Scott Page and myself. Go check that out. The model thinker, I actually it came together organically. I just told people I'm doing this thing, come hang out. Like, I think the first office hours was definitely Eric was there, Eric and Toshi. And we go, I don't know if you guys remember. We go, I haven't seen him in a while. And a couple other people, a small Carlos was there too, Carlos Mercado. And then like a few few like weeks after that, Marc came, started hanging out and then I just started inviting people like, Hey, I do this thing, you know, this is before I had like, creator mode and like access to, like, live anything. So everything was kind of like closed. And I was like, I just do this thing where people come together and we just talk, come and hang out if you want. And then people started coming and, and people, yeah, just started coming and showing up all the time. And I loved it. So yeah, it was very organic. I would say the way this all unfolded. I don't know if that answers your question, I'll pause to.
+
+Speaker3: [01:01:11] Yeah, just, just one more thank you for me to not only to you, but to everybody who's been here, because our artists of data science kind of coincided with my first kind of starting to think about the world of data science. And it was really, really helpful to have a bunch of alternative views on things I was exploring and hearing. And yeah, I appreciate that this, that I was able to rely on this group to have interesting new, different things to say than other places and all in one place. So that's.
+
+Harpreet: [01:01:54] Awesome. Well, thank you for being part of it. Thank you for coming. I could not have done it without you guys. Like, seriously, I don't know if I would have. [01:02:00] Like, I probably would like if people didn't come. Like, honestly, if nobody came to the office or the happy hours, whatever, like, I obviously wouldn't have done it. So you guys kept coming, kept showing up, kept having great conversations. And yeah, that, that just kept kept doing the man. Yeah. Mexico's saying, Mexico, come on, where are you at? I can't see like, where's there you go. And he goes saying that this help with quarantine loneliness. It definitely did. Mexico is the only person I knew before starting this like that I'd met like in person I actually knew. We go back now. We go back and I'm excited here to Mexico and Mark are here. We got some going on together. You know, I've been slow to move on that, but trust me, the ideas are simmering. I've got notes, and what we're doing next is going to be awesome. We're you know, I'll fill out that notion page for you soon, Mark, but that's going to be interesting.
+
+Harpreet: [01:02:54] And I'm excited to focus efforts on that. The few hours that I have on Friday are going to be dedicated to that. And then the new channel that I got kicking off the Deep Learning Channel, the Deep Learning Channel will be just all about deep learning. And I'm starting first from like doing deep learning straight from just nothing but like Python and NumPy and just working at it from there. So from first principles. And right now I'm, I'm trying to figure out man in man I am that's the, that's like the, the software where three blue one Brown uses to animate his videos. So I'm trying to like learn that and trying to figure out, okay, if it is worth the time investment or should I just draw stuff by hand and and explain stuff, but I'll be checking that out as well. But yeah, shout out to me Kiko symbol, what's going on? Good to see you as well. How I'll do what you all up to.
+
+Speaker3: [01:03:47] Trying to figure out. Hey. Hey. Sorry we couldn't join earlier, but we were doing a team meeting some. Would you want to say hi?
+
+Speaker2: [01:03:58] What's up, man? Good to see you. [01:04:00]
+
+Harpreet: [01:04:00] Good to see you, too. Man. Good to see you.
+
+Speaker2: [01:04:05] Jimbo.
+
+Speaker3: [01:04:07] So there's Joan, like Joan Matthew.
+
+Harpreet: [01:04:12] He was watching on a small screen there. The the question that that that Greg had. I would love to see if you guys have any input on that. Greg, just kick it off one more time because that was a great discussion and I'd love to hear Mexico's input on that.
+
+Speaker5: [01:04:30] Yeah, so, so so Michiko, I've had, I've had this like crazy dystopian sound sounding like theory about like this future coming up where, you know, a few companies will have control of what I call this power grid that goes straight to consumers nowadays. When you think about GPT, they go to, you know, they enable a lot of startups who build technology on top of it and serve it to more businesses or consumers. But now, you know, are we going into the ages of a power grid where as a consumer, I can just have a utility bill for all of the ML or AI based features that I download on my devices or tools to enhance my life, whether it's to monitor my feet when I walk or my my stress level at work or anything that I do in life where I become increasingly dependable on it. So all we or will we get to that point where a few utility companies or power grid utility companies will serve us these things that make us increasingly depend on them to do things in life? So what are your thoughts there?
+
+Speaker3: [01:05:45] So I'm going to so I'm going to say my piece. But actually, it would be fun to also get some take on this. So let me just draw the example of utilities. So most people don't realize that, for example, solar [01:06:00] in the US, if you were to trace, like for example, wherever you live in the US, you probably get an advertisement for some kind of solar company, right? Residential, solar, it could be insert name that's got green or planet or sun or light or bright someplace in there. Right? So the way a lot of those work, for example. So you would think that it's a competitive market, but it's really not for a couple of reasons. One, energy markets are not competitive. So you do have like certain you do have like an oligopoly in terms of power purchasing, trading, supplying all that jazz. The second part is that like that is an industry, for example, where it could be different, but the average like sales lifecycle. So a solar panel, right, is X thousands of dollars. It's a pretty big purchase. And also buying and selling energy can be kind of complicated. So even though you have what seems to be competitive, local companies, a lot of them actually end up being subsidiaries of bigger companies or their sales and marketing channel partners. So for example, I worked at Sunrun, which is one of the largest residential solar companies.
+
+Speaker3: [01:07:11] The Solar City is another one that people are very familiar with. But a lot of those companies, they seem to be competitors, but they actually have a lot of like integrations and and channels and partnerships that are not necessarily visible to like the common consumer or the consumer that's purchasing energy or buying panels. Right. So I think you'll get something that is kind of similar to that, only just quite a bit more fragmented or even if you think you're basically paying into a competitive market, it's actually not. But once again, like, you're not going to but you're not going to necessary know that unless you have domain expertise in that market or I don't know unless you like to read industry reports, which you must be all fun at parties. But no, I'm kidding. I think that's really fun. So, I mean, that's kind of my take. [01:08:00] And the other. And like, can you can you recommend this book to me? A long time ago it was about the globalization and militarization of like I, I forgot what book that was. But like the A.I. superpowers. And I think that's also another thing that you'll see. But Simba, what do you think? Do you think there will be a grid of like.
+
+Speaker2: [01:08:28] So to make sure I understand the question, the question is essentially like, are we is all the kind of every AI functionality in every company going to kind of be dependent on like two companies models? Is that kind of generally what it.
+
+Speaker5: [01:08:44] Is kind of like more like us humans, like consumers will be dependent on a few utility providers of AI features like low code onboarding. Like I can say, Hey, I want to purchase this little AI features here and embedded in my device, and now it's serving me and I'm paying a monthly bill for that service kind of thing.
+
+Speaker2: [01:09:06] I mean. I think it will happen to an extent the same way that there's like a Google cloud, like Azure, like it does kind of consolidate around the big players because there's a certain level of scale you need to be able to train something like a large language model or any of these foundational models. Point is, is that most of those things kind of or input and I mean they mostly output embeddings, but people are just using for their own specific use cases anyway. So. I think it will happen. I don't think it's a major. Risk factor is issue as much as as it would be as much of a risk factor issue as being a centralized as it is. And like Baywatch goes down, like there's probably this Zoom chat would go away. It's [01:10:00] kind of my take.
+
+Harpreet: [01:10:05] Thank you very much, Paquito and Skip. I'd love to hear from Yusef on this. Yes. If you want to jump in and let me know, I used one of those tips earlier today when I was coding. He said, Don't do four I in range land of something. He's innumerate and said. And I did that. I started doing that. Thank you, Yusuf. We'd love to hear your take on this.
+
+Speaker3: [01:10:23] Also, quick comment. This is why we need more citizen data scientists, because they will be the anarchists of the data science machine learning world in the future. You train up more seasoned data scientists, you get more like badassery, like stable diffusion, my friend. Community developed and trained. Yeah, right.
+
+Harpreet: [01:10:41] Right up. Yeah.
+
+Speaker2: [01:10:46] Yeah. So I'm usually IRC. I look on LinkedIn but custom. I used to work with custom and our last job and he's like, this is the last song you have to join with. Like, okay, I'll join. So thanks Harpreet. Thanks everyone. I'm going to miss, especially my two favorites, just keeping it 100. Greg And then I want to miss the text from you too. Thanks. In terms in terms of my take on this, I think for things that rely on data like it might be the case, but for things that rely on compute, as the compute costs go down and it becomes easy for lesser players to have the kind of compute that the bigger players have. Now, it would be hard to consolidate things that rely on compute. But the data advantage, I think will remain and things that rely on data that's more likely to happen.
+
+Harpreet: [01:11:55] Yusef, thank you very much. See if there's any other questions or [01:12:00] comments coming in. Ben's talking about a therapist. I think that'd be awesome. I would probably see a therapist more sooner than I would see a human one. Like it's been on my to do list this year is to find a therapist.
+
+Speaker2: [01:12:14] Is that like, a version of, like, better help or something?
+
+Harpreet: [01:12:18] Better help, huh?
+
+Speaker2: [01:12:19] I've never heard of that. Oh, you could sign up online for different therapists. They have them on every podcast, so you should get. You could start reading like betterhelp ads in your podcasts. That'd be pretty funny. So, Joe, you could transcribe. There are all these Tik Tok and Instagram therapist influencers. You could transcribe all the advice they're giving and then you would just have that response like, There you go, you're done. You got to be your best self, you got to get out there. You could you.
+
+Speaker4: [01:12:47] Could do that with professional coaches as well, right? You could also do that with fire with finance gurus on YouTube. Just scrape all the YouTube channels, create a model. You could come up with the ultimate crypto crypto guru bot, right? That's that's something I'd love to see tomorrow that would make my day.
+
+Harpreet: [01:13:05] I mean, that could be possible, right? Aren't there isn't there like an extension of stable diffusion that can generate like movie ish scenes. I think I've seen something like that or heard of something like that.
+
+Speaker5: [01:13:16] Plus like I can see I can see legal, legal folks with cuff links like their conflicts must be tangling with like legal implications, copyright implications. Right. So all of these things.
+
+Speaker4: [01:13:28] So this company that we're all building, we're going to create an AI bot version of Sam Bankman-fried, right? That's that's the goal. That's the ultimate.
+
+Speaker2: [01:13:35] You said that, not us.
+
+Harpreet: [01:13:37] So that's good.
+
+Speaker2: [01:13:40] Maybe Jordan Belfort Matt said, I don't know. That'd be funny to.
+
+Harpreet: [01:13:47] Are you reading this?
+
+Speaker2: [01:13:47] If I have a question for everyone. I'm sure you saw the latest good stuff. Like how incredible the text generation is like. Did you see, [01:14:00] like, the one where I'll explain why this algorithm implementation of like, bubble saw is wrong in the seventies slang or just it was mind blowing, really. What do you think the impacts are going to be of such technology on the creativity of variety. Like if you imagine a future, someone who creates content can just be like, Write me a post on delayed gratification and just boom, boom, write. Like, how do you think that's going to change how content is created from a writing perspective?
+
+Harpreet: [01:14:36] Yeah, I think I've ever seen that. It was like stayed in the style of, like, a gangster. And I was like, Hey, you see here the problem here with this is there's already companies out there. Like, I think Jarvis is one of them. Drivers has actually a company that does like help with copyrighting and stuff like that, but. Yeah, I'm excited for it because I think it's just augmenting human creativity. I think at the end of the day, the prompt goes in, the stuff comes out, but it's still the human that has to like look at the stuff that comes out and determine if it's decent or not and then, you know, add their own kind of spin to and remix it. But Kosta, let's hear from you.
+
+Speaker4: [01:15:15] Here's what that breaks down, right? So on a on a general when you when you're creating generalized content, fantastic, right? When you're creating like like you look at it with we were talking about therapy influencers, right? A lot of their content at a general level, very, very powerful, very good, very useful. Right. But how do you individualize that if you have to individualize the output of something like GPT three if you had to create generalized content, fantastic. But at the end of the day, if I had to, I had to ingest therapy. It has to be specific to how my needs are. Right? So how specific could you actually make it? How responsive could you make it to the nuances of human psychology, particularly from psychotherapy [01:16:00] standpoint or from a financial advice standpoint or from any of those things? Right. Like even from a like I mean, you said you and I were talking about this a few months ago about how do you create like brand content, right? You could auto generate brand content at some point without needing to spend as much energy. How much of that then can you actually nuance? Like how nuanced can you get with that brand content that's being generated and how kind of generic does it become? Is is kind of my tack on to that question almost is to say this could get really good for generalized, but what's the step that you'd need to make to make it nuanced enough to deal with individual The individual aspect of that, particularly with therapy bots, particularly with branding bots and things like that.
+
+Harpreet: [01:16:49] Mark. So you had your hand up, but I guess maybe.
+
+Speaker6: [01:16:52] Uh oh. I was a tangent, so that's kind of related, but I can hold off to that later. Just, just an idea I have for all these different creative, generative.
+
+Harpreet: [01:17:04] Let's go to Mexico. You saved them.
+
+Speaker2: [01:17:06] Greg Yeah, in terms of nuance cost, like if if it's able to mimic a seventies gangsta slang, why couldn't it mimic than the ones that you have potentially? So it could be fine tuned on your stuff and then not need much data and just keep generating content that you generate. Right? That's my take on the nuance.
+
+Speaker4: [01:17:34] Scary shit, though.
+
+Harpreet: [01:17:37] Greg, let's hear from you.
+
+Speaker5: [01:17:38] Yeah, I guess the question is that I haven't been able to answer and I've think about constantly when it comes to, like, generative. Ai is like one who owns, like the output, like the, the, the rights to the output, right? And then and then who needs to be rewarded, right? So for example, a lot of the things that they get trained on, you know, it may be [01:18:00] somebody else's code, it may be somebody else's art and things like that. Right. So when when the AI generates an answer in a certain style, you know, does the artists, original artists that gave their data for that model to train on, does it get a commission on it, or should he or she get a commission on it? Right. And then I understand that the person who created the prompt should own the copyright of the output. But at the same time, you know, if I'm an artist or a copywriter who, you know, willfully gave my data for that model to be trained, should I get a little bit of commission on that output? Right. Who, you know, that gets consumed downstream, you know, And with that, how does all the legal implications, you know, take place around that? So I keep thinking about those things. So when I see something like chop chop, is that what it's called? I think about that a lot in terms of how does everybody benefit from it? Because I can think of many cost centers for maintaining a large language model. But there's got to be some sort of like payments to people give their data for training this model to as a cost center, too. So that's just my take.
+
+Harpreet: [01:19:21] I'm wondering, like, does the person who created the keyboard, does he get a cut of royalties every time somebody gets paid on Medium? You know what I mean? Like, I hope that analogy is making sense. I'm just kind of saying, like, something something is is is a tool for people to to use, Right. Yeah, that's, that's, that's the thing I like that. The issue I have that is like yeah, it might be sampling a bunch of different things, but we do that naturally throughout life. We're inspired by a bunch of different things. We take in ideas, meld them, mesh them together and create something new from them. I do. I don't necessarily have to go and say, Oh yes, by the way, [01:20:00] this idea for this startup I had came to me while I was walking down the street and I saw a billboard, and now I have to give these guys like .00 5% of revenue or whatever, you know what I mean? That's that's the the issue I have with that is like that, you know, like for every house that gets built, do we send a royalty check to the inventor of the hammer? You know, I mean, uh, let's go to Mexico and, uh, and then after that, we'll start to wrap it up. I've got to head to a hockey game.
+
+Speaker3: [01:20:27] So. And this is like something that I was talking about with Karadzic for people who know my better half, right? He's a designer. He makes his living off of making really beautiful stuff. And the thing that we were both discussing is that like right now, for example, to generate the three images or assets, okay, so you throw in a prompt and you get an image. Can an artist actually work with that? Yes, but that's actually not how most designers will work with assets. Right? When you are working in Photoshop or Illustrator or whatnot, as a designer, you tend to work in layers. So for example, your background will be a layer, your items within it will be a layer. So I'd argue that like if you for people to say that Generative II is like enabling artists. You would have to show me that the output, for example, like very strictly, is in fact in a form that an artist would actually use in their workflow. Because right now, if you do an image or you do a video, it just spits it out. Like as a single file, maybe as a video, you might get the image in the audio. But once again, like that's not actually how most artists work. So to a certain extent, right. I think if we're going to make the argument that we want it to be enabling, we want to be assistive, we kind of need to actually show proof of that.
+
+Speaker3: [01:21:51] Something that I thought was very cool that MailChimp did was so we had a product called Creative Assistant, right? And so our main customers [01:22:00] are small, medium sized businesses and they actually use generative A.I. in a way that was meant to provide value to small, medium sized businesses. How do they do this? Well, the customers or the businesses would provide their design assets, so color palette, logo, sample of body text, right? And then we would essentially generate transactional emails or marketing campaigns using the assets that they provided. Right? So the goal wasn't to try to replace their business. The goal was to actually automate like a low hanging fruit task that, for example, if they were to take it to fiber to try to have to design every single asset, not only is that kind of sort of dull work for a designer, but it's also something that would be like very hard to price and like batch, right? But that's not to say that they would have to replace their designers, right? Because at the end of the day, you still need to have new creative, unique assets to put into the training pipeline to essentially get a better, more personalized output. Right? So there I think the use case was very, very clear to me as to how I was like helping our customers or users. But I think in a lot of cases, when's it happening? So for example, copilot, the reason why a lot of like engineers and open source contributors were really upset about the way Copilot was developed was because essentially copilot had just been trained on all GitHub repos regardless of the actual license that was attached to that repo.
+
+Speaker3: [01:23:23] So with open source, right, there are certain things you can and cannot do depending on the license that is part of that project. But at least initially copilot was trained on everything and no attribution was given. I think that and there's also some other examples, right, where the design elements or the style was directly like ripped off like a training data set and no attribution was given to the URL at all. Now all of us get really mad when people steal our LinkedIn post, right? I know a lot of us that have had that happen to us. We get really mad when it happens. How is it suddenly that it no longer applies to like this other [01:24:00] use case? Like why is it that our LinkedIn posts are holy and sacred? But an artist who spent like 1015 years developing their skill set, they create this body of work that's unused in a training mode where they don't even get any attribution. Why is that suddenly okay, especially if they rely on that for their living. So that's kind of my my $0.02 cost tip.
+
+Harpreet: [01:24:21] Go for it.
+
+Speaker4: [01:24:22] Because it's cheap because ultimately, like we've come down to this conclusion so many times on this on this happy hour that things are run purely for the benefit of profit. The way we the way we essentially look at entire economies is just that GDP breaks that entire cycle, right where we're looking at productivity as just the sellable asset. So if you can make something for cheaper, then it's worth doing, right? If you can write code for cheaper that it's worth doing, if you can create image assets cheaper, apparently according to our current society, it's worth doing irrespective of the implications of genuine infringement of creativity. Right. And people's ownership over their own content and material. I totally agree with you. It's completely insane. Right? I don't I think to a point you see this in the music industry as well. You see a lot of re sampled material like I listen to one song and I'm like, hang on one second. Isn't that just the intro riff to like Michael Jackson that straight out of Michael Jackson? And they're just use that as like a background beat to something else? And I'm like, All right, okay. I take torque content. How much of it is just, hey, there's that one song that everybody knows, I'm just going to slip this over and just kind of dance to it. The number of YouTube shorts and Instagram reels that I'm seeing that are literally just someone else's YouTube short that some dude is watching and you watch this guy watch that short and nod to it and shake his head and go, Yeah, man, that's not content.
+
+Speaker4: [01:25:57] At what point is that content, right? So we seem [01:26:00] to be okay with stealing shit from people as long as it's for the benefit of making money. And that is mind boggling to me, right? The saying bullshit baffles brains keeps coming back to mind for me. I should probably get that tattooed. If I ever get a tattoo, that's probably going to be it. But seriously, like at some point I see this like where this worked and I and I agree with you, right? Like, if I had to do a generative soundtrack, I would want it in layers. I would want the the drum, you know, the drum line and a separate MIDI output. I'd want, you know, the electric guitar line and a separate MIDI output and things like that. If I was to compose something generally and we kind of do that with samples and, and loops and things like that, but in the music industry, all of those loops and samples are extremely well controlled in terms of, in terms of copyright. Right. We haven't seen I hit the music generation nearly as easily as we've seen the image generation. But yeah, it boggles the mind, right? Even if you could get that in layers, is the right attribution going to the right people? It's a huge issue. And I mean, like back to the GitHub copilot thing, didn't they just get like a lawsuit filed against them earlier this month? Not this month, a month ago in early November? It's I, I mean, I didn't really think about it that way, but now I'm like, hey, hang on, I've got bucketloads of code at companies that I work for with sensitive IP, right? You're talking defense contract software that I've created that I know for a reason.
+
+Speaker4: [01:27:34] Hey, you should use this only to a level of proof of concept or this is actually a like code that works and it's tested well and it works for this. But if I know that part of that code could potentially end up in the hands of someone where it doesn't really make sense and they don't really know the context and the limitations of that code, particularly if it's machine learning models. That freaks the crap out of me. So I. I see there being at [01:28:00] some point other companies coming up. I don't know what GitLab does, whether they have any kind of copilot move that they're going to as well. But I'm seeing companies moving to GitLab. They're happy to change provider. It's just GitHub. It's a source repository. Like how long until there's someone else who just provides something? Dags Hub came across for data scientists and actually presented a little bit of a market threat at some point to a very small proportion of people. True, but I don't think we're limited from saying, Oh, we'll just use a different platform then. And I think that will happen if we see more of this. I think the issue is that it's a little less traceable when you're talking about generative stuff, right. How can I provably say that this piece of content came from me when it's a generated image that kind of looks similar but is different enough because it's amalgamated from a few billion other images?
+
+Harpreet: [01:28:56] Yeah, but it's still it's still the human has to give the prompt that has to supply those ideas with their own creativity, even though it might be sampling from from a bunch of different things. So I think it was yesterday. Yes, it was yesterday. I did a AMA session with Dr. Tristen Burns, who made like a he's called a hexagon machine. Look him up on Spotify, look him up on YouTube. He does a lot of AI generated music. And it was interesting the way he, he, he did this. I think he I think it was like 4000 or 400,000 songs he sampled and it was like MIDI files, songs transcribed as MIDI files. And he took that those MIDI files turned them into musical notes and then use GPT two to create more musical notes that he then had to go and enter into like a synthesizer and, you know, whatever you use to make MIDI music with. But he's still the one who had to provide the, the you know, he's still the one that had to provide the prompt and all that. Yeah. Um. So yeah, I'm sure we can go on this for, [01:30:00] for, for every Anybody wants to have one last closing thought, let me know because I got to start wrapping it up. Shout out to everybody that's been here through it all. Go for it.
+
+Speaker4: [01:30:10] Because the one last closing thought, everyone in the room. I think the one thing that I've learned in what is that year and a half, almost two years, like a year and a half that I've been joining this podcast, Happy hour, whatever you want to call it, is that find yourself a room of people that can teach you just how much you don't know. They can teach you, just how much you don't have a clue. I'm looking at Vin, I'm looking at Greg. The knowledge bombs. Russell making everyone across the room. I know Joe, Joe's not in the chat anymore, but geez, like the knowledge bombs dropped by everyone in this room, you know, surge, surge, half the stuff you say in the chat on the side that I just wish you said it out in the actual chat. I'm just like, okay, damn right. So everyone in this room, I'm not going to name more names because I'm just going to lose the list and we'll be here forever. But find yourself that room where people teach you that you just don't know, right? How much more you need to know. That's been this room for me over the last year and a half. I'm sure I'll find another room like that. I think I might have it work already, actually. But yeah. Find yourself that room, guys. If you're out there, you're looking for ways to grow and just learn where you are. This has been really great. Thanks. Hopefully, that's been amazing.
+
+Harpreet: [01:31:25] You're welcome, man. It's been my absolute pleasure. Thank you all for for being here, taking time to join, like. Like, you know, all those times where I couldn't host. For whatever reason, you guys stepped up and took over as host for me. Thank you for that. Thank you for being here and just chatting and creating helping me create this space. I would not have done it without you guys here. I think this is, like I said, the most important thing I've ever done career wise. And I know it's like a lot of goodness has come from for everybody in this room, just from being associated, affiliated with each other and just saw the opportunities and things that are happen for everybody. I'm glad [01:32:00] for you all. I'm so happy. I'm excited to to see. I mean, we're we're still in touch, man. Like, you know, we're still in touch. Most of us have each other's phone numbers, you know, various chats and all that. It's not like this is the the end, you know, it's the the end for now. You know, I got something with Mark and Kiko coming up. I got my deep learning channel. I'm still podcasting, right? I'm still doing like AMA sessions where you guys can jump in and have conversations with, with experts and stuff. But yeah, it's been amazing last over two years. I really, really appreciate everyone here tuning in. If you're listening on the podcast, I know there's a lot of you listening after the fact. Shoot me an email. You guys know my email address, The [email protected]. Appreciate all of you guys. Thank you so much. And remember, my friends, you got one life on this planet. Why not try to do some big change your.
+

data/hh101.txt

@@ -0,0 +1,210 @@
+HH101_mixdown.mp3
+
+Harpreet: [00:00:06] What's going on, everyone? How's it going? How's your body doing? We are here with the data science. Happy Hours. I'm live for the third time today. So you guys are not yet tired of me. You will be soon because I'm going live like crazy. I'm going live like crazy for the month of November. Today is my third live stream. I did a live coding session lecture kind of session earlier today talking about how resonant to change the world, really how the Skype connection changed the world, gave like a brief history of computer vision before deep learning, then talked about convolutional neural networks and the building blocks and then, you know, everything leading up to a to to resonate. The live coding session seen resonate in action, which is cool. Then I did a session with that. Jess Ramos I had a lot of fun talking with her, so hopefully got that a chance to join in with that. A couple announcements for what's going on next week. Next week I've got more live sessions happening next week, doing a live session on Thursday, 12 p.m. Central Time with Mark Ryan, who's the author of Deep Learning for Structure Data. I for 1 a.m. excited for this conversation because, you know, there's I feel like deep learning is a lot of hate on LinkedIn for some reason and I don't understand why and I well, maybe I have have you know hypotheses about why but but I want to debunk some of those myths and, you know, see how it could be applicable for those of us who are kind of working out of tabular database, things like that.
+
+Harpreet: [00:01:31] So stay stay stay tuned for that. I'll be posting links on on LinkedIn for you guys to join in. And then again on Friday, I'll be talking about efficient the efficient family of models, and we'll see that implemented as well in my favorite low code training library called Super Gradients, which also happens to be the library put out by DC. I wonder. Coincidence also launched the the Community Deep Learning daily deep learning daily dot [00:02:00] community. Guys check it out it's I'm trying to build a one of a kind community for deep learning practitioners those people who are in industry who are solving difficult problems but also make it welcoming and inviting for people who are early on in the journey in the community. We've got like people like Co Sub and Richmond, al-Awlaki and Lou Rivera, who's there's people in there who are like doing like the ML ops side of deep learning and computer vision, which is amazing.
+
+Harpreet: [00:02:29] And then we've got people who are joining that are kind of early on and then people like me who are kind of meddling in the middle. So it's the community for for deep learning enthusiasts, a place for you guys to come ask questions, join in on live events and all that stuff. And I'm proud of this, you know, building something from the ground up. It's it's hard work, but I'm happy to be doing it. So I hope you guys can join. That being said, those you guys that are watching on LinkedIn, all of your questions and comments are welcome. So please do let me know if you have questions or comments. And then also all of your engagement, all those likes, all those reposts, those are all welcome as well. Spread the word, man. Happy hour. What's going on? You know what else is going on? Layoffs, people. People getting fired. Left, right, center. I wonder who were who wore it worst. Let's go to Vin and talk about that. So first, just give us give us a recap of this week. Companies are getting laid off and who was doing it? You know, who was running at the worst? Go for Vin.
+
+Speaker2: [00:03:26] I think there's something like 30, 35 companies this week, just like this week alone that ended up laying off in the tech startup space And bigger ones, you got Stripe that laid off, Lyft laid off. Twitter is the big one today. And when you say like, who were it worst? I think if you're looking at Stripe and Twitter, I think both of those are the worst looks because you've got companies that like, why are you all of a sudden dropping a ton of people? For Twitter, it's because [00:04:00] Elon showed up and it sounds like he violated a bunch of laws. In Ireland, you're supposed to give 30 days before doing a mass layoff. That didn't happen in the US in California. I think it's 60 days. It didn't happen. So. And not the system that he used was something like you got an email or you didn't get an email. And some people were getting locked out of their accounts last night before they got the email. So they were learning because they got kicked off a slack. That's not the great way to learn. You just got laid off, especially from a company like Twitter. When you listen to the way people that work there talk to each other. That's a community. A lot of people that work there long term love that place. And so laying them off that way, it's everyone now looks at Twitter differently. And it's the same thing with Stripe. And I think companies like Peloton have done terrible layoff rounds. That's another company that. And what are you doing? But if you look at most companies right now that aren't profitable. You know, their stocks are getting destroyed. And so even if there's no reason for them to lay off, they're going to be laying people off just because their investors are saying, look, you can't you can't keep losing like Uber.
+
+Speaker2: [00:05:19] You can't keep losing like $1,000,000,000 every quarter. You just can't do that. There's no way to have any sort of valuation behind you. So that's what's driving it. Investors are basically saying, look, we're fed up. And I wrote a little bit about how different types of investors are cycling in last week. And one of the big themes now is when you go from long term investors to short term investors, short term investors are all about 12 to 18 months. And so if you've got initiatives that are running that are going to be profitable for 24, 36 months. They're not going to put up with it. They're going to be saying, just cut that entire group. And so that's what's happening at some of these companies. And the layoffs are being done so badly. You [00:06:00] know, there's no such thing as a good layoff. But if you can give people advance notice, if you can talk to people and say, look, this is coming, we're in trouble, like Google's great job, kind of laying the groundwork. Back in June, July, Metta did the same thing. We're tightening our belt. We're going to get smarter about things. Microsoft in different groups that were going to be impacted. The same thing. They said, you know, it's coming. We've got to reevaluate. We've got a freeze. We're going to be smarter and more strategic about how we hire. So there's companies that are doing it better where they're basically saying, look, this is coming and they've been clear about that for months. So no one's no one's being caught off guard. Everybody has enough time to prepare. But when you tell somebody a week in advance piece, that's just. That's the worst.
+
+Harpreet: [00:06:51] Russell, I'd love to hear from you. You had some commentary before we were on on on air. We'd love to hear from you. Shout out, Joe. Risto. Good to have you here again. We're talking about layoffs and things like that. So if you got any. Yeah. If you got anything on your mind in regards to that, I'll call you up after Russell and then shout out to everybody on LinkedIn who's watching. And Jennifer and A.V. guys got commentary that you wish to contribute. By all means, let me know. Russell is here from you.
+
+Speaker3: [00:07:18] Thank you, Abby. Yeah. So my comment was, as an outsider of some denomination being from the UK rather than the US, I'm interested to know what the perspective opinion is on these types of layoffs from the big companies, especially Twitter, which I look at being an extraordinary event after Musk has purchased the company and then affected these layoffs, plus the others like the Amazons, the Metters, the Stripe's, etc., that are huge, big companies that have hired hard for a long time and had a lot of workforce and are looking to make more efficiencies now. So it could be considered something that could have been strategically [00:08:00] forecast a few years ago possibly. Is that different to any other technology companies that are operating across the wide spectrum from, you know, web3 into data, into anything else that's technologically driven? And if it isn't, is there hope for those that are subject to these layoffs to find employment elsewhere in other companies? And where might they best look at this time?
+
+Harpreet: [00:08:30] Vivian or Joe Diaz won't take a stab at this.
+
+Speaker4: [00:08:34] Can you paraphrase your question? That wasn't.
+
+Speaker3: [00:08:38] Sure. Okay. So so I was saying, so the people that have been laid off now, the big layoffs from the tech companies, Twitter being kind of in the room on its own is Elon Musk just took it over and the other big tech companies have hired heavily for a long time and had a lot of people. So maybe it could be considered just an efficiency drive after so many years of a lot of hiring. Is that different to other technology companies in similar environments that aren't so big or haven't gone through such extreme situations such as Twitter, etc., that may not need to lay off so much? And therefore. Is there additional advice we can give to those that have been subject to the layoffs of what type of companies to look at if they are exiting the Twitter's, the methods, etc.?
+
+Speaker4: [00:09:27] Yeah, for sure. I mean, I know startups that are hiring right now and, you know, companies that are still hiring. And so I would say that for those companies this is a blessing. This is this is the one that they've been waiting for. If anything, it's like if you know how hard it is to find engineers, especially in the Bay Area, it's insane. So, yeah, I would say that for people looking for work, you know, I mean, keep your chin up. I know it sucks and I've had that happen before. You know, getting laid off and it's, you know, it hits your ego. It hits your pocketbook, obviously. But the thing you got to realize is, you know, there's you [00:10:00] know, hopefully you have a good network of people and hopefully people are looking out for each other. But, you know, you'll find something, hopefully. But the big tech companies, it seems I mean, there's been a lot of studies on this, or at least a good analysis, I would say, of like the the head count versus the revenue and versus the the output of these companies. It was just pretty clear. A lot of these you know, in hindsight, everything's really clear. Now we can, you know, trash talk the decisions that everyone made for the past few years because this is the easy target. But, you know, there's definitely there was definitely a lot of hiring and kind of overshooting things. And but the strategy that worked in a zero interest rate environment doesn't work now. And rates are high. That's just it's Warren Buffett always says, you know interest rates or the gravity on asset prices and when the party stops, you know, kind of find a new party, whatever that looks like. So, yeah.
+
+Harpreet: [00:10:52] It's an interesting point you made there about, you know, how hard it is to find engineers. I'm wondering, is there a is there is there a I don't know if class is the right word. Is there like a department or function that is usually up on the chopping block before everyone else? I mean, my intuition tells me that if for in a recession we're going to downsize, we should probably start getting rid of HR people first. But I don't know if that's correct or not, but I'd love to get your insights on that event. By the way, those of you guys watching on LinkedIn, smash that like, yo, smash that like and let me know if you got questions. I don't know what's been going on with LinkedIn. I can't see comment during my livestream. So if you do have a question, please do send it to me as a PM and I'll make sure we get it up here. Dm Whatever the hell is called. Go for it.
+
+Speaker2: [00:11:38] Vin Yeah, don't be a recruiter right now. Let's just Oh my goodness. I feel horrible for recruiting departments that are losing 75. I mean, I've heard ten person teams going down to one. You know, it's just brutalizing right now, especially in tech companies who are looking at the recruiting [00:12:00] team and saying.
+
+Speaker5: [00:12:00] That.
+
+Speaker2: [00:12:01] You're all gone. Marketing is another one that's just been getting hammered and it's not marketers. The the top end marketers themselves, the people that are really good at being creative and building the campaigns. It's the administrative and support staff that have just been whole, you know, and at the sort of a lower entry level in marketing, it's been brutal. If you're in any of those types of roles. And so if you if you're thinking about getting into data science from a different role, it's, you know, race into maybe an analyst role, take something that's a little bit lower down right now, chase into maybe a software engineering role or data analysts role, try to get into something out of recruiting, something that's outside of marketing. Like I said, there's entry level roles. Or if you can get into one of those creative roles, great spot to be in the other teams that get absolutely devastated, our innovation and advanced R&D teams. Any company right now that's looking at an initiative, you know, 24 to 36 months out, like I said before, it's going to produce any sort of revenue. Those are going to be on the chopping block. And any teams that are the primary engineers, developers, data scientists, they're going to be going with them.
+
+Speaker2: [00:13:19] In some companies you're going have the opportunity to transfer, which is cool. There's there's a kind of stack ranking, though, so if you're not one of the hyper. Formers on that team. You may not have a seat when the hokey pokey is over. So it's really looking at yourself with Does your team support core business? Is it essential? Is the role that you have essential, or would a slowdown in business mean that you're not as necessary as you used to and you don't need as many people to service the accounts that you have? That's another one that's going to be in trouble. And if you're really if you're a low performer right now to company. Great time to cycle [00:14:00] out because in the next 12 months, if you're in that bottom 50%, you're pretty much I mean, I don't want to say guaranteed because nothing's a guarantee. But if you're in that bottom 50%, you're in a lot of a lot of danger of being laid off. And sometimes it's just better to start clean. You can end up going from a low performer at the bad job to a high performer or a better place for you.
+
+Harpreet: [00:14:23] As a developer relations professional who's typically housed in marketing, your words frighten me. Should I be? Should I be worried? Should Devereaux? Is Devereaux and developer advocacy, especially those within marketing functions at risk? And if so, what can I do to to help secure my job and identify? So you had your hand up. So if you had a question, we will get to it to you right after.
+
+Speaker2: [00:14:45] Go for this. If you're in Devereaux, you're. You're going to be safe at some companies. If you're at a machine learning company, deep learning company, anything, that's data science first data first Data engineering first ML Engineering, ML Ops. Yeah, you're pretty safe because without a developer relations role, I mean, it's really hard to get anybody to buy until they understand why they're buying, what they're buying, what they'll get out of it, how to pitch it to the sea level so that they can get some budget and approval for it. So in those companies they understand the ROI, or as long as they do understand the ROI, then you're in pretty good shape. But in other companies who are just toying with the devil, especially companies where software isn't their core business, that's where there's a lot of risk because some companies are looking at it as a growth area and so far it hasn't come, it hasn't gotten to positive revenue generation and it doesn't really have a good path to profitability. Those are the areas where marketing spends on anything really is in jeopardy.
+
+Harpreet: [00:15:53] It makes me feel better. Thank you, Vin. Jennifer Yager, Hand-raised Gopher it good to see coach lab in the house coast have got the mic [00:16:00] and the headphones. They goddamn look at you man. Go for it.
+
+Speaker6: [00:16:03] Jennifer Really, just to add on to what Vin said, anything that isn't part of a business's core value chain is going to be at risk like it until we also put PMS and operations in with the other cost centers that are evaluated in times like this, or teams where management believes that a function could be done centrally and support a broad audience, that's another one that's sometimes at risk. Now, let me tell you the flip side, and this goes back to Russell's question. A friend of mine was was given notice at Intel several weeks ago. I think it's just two and one half, maybe three weeks ago now. He is already deep into interviews expecting two or more offers next week. So, yes, it it stinks. And I am troubled that Intel is letting him go. But at the same time, I'm thrilled that there is a marketplace for analytics for engineers. It's still out there. It's a shift.
+
+Harpreet: [00:17:09] You had 20, 20,000 layoffs or something like that. That's just huge.
+
+Speaker6: [00:17:15] If Bloomberg was not accurate, it was an inaccurate rumor. But yeah, it still is.
+
+Harpreet: [00:17:20] So yeah, yeah. I remember being at the Intel Innovation Conference just a few weeks ago, months ago. I can't remember. It was recently ish. They're coming out with some new like GPUs and stuff that I'm really excited and excited for. That's going to be definitely, definitely a game changer. It Koza. What's going on, man? How are you doing? Nice setup.
+
+Speaker5: [00:17:43] Yeah. So it's with a bit of an update. I don't know how this sounds. I'll find out when I hear the record.
+
+Harpreet: [00:17:49] Man, it's good. Do you want to be hosting a takeover? Looks good.
+
+Speaker5: [00:17:53] Depends. Do you mind the unnecessary levels of reverb? But. So I just [00:18:00] got this thing plugged into my mixer that I use for practice and stuff, so I just thought I'd update it. The job market in Sydney is, is is weird. It's it's in a strange spot right now. Like, I mean, I'm just listening to what you guys are saying so far and it's weird because we've got the same kind of thing, right? Like we're seeing some companies laying off 30% of their force, 40% of their force in Australia. Right. And not just in Sydney like Brisbane and Melbourne, etc.. And we've got other companies that are doing pretty well and, you know, just snapping up talent. So it's weirdly a bullish market for people looking for jobs. But also at the same time you're seeing people on the other end of the spectrum as well. So it's it's strange. Again, it comes down to something we've discussed a few times in the past, right? Is that where is that band of 4 to 10 year kind of experience, people that you know, have enough experience to make a significant impact but also aren't right at that top end of the spectrum in terms of pay for companies to actually be able to afford people.
+
+Speaker5: [00:19:03] So I think that's what we're seeing play out at at this stage. And I mean, we've we've got like a kind of a controlled inflation situation going on in Australia right now where, you know, every every month or so, the Reserve Bank is bumping up interest rates by like 0.2 5.5% kind. Just to kind of avoid jumping neck deep into into a recession. I don't know the first thing about that. But what I'm seeing is companies just getting really wary on where they're investing their their talent and just kind of consolidating it into experienced talent more than anything. Now, I just don't know what that looks like. I have no experience at any of this. These the first time that I'm seeing any kind of significant economic change in my career. So I'm just like keeping an eye on the horizon and going, okay, interesting stuff. But at the same time, there are so many companies hiring that. I don't know. [00:20:00] I don't know what to make of it. Right. It's. Still seems pretty positive a lot.
+
+Harpreet: [00:20:05] That Vivian got said. Oh, that's not Vivian Venus been, but a shout out to Vivian. Good to have you here, Vivian. I've been saying, can your Fed call our Fed and work on that not jump jumping face first in the recession thing. Talk to us a little bit about that. And I want to go to Joe after that, because, Joe, you were recently in Australia. I'm wondering what you thought she had around the Australian like data science, data engineering type of market. But first, then then Joe, and if anybody has questions whether you are on LinkedIn or YouTube or wherever it is that you're watching, please do let me know. I'm happy to take all of your questions and comments.
+
+Speaker2: [00:20:40] Yeah, I'm just our currency in the US right now is like a sledgehammer or a wrecking ball. More like when you look globally trying to do business right now in the EU or anywhere is so much harder than it was six months ago. That's kind of it. We're we're raising rates really, really fast comparative to most other countries. And so the US dollar is just going it's so much higher than all other currencies that we're taking hits with all the companies that are doing business internationally. And like my courses internationally have basically they're 20% more expensive now than they were six months ago. And trying to normalize pricing internationally right now has been a nightmare. So there's yeah, we need to we need to call up maybe some people on the Fed and say, you know, yes, raise interest rates, maybe not as.
+
+Harpreet: [00:21:37] Fast.
+
+Speaker2: [00:21:38] Maybe maybe slow it down, you know, stretch it out a little bit more. We've got time. We have months. We can. Slow down a little bit. Maybe not 75 every single time.
+
+Harpreet: [00:21:52] As somebody who is going to be building a house soon, I'm hoping that these rates cool down.
+
+Speaker4: [00:21:59] Ooh, I'm.
+
+Harpreet: [00:21:59] Sorry. [00:22:00] Quickly. Well, you know, we're still the land is you know, land is secure. We just need to.
+
+Speaker4: [00:22:05] I just finished Paul Volcker's autobiography. That was fascinating. It's called Keeping at It. And Paul Volcker was the person who crushed the back of inflation back in the the early eighties. But it was interesting getting his take because he there was a bit of a head fake when. So inflation for context had been running rampant in the seventies and through the early eighties and the order of like double digit inflation. Like I think the Fed funds rate was like 11% and mortgage rates were 18% of their high, which when you think about that, cost of borrowing is insane. I mean, inflation was obviously running really high as we had to raise rates. And so his whole thing was you just have to be very merciless with this thing. It's a monster that if you don't kill it, it will come back. Which it did. The head fake part was, you know, inflation looked like it was under control. They took the brakes off and came roaring back. And so in Volcker's view, and I think this is what Powell is doing, is it just you have to kill this at all costs. You have to crash the economy and there's collateral damage and it is what it is. It sucks. But you get that or you actually get a much worse situation with inflation. If you've seen hyperinflationary economies, that's not very fun either. So it's but that's what happens when you print trillions of dollars and you carpet bomb the economy with it. And so that's super fun. Australia, though, let's talk of Australia. What a great country I hung out with close to. But it's great to great to meet you in Sydney. Yeah, the day to day community there is awesome. It's it's alive and well. I feel like there's, you know, it's yeah, it's going strong I suppose, in Melbourne and Sydney and I felt like both communities were awesome and everyone seemed pretty positively as far as I met the economy in Australia felt like it was different.
+
+Speaker4: [00:23:51] I talked to an American who actually lives there and he felt like it was America. It's like America, but things just move a lot slower there. It's only, [00:24:00] you know, and America is a land of like extreme ups and downs. There's not really like a middle here. It's not like you sort of, you know, when the highs are highs and the lows are lows and we're going to the low lows. But when it's high, it's real high. It's pretty schizophrenic around here. So it it's really felt a lot more even keeled. But even so, you could definitely tell that, you know, people were kind of skittish when I would talk to people about the prospects of their employment and whatnot. And it's the same here. So it just seems to be everywhere. And same with the UK. I was just in London, actually saw Russell there, you know, and that was it was cool to hang out, but same sort of thing, you know, I don't think anyone was really, really stoked in the situation. I mean, I wouldn't mind. Is it Russell? I mean, your Prime Minister was on the way out, so I was like, if people ask about America, be like, well, at least we're not. We don't have that problem this week. So but yeah, it's strong American dollars. It's a good thing if you're traveling, but it's a crappy thing if you have to export anything. So it's not like going to Australia was awesome. In England, I felt like went to Mexico, so that was great.
+
+Harpreet: [00:25:04] They get paid in US dollars for Live in Canada and it's beautiful. I love it. Hello.
+
+Speaker4: [00:25:08] Lucky you. Yeah.
+
+Harpreet: [00:25:10] I make more than most doctors in Canada, which is funny. Shout out to people For some reason it's hard for me to see live comments on LinkedIn, but I do see a few here. Shout out to Rodney Beard. Man, I haven't seen Rodney or heard from Rodney in a very long time. Good to have you back here, Rodney. Warren Simmons is saying I have seen several recessions already since 1990. In the markets where I've worked, one things holds true Keep true to your ethical standards in whatever you do and maintain your standards. Be compassionate with your colleagues who get the chop. What goes around comes around. What are your thoughts on like Elon Musk? Like just blame everything on Elon Musk. But those Twitter layoffs, those fake fake Twitter layoffs, like he hired actors to to pretend to be like, fired. And then all I saw all week long on my Twitter feed was people poking [00:26:00] fun at that like I was the PM in charge of, like, the bookmark thing or something like that. Yeah. What are your thoughts on that, hiring actors to pretend like they got to that?
+
+Speaker3: [00:26:11] Did you see the names of the people out there? Were strategically chosen names altered in a certain order?
+
+Harpreet: [00:26:18] Yeah, yeah, yeah, yeah. That was. That was interesting. Yeah. So. So how do you tell if a recession is going to come for your particular role? What are some warning signs you should look out for? That the support that then will go to use the resident expert on layoffs. What signs should I look for at my company to kind of gauge whether or not I should temper my fear of getting laid off?
+
+Speaker2: [00:26:58] The big one is when people stop caring about what your deliverables are like. That's a huge that's big. And that usually happens maybe a month or two before you end up getting laid off, because these decisions are usually made beginning a quarter or a quarter in advance because there's a lot of reporting requirements and that sort of thing. So you'll know about 30 to 90, 30 to 90 days in advance if your workload suddenly isn't on anyone's radar. You're not getting invites to meetings that you used to. No one cares. Pms don't talk to you about your deliverables anymore. If you're asking what are we going to be working on after this project? And no one really knows. If you're supporting a business unit that they keep talking about winding down and they don't tell you where you're going next, that's there's most leaders will give you the hint, hint, nudge, nudge, warning that something's going to happen. Nobody [00:28:00] can say you're about to get laid off. But if you're looking for, you know, kind of your workload falling off a cliff or your involvement in other projects falling off a cliff, that's your leader is giving you the the. Yeah. Know your jobs. It's totally safe. And the biggest rule is if you have a first round of layoffs and somebody specifically comes to your team from a very high executive level position and tells you all your job is safe, it's not, you're done. You're in a lot of trouble. That's it's like the biggest lie. And it only happens when they intentionally come to your group and tell you, no, everything's cool. It's not.
+
+Harpreet: [00:28:43] Anybody have thoughts or comments on that? Vivian, go for it. Good to see you again, my friend. Been so long.
+
+Speaker6: [00:28:49] I know. I'm sorry. Actually, my partner, Eric, had surgery. He had an acoustic neuroma taken out of his head, which is a fun thing. I encourage everybody to look up. Anyway, so that's. I've been, like, dealing with him having that surgery lately. Anyway, I wanted to mention also that sometimes you just really don't know when you're going to be laid off. And it really comes as a surprise and there are no warning signs and. I don't know. I guess I just feel like as someone who's been laid off a couple of times. When the market starts looking scary or we're in times like this. I just always like. I have a card in my back pocket of what I'm going to do, you know. And I definitely don't think that that's a stupid idea to like. Create your backup plan. But as someone who has been part of layoffs before, the good thing is that [00:30:00] I've never I've never been part of a layoff in which there was truly no like. Compensation or something like at least like a few weeks or something of pay first. And so then then that's kind of how I like usually think about it is like, okay, if I found out tomorrow that I only have like four more weeks or like two months or whatever of, of work of pay left, like what, What would I do? And like, how could I prepare myself to like, if I get that news, like be willing to jump so that I can, like, act quickly. So I don't know. I think that it's great to try to look out for like what I was talking about, but sometimes it truly is like a surprise, even to your boss or even to your boss's boss and like. I mean, unfortunately, that's the world we live in. And sometimes you just really don't know. And it really comes as a huge shock and surprise. And the best thing you can do is like, be ready to spring. Should the bad news come?
+
+Harpreet: [00:31:05] But sincere that metta and that ever happens to you. You could always teach people how to get into data science because you have that clout.
+
+Speaker6: [00:31:13] I mean, I guess so. I don't want to lose my job. I like my job, but I do. There are a lot of people that have been like, Oh, well, you're fine because you now have men on your resume. And I guess in perspective, I, I am grateful for that. But I also still really don't want to lose my job.
+
+Harpreet: [00:31:36] Yeah, Yeah, I've been thinking about that. Right? Like, okay, like if I was to ever lose my job, at least I think I know what I need to do in order to, like, pick shit up and do stuff like on my own immediately. Like I've taken enough of those of those marketing courses to know what I could do to kind of build something from scratch. But yeah, [00:32:00] I'd never, never want to actually lose my job, especially because I love it, dude. Like I, you know, I see all these posts on, on LinkedIn from these, you know, and Twitter from these people talking about the rat race and, you know, working 9 to 5, blah, blah, blah. It's like, dude, like, I kind of like having an actual job. Like, I love it. Like it's cool. Like, I love the work I do. I love the company I'm at and it's a lot of fun. Kosta Go for it.
+
+Speaker5: [00:32:26] Yeah, this is something that's been playing on my mind a fair bit in the last, like maybe the last week or so, right? I mean. There is. I can't remember what there's a particular term for this, but there's a law. Someone please shout it out if you know which it is. But. When negative news or lies garner more attraction than truth or positive news. Um, and while I well, I'm in no way telling people not to speak out when they're facing negative work circumstances. I think we can very quickly and easily rabbit hole into just, you know, the algorithm feeding us more examples of people hating their job. Right. It's so easy to fall down that spiral and rabbit hole and then you start turning around and looking at every job and every company and every person is, Oh, they're out to get me and they're out to, you know, lowball me on my salary and do all sorts of terrible corporate corporate crap to me. Right? It's it all it almost turns into at some point, I want to turn that noise off in the week. Like earlier this week, I was like, actually, I'd like to hear a few more positive stories about people enjoying their job or people excited about the work that they're doing right, because everything we're doing all the all the technology that we're working on, we all got into it because [00:34:00] it's crazy exciting, right? And we don't hear those stories shared nearly as much. Either that or the algorithm's been feeding me some seriously negative stuff for the last two years, right? Know, one way or the other, I'm not entirely sure which, but I do think we do tend not to share as much the positive aspects of day to day work.
+
+Harpreet: [00:34:26] Speaking of positive things to shout out to, Eric Sims just got his house, so that's positive news, man. Eric Simms If you're listening for watching Shadow Team and super happy for you. Super excited for you. But yeah, like I love being a developer advocate. I like it better than being a data scientist. To be completely honest, I absolutely love Denver more than just being a data scientist, and I think it's just personality thing. It's like I get to teach, which I like to do get to create content, which is fun, and I don't have to worry about fighting uphill battles for data strategy and getting that shit, you know, done. There's other strategy battles that I got to fight, but for the most part, I'm excited to fight those type of battles. Then also some commentary on that on that as as you crack it up.
+
+Speaker2: [00:35:23] Yeah there's it's Yeah. Strategies. It's a good business to be in right now but yeah, there's a whole lot of knife fights happening at the sea level right now and it's because we're swapping from FOMO, running the business and technology running the business because of FOMO to strategies back. And many of the strategists now have axes to grind because they've been kind of slapped around for the last five years. So there's yeah, there's some knife fights going on right now. There's some interesting politics coming back into play. And it's [00:36:00] weird to watch the pendulum swing so hard, so fast to strategy being everything now. And any time you hear anybody talking on an investor call, it's always strategy. You know, we're going back to core strategy, returning to a more strategic way of this, that or the next thing. So yeah, I'm having fun, but I can imagine literally no one else would.
+
+Harpreet: [00:36:23] Is there a difference between like strategy and process? One thing I know about myself is that I don't like too much rigorous process for some reason. Too much process feels like it creates too much chaos and entropy for me. Like I prefer to to have as minimal process as possible, but I feel like that is different than strategy.
+
+Speaker2: [00:36:46] Yeah, process is more your workflow, and so you can have a process for strategy planning, You can have a process for implementing strategy. So there's connections there, but that's really the steps workflow work, products, judging quality, assessing when you're done building timelines and that sort of thing. So strategy can dictate process and strategy contains processes and frameworks and systems. But when you start talking about real digging down to the process, like what you're saying, that's more workflow and trying to maximize optimize. So people really like structure. And I think the more creative you are, the more you rebel against structure, but the more you end up benefiting from structure because you you'll realize your creativity can actually be applied to making your job better. And it's one of the things Bill Gates used to say, I hire lazy people because they always figure out the fastest way to do something. Lowest effort, easiest way. And he was really talking about optimizing processes. It was just a fun way of saying the same thing where Irish people that optimize because they don't want to work hard on a particular item. And so there's some strategy [00:38:00] to that. And even creative people, you can build more, you can create more if you have a structured, rigorous process for it. It just feels like you're constrained because you don't really get the opportunity to continuously improve. But if you look at concepts like lean or real manufacturing types of continuous improvement and Six Sigma, it's a really creative process because anyone at any point can step up and say, Look, I think that's busted and here's a better way to do it. And if you can prove it, your idea now is the process.
+
+Harpreet: [00:38:35] I like that a lot. I think even a higher, lazy people. I love that. This brilliant. Yeah. Like the type of process I hate is just like the nitty gritty ness. Like, you know what I mean by that is like, okay, if I'm, if I'm doing a certain thing, then there's like 12 different other things that's associated with that. One thing that I need to get done and I feel like it gets in the way of getting the most important thing done, that I'm being kind of abstract there, just being a process. Kosta was kind of moved into role, where I think process is a lot more important process strategy you're doing like the data pipelines and stuff like that with, you know, with respect to computer vision and deep learning, which is, which is interesting and fascinating. And you know, you're mentioning to me that you're reading Joe's book a lot for for for guidance there. Talk to us about that. How's that shift moving from the engineer model builder to the.
+
+Speaker5: [00:39:35] So so I'm moving back into the pipeline building space like I probably over the last year, what happened was I went from full time model builder to a pipeline builder because we don't have our data labeled because it was at a new role. And then the last probably eight or nine months have been working predominantly on the, you know, operationalizing those pipelines. And a lot of it comes down to what processes do you have in place to use [00:40:00] a lot of the tools that you've got because you're never going to have like it's a it's a beautiful state that we all dream about as engineers where everything is automated and everything is got code for it, right? Not everything is code and. In order to plug in all the gaps. That takes a lot of development time, right? So where you can't automated or where you can't design it out, you have to have some element of process thinking that that comes into it, right? And even when designing your systems, having that understanding of what the actual process is often helps you find really efficient solutions to it from a code standpoint. Right? So. I found. And I always find that it's different kind of thinking. Now, I'm sure you guys would have all heard of disc analysis at this point, but for people who haven't out there, Vince got that smile on his face. I'd love to know what your thinking is on disc profiles.
+
+Speaker5: [00:40:59] But from what I've seen, this sort of for people who haven't heard about it, disc is basically dominance. I think its influence, stability and compliance right now, typically high compliance personalities, not me, are typically very process oriented and are very happy to follow protocols to the team because they see the value in that right and they're able to follow that. It's just a natural personality thing. Now everyone has like an adaptive and a natural personality. My adaptive personality is a lot more process oriented, so I can switch into that. Earlier. Earlier on my career, probably five years ago, I wasn't able to switch into that at all. Like, that's not my natural mode of thinking, but I've started to see that value in having that side of it so I can switch into that as needed. The interesting thing is. When you've got a team that. All of us, you know, don't have that aspect in our natural personalities. It [00:42:00] makes it quite difficult to come up with solid processes and actually follow them because there's a much bigger likelihood that we'll want to design our way out of trouble. Right. Or use our expertise and our our own skills because it's just quicker for me to throw together a quick script to do that, as opposed to think about a process that's kind of bulletproof that anyone could follow. Right. But the downside of that is that you've got a team where people are working for long periods with their adaptive personality, and that's pretty tiring, right? Like, try that for six months, ten months.
+
+Speaker5: [00:42:37] It gets very, very tiring for a lot of people. And that's that's quite honestly the truth. So it kind of comes down to what side like what what stage is your is your organization out or your product out or your your process and tooling at and what's the right balance of personalities that you need on your team Because skills can be taught, right? Natural personalities, having people who can think a bit differently, people with a different background and experience, right? The the only reason I have even remotely some idea of what, you know, a high compliance person, how you would do or process thinking would do is because I was really bad at it five years ago, spent some time in manufacturing and they showed me that weakness in a big way because the people out there were fantastic at it. Right. And I just didn't have a clue. So over the years, I kind of built up on that weakness and just said, okay, I need at least a bare minimum and to the point that it become something that I can switch on when I really need to. Right. But from a process thinking standpoint, that's the main thing is you've got to be able to identify the value in processes. We, especially in the data science and the machine learning kind of community, I think so many of us prefer to be model builders, right? We prefer to be.
+
+Speaker5: [00:43:59] And [00:44:00] the weird thing about that is, I mean, look at the code, look at data science code. It's low compliance. How much testing do you see in data science code? How much are engineering rigor do you see in data science code, Right. Like you're laughing because you know exactly what I'm talking about. It's like we're only starting to turn that curve now. And people like Mike Kerr, people like Joe, they're ahead of the game in terms of looking at things like envelopes and data and data engineering and things like that. Because there's that realization that, hey, actually guys, we can't do this all as experimental notebooks. We need to start thinking about how do we apply engineering rigor, and that's both from software engineering rigor, but also process rigor that we've had in every form of engineering for the last few hundred years. Right? So that's where like I'm leaning back on some of those books, like I've started reading more of Joe's book to just get a better understanding of more data pipelines because I'm heading back into the data pipeline aspect of things with the job that I start on Tuesday. Super excited about that. But basically, yeah, it's we just need to understand that there is a bit of a heavy feel towards your more experimental personalities in the industry and we're slowly seeing that turn the curve right.
+
+Speaker5: [00:45:17] We're starting to see a larger variety of personalities enter that barrier for expertise get lowered so more people from different backgrounds are coming in. I think we'll see that level out as we need robustness. We'll bring in the practices that robustness needs. Put it this way, right? Nothing, nothing that was designed as a safety need mechanism was ever designed before it was needed. Right. Halos on Formula One cause didn't exist right for a very long time. Like the front stalk of the halo didn't exist. And I was watching a I forgot who it was. But there was a video of a Formula One driver from a few years ago before the halo was there, getting hit above the left eye by a spring. Right. [00:46:00] And it's just mind blowing that that's a danger situation that they hadn't considered. Now the halo was brought in to deal with that. Go back to what was it, the sixties, the Tylenol poisonings. Right. And I think it was Chicago, right? We didn't have like tamper proof bottle tops on that. That seems so obvious now. But we wait until we need robustness. We wait until we need systems before we actually build them. And we're starting to see that acceptance of, hey, we need good data engineering come into play. Right? And probably that reflects at a strategy level like what you were saying before, been where previously it was just we just need to go fast and now they're like, hang on, we need to do this.
+
+Speaker5: [00:46:41] Right? So that's the main shift that I'm seeing from a high level. And I'm I'm kind of excited to head more and more into the hey, build more data pipelines, build more, you know, ML engineering stuff as opposed to, you know, the models themselves. And I am starting to see that that value be recognized more by employers and companies, right? Whereas previously every company was just looking for data scientists. Right now companies are actually like, no, we have we have data scientists. We also need ML engineers. We recognize they're different and the value that they add. So it's a little bit of an ego swallow, right? Like I spent like a couple of years learning, doing a master's degree on how do I build models and all that stuff. And now I'm not building any models, am I still adding value? That's the ego pill for me to swallow and understand that yes, I am in these ways that other people probably can't add value in, right? So those are the things that are going through my head. When you talk about, hey, process will hold versus going from building models to building processes and building pipelines, That's the mindset shift that I've been kind of traversing the last year or so. I'm quite enjoying it actually.
+
+Harpreet: [00:47:55] That's awesome, man. Yeah, I've [00:48:00] never been like part of a proper engineering team and I have never had anybody like to show me like the ropes. I've always my roles have always been like, you know, statistician, data scientist and not, you know, much engineering like people around me. I wonder, like, how can somebody like, you know, that that being a solo data scientist, maybe they don't have all that support or a robust team to learn all these practices, like what do they start doing to, to learn these type of, you know, mindset shifts that you're talking about, essentially.
+
+Speaker5: [00:48:36] Go join those teams. Yeah. Like all due respect to all the books and courses out there, they will help you. You'll get that 10%, 20% knowledge that you otherwise wouldn't have access to. That's just helping you get access to information. That's second hand, third hand learning. Right. Go join those teams. Otherwise you're never going to get to see it in practice. Right? Like, honestly, I was at a robotics company from 2020 through to 2021, mid 2021, and it was great. I was building models all the time and I was building stuff that I look back at today going, You're insane. You're wasting a lot of energy building that stuff, right? If I just built it right and I didn't have the team around me to tell me what the right way is to build it. So I ended up building arguably some really janky shit, which still runs well today. Right? Like, that's just I'm thankful that I wasn't that much of a dope, that I built something that's going to explode the moment that I leave. Right. It's still running a year or so later, but what, I do it differently now. Absolutely, because I want to join that team to have a look at how to how do teams outside of robotics do this? Because I know teams outside of robotics do this right, like secede for models and model development pipelines. That's not rocket science like, I mean. [00:50:00] It's it's really not like many, many, many teams are doing this to the point that we have like literally dozens of off the shelf tools begging and vying for our attention.
+
+Speaker5: [00:50:11] Right. So how do we actually do this? That was my kind of initial quest, right. And now kind of extending that further. Right. So I wouldn't have gotten that opportunity to see that firsthand. And I don't think the lessons learned would have been there first hand without the right team. And there you can learn to a point on your own and then you start to plateau. And then you need seniors. You need principals who have four or five, ten years on you. Right. Like it's it's yeah, you need that. You really do. And you need the the time on the job to be able to focus on that as well. Right. When you're highly operational where the the you know, the pipelines are already up and built, you're not going to get many opportunities to go through and examine how the pipeline is built because you're focusing on operationalizing those pipelines and actually using them to deliver the outcomes. That is a very different role. You're not going to get the chance to spend the time in building the pipelines and re architecting and getting your designs reviewed. Go from literal design review stage, right? It's just not going to happen nearly as much. So, yeah, no, go join those teams. Find the people with gray hairs more and more gray hairs than you and ask them every question that comes to mind and just drain their knowledge. That's kind of my goal right now.
+
+Harpreet: [00:51:34] Don't get fooled by people with gray hair because I have a lot and I know nothing. So Rodney St excellent points coast up. I finally see comments on the LinkedIn post but yeah, excellent points and yeah, any other questions, comments going on? Anything else on anybody's mind. Bingo. For a man.
+
+Speaker2: [00:51:53] Yeah. Actually I have a question for Joe. I was just you kind of listening through all of this. Are you seeing a change from [00:52:00] partnering data science or data engineers with data scientists and more preference for data engineers and data analysts kind of backing away from the data scientists being involved at day zero and seeing more hiring towards that direction, where instead of the data scientists being dragged in, it's really a data analyst being partnered with data engineer and getting more value out of that.
+
+Speaker4: [00:52:28] I haven't seen anything change just yet, but I sense what you're, you know, I'm picking up what you're putting down. So I think that that might be the case soon. It's Data Scientist is a very nebulous title to begin with. But, you know, so what I've seen is, you know, it's the same stuff we've been talking about for a long time, right? It's the the artists of nebulous data scientists. Basically. It's like, what have you been hired to do this whole time? And now you're about to find out. And so any any anything that hasn't been yielding results, I think will be. But I can say the same thing about data engineering, to be frank and analysts were if you're not if you haven't been producing anything of tangible value for I guess during the good times, then, well, you should either start doing that it's very, very immediately or you won't be doing much of that at that company you're at. So that's that's a tone I'm starting to get, is I think there's definitely a refocus in general just on every conceivable way of either trying to make more money while you can kind of, you know, refocusing things or just cutting words. Definitely not going to yield anything for a bit. So that's the general sense that I get overall. But I haven't seen any specific, I would say rules being targeted just yet, yet being the key word. What about you?
+
+Speaker2: [00:53:53] Yeah, I've been hearing about the we're focused more on hiring analysts, but [00:54:00] I'm wondering if that's just, you know. People talking about it a higher level or if that's actually something that's ground floor happening yet because I'm here. That's kind of the thing about when I hear someone say at the sea level, hey, we're going to focus more on this. We're going to focus more on that role and we're going to do this kind of partnership. It's like, okay, yeah, what are you really? And so I never know when it's real or if it's smoke.
+
+Speaker4: [00:54:29] Well, the thing with analysts, too, is you need something to analyze, right? Like, there has to be some sort of, you know, you're moving the needle on something, but. So I guess it depends on how much where that function has has become before things kind of dropped off a cliff. So if if those things are adding value, great. You know, hopefully it continues. But, you know, and I think I was like the thing that most companies I give them the benefit of the doubt. And I hope that they're, you know, investing the money wisely. But, you know, endless amounts of free money mass, a lot of stupid mistakes, too. And you're about to find out, I guess, as Buffett says, who's been swimming naked when the tide goes out. So it might be a huge nudist colony for all I know, but. Yeah. Yeah.
+
+Speaker2: [00:55:11] It's do I mean less data science magic being panacea? Yeah, it it's kind of interesting that I think from what I'm hearing, leadership's asking the question, you know, what's the difference between the data analysts and a data scientist? Which ones do we need? When do we put one on a project, not the other? Because, you know, the salary is like half. You can hire a data analyst for anywhere between 185,000 120,000. Trying to get a data scientist for us from 200 K now is it's hard. So that's what they're looking at is there there's actually like a conversation that I'll hear from time to time, which who do we need on this? What department do we need on this? Which, you know, should we be hiring more of this versus that? [00:56:00] That's the conversation I'm hearing. But like I said, I don't I don't know if that's going to turn into something. Or is that just this month's conversation?
+
+Speaker4: [00:56:09] Well, these things have a weird way of working themselves out to because it's like, you know, execs talk to each other, right, at different companies that are trying to compare notes. And I feel like it's it's like a lot of things where people follow fast, even if it makes no sense. And so it's like, oh, I'm going to cut my data teams. I get f them, let's just cut those guys too. So it's, you know, because a lot of this I mean, recessions are a weird thing where it's, you know, you're trying to forecast the future and recessions occur precisely because everybody starts cutting and cutting back. Right. It's not like these things just sort of happen in independent. It's demand drops off, but demand there's a lot of reflexivity, as a source calls it. So these things have feedback loops. And when I talk to each other about their hiring or more to the firing plans right now than I think that there's a lot of comparing notes. So, you know, it's this is this isn't like a fine art, the art of like cutting your teams, right? It's like, you know, how do you I mean, it's a question that I think a lot of people here have been mentioning over a while, which is how are you assessing ROI in the first place? And I've been talking about this in the you know, in the boom times. And if you're tracking how ROI has been calculated, I suppose it should be a pretty easy exercise for you to figure out. You either keep or you cut. But if it wasn't providing ROI back then, I don't know why you're keeping everyone around in the first place. It seems a bit silly, but we might think we've managed to do a really good job at running things that have the appearance of businesses but aren't really run as businesses. So that's changing.
+
+Harpreet: [00:57:47] I'm curious about that. That that last team about running things that have the appearance of businesses but aren't really businesses like what would be kind of an example of that.
+
+Speaker4: [00:57:57] Well I mean I think the entire startup ecosystem, for [00:58:00] example, is an example of this, where to call it as it is. I mean, you have a lot of companies that were flush with VC cash and or were incentivized to grow with. I mean, when I would talk to startups, I asked them already incentivized by revenue, profit or logos and logos was the driving factor for a lot of these companies in terms of, you know, I need to get more logos and that's how I'm going to get my next round. Revenue was, I mean, so you'd see these kind of dinky deals coming through, but it's all long, your logo collecting, that's what mattered. But the last time I checked, I don't think logos paid the bills for real businesses by banner. I try to run our business on logos alone. I mean, we got our business in like 2 seconds and that's the reality of it. But and most businesses are they do these weird things. They make revenues and profits. It's a very strange idea. And, you know, you can look at Wikipedia and find these how it's calculated, but you know, this this this fad of profits and revenue, it's slowly catching on. And so that's what I mean. These by the by the official term of what a business does. Right. It generates profits and cash flows and returns. Those are shareholders. That's literally the mechanism of what a business is. Right. Until then, it's like I said, it's it's it's it's something that's on its way to becoming a business. But I wouldn't say it's strictly defined as a business. So that's what I mean. It's play business.
+
+Harpreet: [00:59:27] So. I like that. Thank you, Joe.
+
+Speaker2: [00:59:33] To define what a laying of business is. My daughter makes more money every month than Uber does.
+
+Speaker4: [00:59:40] Ouch. But that's the whole point, right? I mean, think of how much money went to Uber. You know, I mean, colossal amounts. And I don't know that they'll ever turn a dime of profit that's going to recoup that right Or so. And you can you can play all the shenanigans you want about EBITDA and all this other stuff. But at the end of [01:00:00] the day, it's either making money or you are and you know, smuggler calls it like bullshit earnings. So, you know, you've got everything except the things that matter in a business. But anyway, I got off my soapbox and.
+
+Harpreet: [01:00:15] But what would happen like what would happen if, like Twitter, Twitter, Uber disappeared?
+
+Speaker4: [01:00:21] Like a cabs.
+
+Harpreet: [01:00:23] Cabs.
+
+Speaker2: [01:00:24] Literally nothing. I mean, I would feel bad for the engineering team because they're amazing. I feel bad for all the people that work there because they're all literally trying their best. But how can I just I, I ask this question a lot over the last two years. How can a company that loses $1,000,000,000 a quarter be worth anything? How do you tell me that their stock is worth $10 more today than it was yesterday when they still aren't profitable? Like, what do you you know, we're supposed to be making guesses based on forward looking earnings. But if their forward looking projections are losses, how is their stock value not negative? I'm just you know, I'm just doing math, right? I'm not I'm not talking crazy.
+
+Harpreet: [01:01:09] Where where are.
+
+Speaker2: [01:01:10] They saying it's not he's not nuts. It's all this is the entire startup industry. Talk about how many companies have never made a profit. I mean, Uber's been around forever. It in a year. There have been profitable quarters, but I don't think they've had a single profitable year. Even when they sold part of their business to China to I think it was Didi. I even think that year they weren't profitable and they sold it for like 1.2 billion. So how is that a company? I love them. I have been with Uber and an Uber customer since forever. Like since the very beginning, I've used Uber. I love them. But how do you make that much money and not make any money?
+
+Speaker4: [01:01:50] Well, I think it's more of a security, actually, you know what I'm saying? Like is traded as a as a financial instrument that people will pump up and sell the next person and so forth. And again, there's nothing wrong with it. I mean, I've worked [01:02:00] at startups and Lord knows I got startups asking me if I want to join them right now. And so I know how the game works. And it's like when you're in that game, you play that game and you got to know how that game works, right? And that game's a lot harder than it is than it used to be because it's harder. I would say it's going to be easier in some ways to be able to hire more easily to know. And that's been the bottom, the choking point for a lot of these companies. You just can't find anyone to work there because, I mean, they all the talent's been locked up in Facebook and Twitter and all these companies and Google and everyone else. But I wager, you know, a regular source letter to Mark Zuckerberg last week from the alternative capital letter is like you got to be cutting a lot of people in that it's you know, no offense to Viv, but that's I mean you throw it some pretty large numbers.
+
+Speaker4: [01:02:44] I mean so it's you know, things are going to happen I suppose. But if that's going to unlock a lot of talent that now can go to these startups, I think that's probably a good thing. At the end of the day, like startups, you know, I'm not I wasn't here to bash startups. I think the business model is what it is. It's like you until you generate revenue and things that would, I guess, qualify as a, you know, a business. You mean you literally are like on life support because you rely on VC funding. But again, I work these places, they know how it goes. It's like I'm stupid and just talking too much crap. Like, so you just play that game and hope it works out. So but you know, in this case, I think it's it's going to get easier because you're going to have less competition. So.
+
+Speaker2: [01:03:23] You know, I just wonder how long you can I mean, there's got to be a time where you say, look, how are you not profitable yet? You know, I get every startup needs a runway. Every startup needs someone to take a risk and a chance in it in order for innovative technology to ever make it to market because it's expensive. You know, ask Mehta how much the metaverse is costing. It's not easy to build that big of a platform. You know, it's going to cost a lot of cash. You have to be able to look at your investors and say, I don't care how low my price is, you can put my share price to whatever you want to. I'm in charge. We're doing this. You have to have Mark Zuckerberg [01:04:00] nerves and play that game of chicken. And Amazon did the same thing. You know, Wall Street Journal wrote him up, wrote up Bezos and said, why don't you stick to groceries? Well, because US is now massive. That's why it's now saving Amazon's grocery business, which is really doing terribly so.
+
+Speaker5: [01:04:20] Right. But the difference there is that at some point, the pay, the risk paid off. Right? Right. There was a legitimate. Plan for. Under what market conditions will that move of focusing on distributed like web services actually pay off?
+
+Speaker2: [01:04:37] Well, and I think everyone says they have a plan, like a path to profitability, especially now everyone has a path to profitability.
+
+Speaker4: [01:04:44] You have to say that. Would you would you be otherwise like not? We really don't know how we're going to do this.
+
+Speaker2: [01:04:48] Well, I think that's what a lot of companies have been doing, right? Like until the last six months, they've been going, yeah, some day. I mean.
+
+Speaker4: [01:04:56] It's like, oh, yeah, we have a we have a plan, right? I mean, I've seen all these plans. They're basically facsimiles of other startups at the same stage because like, here's what we need to either do, here's a trajectory you need to be on for all these different metrics in order to get our next round or to IPO or something with nobody's IPO right now. So it's like, you know, here's our plan to be at least like burn neutral, whatever the hell that means, or just extend our runway for a couple of years. But it's like, I don't know. I mean, there's a certain input that you need, which is revenue. And that's that's going to be locking up pretty hard. And so, you know, there's only so much money to go around. And that's I don't know.
+
+Speaker5: [01:05:30] I mean, how much does that come down to the right horizons? The right like because you can make a plausible plan for the next two moves in chess in any situation. Right. I've done that. I'll play that up to like ten. Right. And what horizon does that break down is kind of my question.
+
+Speaker4: [01:05:46] I mean, whatever horizon is going to satisfy the people who are asking the question, Right. That's that's that's what it comes down to. It's all bullshit. At the end of the day. It's like there's there's a reality of the market and there's reality of what you're and there's the story you're trying to spin in order to get what you need. And also [01:06:00] and there's a story of what people who are listening to you want to hear so they can tell people their their stakeholders what the story is. This is how this works. It's all just, you know, Fugazi. Fugazi is the old saying goes in the famous movie. So this is so I'm not out. I have to take off, actually.
+
+Harpreet: [01:06:26] So good to see everybody. Thank you, Joe. We got you like a ghost.
+
+Speaker2: [01:06:32] I think you're asking the right question. What's the runway and how far ahead can you look? But like I said, at some point you have to. Your story can't be a story for ten years. I just I don't know how you keep plugging cash into something. As a VC that hasn't been profitable for five years and they're talking about maybe never being profitable. Like I get. Uber has value. If you broke it down as just a you know, the technology has value, the infrastructure has value, the customer ecosystem has value, the network and marketplace they've built, Those all have value, but they're not profitable. So yes, they've created an asset. However, the value of the asset to investors seems to be higher than the value of the asset to customers, which is where I, I struggle. How look, at what point do you give up on it and just say it's going out of business?
+
+Harpreet: [01:07:37] I'm still perplexed by Uber. Like where are they losing money at? Because, like, they don't own any cars. Like, you know. Is it because they're paying the drivers pain insurance? They have too many engineers. Like, where are they? They lose money or are they not charging enough? Because, I mean, it's not like it's it's not charging enough. Yeah.
+
+Speaker2: [01:07:59] Yeah. Yeah. [01:08:00] Their problem is and I don't I'm not bashing Uber. I love them. Like I said, I absolutely love the company. And the concept and what they do like is awesome. I'm trashing the business model a little bit with respect to the marketplace. And I think the problem is that they expected self-driving cars to come sooner because that's they're only out when you take the labor cost away, all of a sudden you go, Oh, wait a minute, this business model works really well if you have autonomous vehicles, but as long as there is a person in the driver's seat. This doesn't work. Amazon's got the same problem. Amazon Prime has the exact same problem. While there's somebody in the driver's seat, their basic economics is going to continue to get worse. So and I think a lot of companies are getting to this where it's a race to the bottom. Labor is a commodity, but we are in a labor shortage. So all of a sudden, the things that they've been relying upon aren't there anymore. And that runway to self-driving cars where labor is eliminated isn't where they thought it was. And like I said, for a marketplace like Uber, there's value, but they're not charging enough. And the problem is they've trained customers to be very price sensitive. They've trained their customers at a particular price point. And now they're in trouble. Mm hmm.
+
+Speaker5: [01:09:29] So it was just too early in the game then, because, I mean, realistically, for them, they're reliant on many other companies reaching the self driving stage because, honestly, how many how many self driving startups have you seen actually stand up to the existing automotive industry market? Right. Like the dice and pulled out of the electric car market? Forget the self driving car market, right? I was there when it happened, actually. I was at Dyson when it happened. It was quite an interesting week. That's all I'm going to say. But [01:10:00] I mean, rivian they're standing up, I don't know, on their profitability. I haven't looked at all, but they're the only name that's other than Tesla that's a nontraditional, like automotive company. Right? And the other automotive companies are catching up quick. Hyundai and Kia just released their flagship electric cars. Right. So they're going to catch up to, you know, the likes of Tesla and Rivian pretty fast in terms of their actual technology offering. Right. But in terms of self driving, how much does that actually like? The point for Uber is that they're completely reliant on the industry of the entire automotive industry to catch up to what they need to make that profitable, Right? Amazon Prime, on the other hand, they're really just waiting for drone regulation and stuff like that becoming a little bit easier and that may be more accessible. But the funny thing to me is like I understand Uber not being too willing to build their own self-driving cars and stuff like that. They've they sold their self flying aircraft business at a loss or something, right? Like if I'm wrong, but someone like Amazon, I'm surprised they're not hiring more robotics engineers to work on this self flying drone problem. I mean, package delivery drones is not a very difficult concept to adapt existing drone technologies from like they should be. I don't know, like, I mean, if that's their plea, why don't they go out and hire bunches of robotics engineers and try to solve the problem themselves because there's no established industry for that, Right.
+
+Speaker2: [01:11:38] Well, you got to think about it. If they live up to high reliability standards, five nines, that means one in. If I'm remembering. Right, one in 100,000 failures. If you do 100,000 deliveries a day, that means one thing kills somebody every day.
+
+Harpreet: [01:11:55] Yeah.
+
+Speaker2: [01:11:56] And so five nines all of a sudden doesn't sound so amazing. You [01:12:00] know, if one drone falls out of the sky every day or every 100,000 deliveries you imagine, like every 100,000 plane flights, something hits somebody in the face.
+
+Speaker5: [01:12:14] It's it's not a problem. That's the reality of of a robotic system. Right. It's that much more dangerous because you're dealing with it in the physical world. It's passed litigation now where you can just fire or sue a driver. Right. It's about is the technology willing to stand up to it? It's possible, but that market's not yet big enough to, you know, to make it affordable for a company to do that. So, I mean.
+
+Speaker2: [01:12:41] It's like Elon Musk said, I mean, this is a hard problem to solve. And as much flak as Elon gets, he's not an idiot. I mean, he he used to be a very talented engineer. I don't know how he is now, but I'm just saying he used to be at PayPal, no joke. He was a talented engineer. He understands engineering challenges, but he's had the same realization. Everybody who's tried to tackle self-driving cars has had, which me included. I thought we'd have them by now. I bet somebody a very nice dinner in 2017 that we would have significant disruption by now in the the automotive industry and trucking and everything else. And I was wrong as anybody else was. So not pointing fingers. I am the idiot I speak of. But it's a harder problem to solve is we don't know how to get self-driving cars through people's perception. And it's the same thing with drones. I mean, if I drove these same frequency as a drone did, or the same frequency as a self-driving car did, I'd get into more accidents than they do if you if you did the metrics on a self driving Amazon versus a human behind the wheel, Amazon, all of a sudden that self-driving car looks really, really good. Nobody says that about Tesla's autopilot. [01:14:00] You're not talking about a comparative. And that's one of our problems in data science is we don't know how to talk about reliability. We don't understand how to publish reliability requirements, human reliability, how many crashes per mile do we have with a human driven semi versus a rivian? I think rivian's do semis, right? That's rivian versus a rivian. So how many crashes? And if you look at self-driving cars, Tesla in driving that autonomous mode compared to a person, how many crashes per mile do we have? When you begin to advertise it from a reliability standpoint, you can say this must be at least as reliable as a person. And if it meets that reliability standard, you're good. Because, I mean, what are you supposed to do? Make it better than us? Really? Come on.
+
+Speaker5: [01:14:54] Well. Well, that's. That's the eternal perception of all things robotic, right? Like on a manufacturing line. A human visual inspector is probably going to have 80% accuracy over over the course of a day, a week, a month, a year, a career, a model that's supposed to detect defects in complex plastics. Yeah, sure. That's expected to be 99.9%. Right. Like you see it all the time, Right. We just expect perfection because there is no how do I put this? There's no throat to clearly choke.
+
+Speaker2: [01:15:30] So what do you somebody who's a very well known expert in robotics once said to me privately that the the difference between a human and a robot is that humans are way better covering up their messes.
+
+Speaker5: [01:15:48] Oh, man. That is so true. You can't hide the magic smoke, guys. Trust me. We'll try it. You can't hide the magic smirk. Robots just hate giving that stuff out.
+
+Harpreet: [01:16:02] With [01:16:00] that, let's go ahead and wrap it up, y'all. Great discussion. Thank you all for being here. Thank you all for watching on LinkedIn. I thought for the longest time LinkedIn algorithm was punishing me, but we've had steady, you know, mid-teens viewership in this video. And I got like the biggest engagement on the post that I've ever had recently. So that's pretty cool to see. So I think LinkedIn is now rewarding me again. So thank you all for being here. I don't know why I'm going off on that tangent, but thank you all for being here. Thanks for joining. Have a good rest of the afternoon. Remember, my friends, you got one life on this planet when I try to do something big.
+

data/hh102.tt

@@ -0,0 +1,118 @@
+Happy Hour 102.mp3
+
+Harpreet: [00:00:09] What's up, everybody? Welcome. Welcome to the Arts Data Science. Happy hour. Friday, November 11th, 2020. I don't know about where you are, but slammed with some snow last night. I think so. It's a snow, but it's nice for the Christmas. But here in Winnipeg where it lasts for six months but Christmas sweater season, hopefully you guys got a chance to tune in to some of the live events I did this week, you know, podcast. I've got a backlog of podcast episodes that will start to be January, some fresh episodes. But in the meantime, I'm doing a bunch of live events over at Dessie did a couple of sessions so far, and as intuitive manners, I possibly intuitive in the sense that it was intuitive to me. I kind of understood it, so I'd try to and then showed how to implement that using the Super Gradients training library. And I'll be doing that for several papers. That's going to be kind of like the main is just distilling it down, make sure I grok it and then communicate it in a way that's free of and then of course, super gradients. So I did like a cool little project. It was a hard project and it was classifying car brands, which is harder than you might think because all cars look the same like cars. So it was a matter of trying to figure out, okay, what's the right loss function to use cross entropy? And, you know, I was collaborating with one of my colleagues at every day, all day for five years and dropped some knowledge on me and said, you know what, situation like this, we want to use something like such kind of high overall.
+
+Harpreet: [00:01:28] So we went that and, and made a couple other tweaks which you'll check out by looking at the notebook itself. But yeah, it was great, great, great session. I hope we get in on that next week. I've got live sessions happening as well, three live events that are going to be fairly technical. I've got an event happening with Serge Machine Learning. Susan Chu Chang is reinforcement learning and we'll be talking to Kate Markova about all things these stacked week, which means I got a lot of reading to do. I got a lot of learning [00:02:00] to do because in order for me to be knowledgeable and make it a good ask me anything, my default assumption is like, nobody's gonna ask a question. Everybody's going to sit silently. So that means I need to be up to speed and knowledgeable about this topic and just be able to ask the dumb question. Usually are pretty insightful questions. Shout out to everybody in the room, wrestles in the building, then get to see Ben Taylor back. I was back in Bend. We've got to we've got to reschedule the the interview that had scheduled sometime soon. I was supposed to go live with Ben about a month ago, but construction happening. You might venture to.
+
+Harpreet: [00:02:33] I think you were trapped. So that shout out to everybody else in the room, Sanker was going on chainsaw into the building. If you guys watching on LinkedIn got any questions whatsoever, please do let me know. I'm happy to take all of your questions. Speaking the questions, I guess. Let's kick off this discussion last week. We're talking about layoffs. Right? And I've seen like a lot of posts about people. You know, obviously, people are talking about the layoffs, are talking about the struggles they're going through. I saw a really interesting post by someone. It was kind of like a anti layoff post, but like in a good way, they're like, oh, these people are like, we shouldn't feel bad for them. They got hired at the best of the best companies. They're probably going to get picked up again real quick. So let's kind of look forward in the future or look towards a brighter future and just dwell and think about you talk about the prospect. A lot of people got laid off. What does that mean for the tech mean that sooner? Does that mean that we might see more innovation, more disruption, or are we going to just see tech? I don't like to start that discussion. Let's go to Vin and then maybe we'll go to Ben after that. Anybody else wants to chime in? Please do let me know. You guys watching on LinkedIn, if you have questions or comments as open, there's.
+
+Speaker2: [00:03:43] Some good news. There's got to be it can't all be bad. But what people don't realize right now is that we're kind of in the beginning of layoffs. We're in phase one, even though if you're in a startup world, you're kind of into the second, sometimes third rounds of layoffs. So I want to paint a rosy and bright [00:04:00] picture. But the reality is that we're we're at the beginning of this cycle and we're probably going be going through it for another nine months in one way, shape or form. And every industry that's dependent upon one of the industries that's laying off today or one of the industries that's suffering today is going to be laying off in three months or nine months. So it's going to get worse. But the good news is we've got a lot of pent up demand that we have to work through in the system. We've got a lot of companies that haven't been able to hire and they still have open positions. There are companies that are growing. There's small spaces here and there that are growing. But I think at some point we start overwhelming the demand with supply and people are going to have to pivot into other careers, which is one of the benefits of being laid off and in a tough marketplace is sometimes it forces you to upskill and you've been comfortable in a role for a very long time, and now you have to look at a better role and look at what would it take to move forward, what would it take to pivot, get promoted.
+
+Speaker2: [00:04:58] Sometimes layoffs turn into promotions, sometimes you upskill into a better job or a better industry. And the other piece of what we're seeing a lot of right now, or at least I am, is. A lot of consultants, people are going into consulting, opening their own one person, three person shops where you know them and a couple of teammates got laid off and they just start. And you can get clients pretty quickly right now because companies, as they lay off too many people, all of a sudden they need a consultant. They need a consultant pretty quick because they realize they have some some work. So there's there's benefits, there's upsides, there's opportunities. But also at the same time, I want to be realistic. It's going to get really rough for about nine months.
+
+Harpreet: [00:05:40] A couple of questions I'm wondering off of that. Like, you know, we'll get to these questions later. I'm wondering, will this what will this mean for tech salaries for software engineers and data scientists in the future? And also, like, does this mean that people will quit doing these ridiculous ass interviews because there's demand? I don't know, Ben, let's hear from you and then let's come back and revisit those questions. By the [00:06:00] way, if anybody wants to chime in, Russell Sanker Vivian, she's ready. If you guys want to have anything to say here, do let me know. Those watching on LinkedIn. Your comments and questions are welcome as well. Go for it. Ben, As usual.
+
+Speaker2: [00:06:13] I agree with everything that Ben said. I think the only thing I would add is I think sometimes we don't realize that how necessary layoffs can be given the current environment. I like to think of a business as being an organism, and if it's sick, if there's too much burn, if things are upside down as far as the business is concerned, then of course you need to do layoffs. One of the recommendations to to do layoffs once and cut once cut deep. Because when you have to do these repeat layoffs, it can definitely impact morale inside a company. So I don't think I have that much more to add about layoffs. Just if you're if for the people that are one quick thought on layoffs is I think for people that are in in a position right now, it's important for them to understand how their activity maps to revenue, because I think in a lot of roles, sometimes we don't do that, whether it's evangelism or data science. And I think in this environment, you really want to fight for that. You really want to make sure that the work you're doing is mapped to short term value for the company because they tend to pull back on long term initiatives. So that's the only thought there.
+
+Harpreet: [00:07:29] Yeah, I'm like, I'm, you know, I see some of these CEOs and they put out the tweets for post on LinkedIn and they talk about how good separate severance packages that are giving to their employees. And like part of me is like, oh, why don't you just like not lay off that many people right now? Like, why are you immediately laying off this many people, giving them all this money instead of just like saying, okay, let's reassess the situation, keep X amount and layoff like, you know, a smaller amount. Like, how does this make sense [00:08:00] to lay off that, you know, that amount of people just give them all this kind of. Any thoughts on that for me? One, I'm going to go to Vin here, but if anybody else has.
+
+Speaker2: [00:08:09] Yeah, share price. Two words. That was it. And doing it this year means that they can write down the expenses this year when everything's terrible anyway, like their stock price is going to get hammered no matter what. I was kind of joking about this with some folks back in March. You know, if you if your earnings beat, your stock gets hammered, if you miss earnings, your stock get hammered. If you lower guidance, your stock gets hammered. It was pretty much, you know, this year is if you report earnings, your stock's going to go down. There's been so few companies that have had good earnings, good outlooks. And so this is kind of one of those you might as well. But a lot of these layoffs aren't truly necessary, which is and in my opinion, I think that's kind of the garbage CEO that you're starting to see, is that we've had CEOs that don't know how to lead companies during a downturn. And so they're doing whatever investors in their ears are telling them to. And so it's a lot of share price. And when they were listening to long term investors, they were talking about you have to invest in growth. You have to find ways to grow long term. They cycle out right before these types of downturns happen and a short term investor comes in and the short term investor doesn't care about anything past 12 to 18 months. And so that's all you're seeing, some layoffs that don't make any sense at some companies. And then you have other companies like Amazon who's revisiting strategy. They're looking at unprofitable business units and saying, okay, this is a long term bet, but is this really a smart way to spend money right now? Is this how we should be spending money, given the way that the downturn is happening and they're downsizing robotics because they're looking at that and saying that's probably further out and not as profitable. And so we can come and revisit that later. And so there's there's some intelligent [00:10:00] layoffs, but there's other ones that are just don't make any sense.
+
+Harpreet: [00:10:04] Sucker or Russell any any input cost going. Of course, I was in the building with a with a comment. He's a robotics guy in robotics. But soccer wrestle. Go for it.
+
+Speaker2: [00:10:15] It's one quick point. You were saying, you know, a lot of the companies that are making these layoffs, that they're high scale tech companies for the people that are laying off good quality people. So they shouldn't have difficulty getting employment elsewhere. The one contrary point to that, though, is the scale. So the amount of people that are being laid off at each company and then there's multiple companies that are being laid off. So there's an awful lot of people hitting the market at once. Is there enough other companies looking to hire to take them all on? I mean, I doubt it in one fell swoop. But as Ben was saying, you know, there's probably going to be a tough nine months over that nine months and beyond. Hopefully, there is enough to to absorb those people back into the market at a place that's stable for them so that they can make their, you know, their next play, their next move. And fine statement going on is if if the market is unstable, it can be tempting to take the next the next soonest thing and skip from contract to contract. So, yeah, it's a it's a tough it's a tough choice. I feel for everyone out there.
+
+Harpreet: [00:11:23] Yeah. Wondering what this means for one like tech salaries. Like, are tech salaries inflated, do you think? Realistic and is this going to mealing off for people going forward?
+
+Speaker2: [00:11:33] One quick point back on that. I'd have thought if anything that there likes to be, go on. Because if people have been cut out and especially if the employers have, you know, they've seen a little bit of frostbite in their big toe and they've cut their whole leg off, you know, then they're going to need to employ people back to make up for the shortfall that they've got rid of. And they're going to have to employ people at a higher rate because they've either just been cut off or [00:12:00] they're bringing consultants from external who know what's happened and they're going to demand higher rates anyway. I think this is likely, if anything, to to inflate the market rates. What do you guys think?
+
+Harpreet: [00:12:12] Let's hear from my son. He's got a good chat. Go for it.
+
+Speaker3: [00:12:15] Yeah, I was just commenting on the Vince point, I thought been talking about it as a sort of like a market behavior. Apologies for the noise in the background, but if you really think about these things like financially, right? It's like in downturns like this, there's always people who just follow the trend and follow what everyone else is doing. Meaning that to Vince point, there are CEOs who are overreacting going to too far maybe to correct course. Correct. And as a result, that's potentially where there's a lot of opportunity. Right. When you have a market that's stable, that's typically when you have everyone is at the same sort of level playing field. But when the markets are tumultuous, that's also an opportunity in some sense for some people to maybe double down on certain bets or maybe pick up some talent that's being overlooked. So I want to throw out that angle, but.
+
+Harpreet: [00:13:12] Thank you very much. Question Coming in here on LinkedIn from Mike. Mike Nash As a data professional, what is the best way to exact, as Ben said, do you have to to get them to the value or to.
+
+Speaker2: [00:13:27] Sure. I think it's I think it's really understanding how you map to defensible value within the organization. I think sometimes people don't finish that last mile. If data scientists want to defend their activity or how model's working, they'll defend it with metrics tied to activity rather than metrics tied to KPIs or otherwise. The classic example I give is an AUC score versus how much money are you actually bringing back into the business. Yeah, I it's [00:14:00] not a lot of people struggle with this. A lot of people are not attached to revenue. They don't have a clear number that they can defend for the quarter. The other thought, too, sometimes there's these natural tensions that exist. So in an environment like this, people really focus more on efficiency, so they'll pull back on innovation. And some of those things are really, really hard to defend in this environment, which is unfortunate.
+
+Harpreet: [00:14:26] Russell next on this. By the way, those LinkedIn following questions and you chat.
+
+Speaker2: [00:14:32] I can just I mean adding onto it Ben was saying it having defensible space around your team means having a really good pitch deck for cost savings, improve productivity and revenue generation and just have that ready, you know, three slides, one slide for each one of those main points. And if you can't make the mapping, that's that's a big problem because somebody is going to come asking you in the next six months, what are we doing with all this revenue? What are we doing with all of this money that we're redirecting back into the data team? And so if you. If you find yourself unable to fill up those three slides, the best thing to do now is look at initiatives with really short time horizons, where over the next 1 to 2 months you can get some wins on the book. Because a lot of long term initiatives you can incrementally monetize and that if you can use that as sort of your mantra, long term, big wins but incremental monetization. So make incremental progress and incremental monetization. And think of that in the roadmap form. Really just think of it as milestones. How much can we deliver in 14 days and what's the revenue, what's the cost savings, what's the productivity, what can we do in 30 days? What can we do in 60 days and really break it down that way? And if you can't do something in two weeks, move on.
+
+Speaker2: [00:15:52] So that's the defensible space is what I call it. But there's a lot of different terms for it making a small defensible space [00:16:00] around you and justifying why? Why do we do data? And if you can find some people at the product management level, they're usually really good advocates because they'll help you find these. They're looking for ways to save their job just as much as you are. So talk to people at product. If you can talk to somebody in the strategy side, they're the ones who are deciding who's getting laid off and who isn't right now. So if you can find some allies in the strategy team and maybe even just help them give them data that they need to understand how the organizations are, you know, do some data gathering and start saying, hey, we got some we've got some gaps here that I can help you fill so that you understand how these other business units are producing value or even help business units defend their value. So there's you know, there's there's opportunities to create that defensible space.
+
+Harpreet: [00:16:47] Ben says in March 2020, most people did big cuts. I knew an exec that the opposite and started hiring more salespeople to understand and expand. That unusual strategy ended up being Hasidic speaking orthodox. There's a canal that was missed and a lot of swelling and pain and why it's comfort at the first root canal.
+
+Speaker4: [00:17:07] Hey, I still have a job, by the way, if you were wondering. Good. Yeah.
+
+Harpreet: [00:17:13] For two invaluable. I wouldn't. I wonder.
+
+Speaker4: [00:17:15] Oh, that's so nice of you to say. I was pretty nervous, though. I mean, one cannot help but, like, count all the ways in your mind. You start being like, Well, I don't know what the criteria are. I don't know how they're deciding. This was very nerve wracking.
+
+Harpreet: [00:17:29] Do I talk about that or is just best to To what?
+
+Speaker4: [00:17:33] What do you mean?
+
+Harpreet: [00:17:34] Is that like. Like. Like that? I don't know if that's.
+
+Speaker4: [00:17:38] I they have ensured that much about it. It was mostly strategic like as far as like, like a higher level company strategy, I guess. Like, I don't they like, there's been a lot of like communities and stuff which has been helpful, but they basically just listed. People were like, Hey, how did you decide? [00:18:00] And then it was like they basically just listed like all the things like, Oh yeah, we like considered strategy of the company and we considered like, well, we consider performance and we considered seniority and like just like threw everything out. So it was like, okay, well, I don't know, I considered everything, I guess. I don't know.
+
+Harpreet: [00:18:18] I wonder if, like in these process, like how, how bad slightly abrasive in your person towards getting or not maybe not a strong opinion question coming here from. Well actually we'll take the question from Russell and then Saga on LinkedIn. I see there I will hear your question as well. So go ahead and sit tight. Russell, go for your question.
+
+Speaker2: [00:18:40] Yeah, thanks. So I was saying, I wonder if there's like a covert risk here in the data communities being that there's been a long, hard slog to get the wider business community to understand data as a as a product and later an asset. And we're not quite there yet, although it's getting better all the time. But is there a risk that once the purse strings are being tightened due to what's happening with these layoffs and wider economic climates globally, that the thing least understood at the moment is the first thing to be discounted for what seems like sacred ground or well, it seems good, but I don't understand it yet. So let's just let's put that away and go back to the abacus. You know what I mean?
+
+Harpreet: [00:19:28] Well, again, try this one over to is an expert on this type of I'm still sitting here. Just go for it.
+
+Speaker2: [00:19:35] Me too. My boss is a jerk guy. So it's, you know, two streets and Ben kind of nailed it. He said that. And this is something that happened in 2008, 2009. Look at all the companies that showed up in 2013 to 2017 and just crushed the building. They all invested in innovation and inappropriate staffing, really cycling [00:20:00] out people that they didn't need anymore and filling roles more strategically with people that they did need for growth, those companies. And crushed. And so there are companies right now that are thinking that way. They're looking for opportunities. They're thinking predatory. I mean, I'm sitting in strategy planning meetings where it's back the predatory way of thinking is really back. It's, you know, how can we take market share? Who are we putting out of business in order to help us grow next year? It's the strategists are 100% back run in the building and in companies where the data team has made an impact on the C-suite, where the C-suite understands data is been huge in helping them avoid some sort of titanic type disaster. They're not. They're doubling down because they understand during uncertainty you want data and you want better data.
+
+Speaker2: [00:20:50] And so they are they'll cut other areas before they cut the data team. But the opposite is happening to you. It's like you're saying, Russell, there are places where data team just hasn't they haven't really gotten traction. And there's 100 reasons for it. But the data team just hasn't gotten traction. No one's seen it, no one gets it. No one's bought in. And you know, when you said Harpreet, the abrasive personality, there have been strategists, you know, knives out that have been waiting for a chance to take a lop off the technology team that's been running things that they used to run. And so there's yeah, in some businesses they're going to cut way too much and they're going to come out in two years and just be gone. That's the scary thing, is we're moving so fast. If you're not innovating right now, you're done. So a lot of these layoffs are going to really hurt the company. And yeah, there's there's some strategy behind it in smart companies. But in a lot of companies, there's just going to be this knee jerk reaction.
+
+Harpreet: [00:21:50] Vivian, go for it.
+
+Speaker4: [00:21:52] I feel like I keep thinking about work, like I joined this Fang [00:22:00] world and like, it's all about impact, impact, impact, impact all the time. Impact. And I feel that's kind of the question that's being asked here is like, how do I create impact such that my work is considered invaluable or that I can prove my worth? So at work, at least for me, the way that I sort of think about impact is that the most valuable impact that is the most has the greatest hit and is the most meaningful is like the further out in the future you can be. So like if you're if you're impacting like mission and strategy, like future decisions like way out there, like six months, even a year, like out there, then that's like the biggest impact because you're like helping to steer that ship, you know, and like helping to like be that voice of like helping make product decisions versus like something more operational of like, oh, well, our, our processes efficient like then and you take those measurements and do some analysis with that. Like that's not, not valuable, but like what's going to have the greatest hit is like if you can be like out there in a future, you know, making like clearing the path for like where we should go next and like, what our strategy should be.
+
+Harpreet: [00:23:22] Yeah. Thank you, Vivian. And in some ways, that makes me feel being in this position. Half my foot is like here in the present. Now, how to kick up enough dust. I our say signal. I don't. I don't say noise. I'm not a fan of making noise. Broadcasting signal. How much signal can I broadcast. Where we had a rumor. My sister from Saga on LinkedIn. She's pursuing a master's in information technology and management with specialization in the data science track, graduating in December and just a few weeks here actively. How's the job market grads? Well, I mean, let's touch on that. Let the what what are some of your projections? Go [00:24:00] for it, Vivian.
+
+Speaker4: [00:24:02] Well, I was thinking about this a little bit when you guys were talking earlier about layoffs and making some predictions there that recessions are like, hardest for the people that are new in their careers. And like, I mean, if we're being honest here, I mean, sure, we can try to find the silver linings of stuff. And one of those silver linings being like, you are not alone. Like there's a whole cohort of people out there like, you know, when you're when you're experiencing hardship, like trying to find a job during a recession, like you can know assuredly that you are not alone. And that's can be really comforting. And, you know, but there's also like a real truth here that like, for instance, I graduated college, like during the peak of like when, you know, the Great Recession, the 2008 recession and stuff was going on and like being real, like, I will never make up those losses. Like, my career was forever set on like a lower trajectory. And like they like studies have shown that like once that happens that you really never close the gap. Like you just it like that's part of like one of the reasons of like millennial generation not being able to like afford housing and blah blah, blah because like, there just is a realistic like once you get started on this lower track, then you're just on a lower track like and I don't know, I, I mean, obviously I'm pretty happy where I am now.
+
+Speaker4: [00:25:38] Like I managed to get a job at Meta and everything and I survived this layoff, thank goodness. And like, I'm, I'm happy about that. But like, realistically, like I lost out on a lot of, like, great experience. You know, I might have gotten here much sooner. I might have been making a lot of money. In the meantime, I might have had a higher salary. Then I could continue to demand a higher salary [00:26:00] like throughout my whole career. Like there's there's like real losses here. But like the people, you know, if we're really heading into a big recession and stuff, I'm like, morning, you know, this cohort of like people graduating and stuff like, like I feel you. I feel your pain. I know. I know what this is like. I'm I'm sorry. Like, there we can talk about silver linings all day, but it's never going to change the fact that, like, your life is always going to be different, like because of just your age and like, the unfortunate linings of, you know, when you graduate and stuff.
+
+Harpreet: [00:26:33] So let's go for it.
+
+Speaker3: [00:26:35] Yeah. I want to first of all, think what Vivian said makes a ton of sense. I guess one way I like to think about things like this is in terms of like opportunity costs. So a lot of times people are talking about the decision to pursue graduate studies versus take a job in terms of opportunity cost. Right. And so a lot of reason, a big reason that people don't get PhDs is because they think the opportunity cost of not going into industries, it's too high. But now that the economic climate has changed, that sort of calculus itself was changed. Now it makes a lot more sense to really invest in education, whether it's through graduate studies or through like a role, right. A nontraditional role that isn't like labeled as sexy data scientist, sexy data analyst. Like it could be just a marketing analyst or some other kind of endless where you touch on data, you have an opportunity to make like optimizations to a business. You have the opportunity to take some responsibility of some part of the business. I think that's super underrated and it's like all extremely valuable, especially at a point like this where you really have nothing to lose, right? So it would make sense now more than ever to really look at that equation and see what makes sense right now for you.
+
+Harpreet: [00:27:55] Yeah I graduated my first undergrad like two thousandseven right [00:28:00] during that great was in the second the graduate degree was 13 so like was kind of less school in two downturns it really did have an effect like so just to clarify when you say like to be wise or lower tracking.
+
+Speaker4: [00:28:13] Well you know because this is a thing even with like women to of like why it's so hard to close the pay gap is because when you make less money and then you go into a new job then like and that's why a lot of states are trying to make it illegal and stuff to ask for previous salary because they'll base your new salary based on your previous salary. But you know, even when they don't ask, it's still kind of like a, you know, still an anchoring point. And then even just in general, like it can it can change expectations of like what the company expects to like, pay people. It kind of like changes that trajectory of like salaries going up based on your experience and stuff like that. Does that make sense? Yeah.
+
+Harpreet: [00:28:53] Ben says New and Julia. Sorry. Hopefully that doesn't you too much, but then go for it.
+
+Speaker2: [00:29:03] Yeah, I just want to give some quick advice. Industry. There are recession resilient industries. Casino gaming is one of them and casino gaming is. I mean when it swings down, it swings down hard and get laid off. So it's not the best industry in the world, but you want to look at things like casino gaming or traditional online gaming companies like Blizzard and, you know, Activision Blizzard and take two and all of those. Some are doing better than others. And that's the other thing. Pick companies that are succeeding versus the competition. Those companies will continue to hire and they'll be safer havens. They'll likely be hiring junior talent a whole lot longer because they have a different growth plan, a different outlook on growth. But you're going to be going into a way more competitive marketplace. And so find something about you that's awesome because everybody has something amazing about them. Everybody has an advantage over other people. Something happened in your life [00:30:00] or some series of experience in education combined where you have natural talents, whatever it is, figure out what that is. And market the heck out of it. You know, make that your superpower where it is. I'm a data scientist and this other thing. And because of that, I can do all these other things and get so good that your value proposition is undeniable because there will be opportunity. There'll be a whole lot less of it. There'll be a whole lot more rigor in the vetting and even just getting in the front door. But figure out what your advantage is and market it. I mean, just relentlessly always be marketing yourself.
+
+Harpreet: [00:30:38] Here's a question coming in from Mike, which will get to your question, Mike. But there's a side if you if you guys don't follow him on LinkedIn, a lot of great content. We did a live session a few weeks back at the tube as well. And I think what Vin just said speaks to this question How does one differentiate them if they have no formal experience in the field, what Vin just said and any other input on that, anyone else addition as well. But any other tips or advice on that? How does one differ themselves? They have no formal experience. I agree with that. I go deep and I love this phrase. No, no. Something about everything is exactly what they're saying. Be like, Yeah, I'm a data scientist, but I'm also this other thing. So just talents that can combine skills and do it in a way that is really, you know, authentic because you're going to be that much more interested in it. But I think you go around trying to assemble those skills and in a way that's geared towards want to find a way to make money from it, you probably won't. So yeah, the term is specific knowledge, they gather specific.
+
+Speaker4: [00:31:39] Vivian I think that also there's something to be said for like crafting your story and being honest about it. I feel like something that really helped me is I felt like a sense of embarrassment about, like, certain ways that I got to where I am. And so I was like trying to, like, be evasive [00:32:00] or like, you could feel kind of that energy coming off me of like, I'm embarrassed to answer this question or something because I know that it's like I feel inferior to like other people who have more traditional backgrounds or something. But instead, like, I feel like I finally started succeeding when I got out of my own way and started like, owning it of like, yeah, I am untraditional And here's like, why that makes that great. You know, like the here's like, why I have a different perspective than somebody else and like, that's meaningful and like, that's also where you're going to find, like eventually you're going to find that employer that like values you and like your perspective and it's going to be like a good fit on both ends. It's sort of like dating, you know, like if you lie and if you like, create this like paper person of like who you think you should be, then like you're going to end up with somebody who sucks and isn't a good match for you. But like when you're honest with yourself, it's and like honest with other people, like who you are and what makes you great, then like eventually, eventually it may take some time and maybe super frustrating and a lot of tears. But like eventually you'll find that fit and it will like, you know, magic.
+
+Harpreet: [00:33:10] Yeah, Authenticity sort of comes out. Dude, I can see exactly what you're saying so much. Own up to my story and failures. Until recently, I wrote that blog. I thought failure was my desk. It just felt good. Just fuck. Yeah, I was a failure. I was. Yeah, I was surprised. Yeah. Question here then from go to go to Teen Resource question here first, then we'll go to Mike's question. Just because they are in the room right now, if you'd like to, to unmute. If not, I think that's more of a quote than a question still coming up in the field, but intentional about my growth, which joined this session. Well, great place. Looking for some sorry, looking for some mentorship. Well, yeah, just to do it. Just to ask you questions, please. You got to go through some courses here. Finding communities. Talk to us about that. A way to.
+
+Speaker3: [00:34:00] Yeah. [00:34:00] So in terms of differentiating, it seems almost counterintuitive, right? Like you find a community and you're just another member of the community, but that's the hope. The goal is to find a community that is passionate and that's that's been the key for me at least to at least keep my morale up. When you see all of this bad news and whenever obviously you're not having a perfect week at work or your project is not going so well, it's just being part of something and finding other people who are. I think passion is contagious. Like I think when you're with people who are really interested about something, that's when you'll also be interested. And then you bounce ideas and then it has a reciprocal effect where you amplify each other, you grow together, you learn together. And and I think that's like really underrated as far as like just growing as individuals, just people are at the end of the day, what will make or break your life. So it makes a lot of sense to invest in having good people around you. We're just excited about life the same way you are.
+
+Harpreet: [00:35:06] Can be an easier time to join communities. And now, like. Like there weren't I mean, there were communities. It's diversified the right word or niche towns or the right word like if if you're just like, interested in one particular thing, like I'm just interested in the YOLO v seven model. So there's probably a community. Um. So yeah, well, and just gonna read off some of the comments here before going to Mike's question, Russell says honesty and asks some of the best ways to differentiate he behaving like asses and prosper through that. Ben Taylor Networking storytelling can help someone up realize the importance of those things early. Yeah, I. I didn't appreciate it very, very recently. Yeah. No I. Cool. Let's. Let's go to the question. Yeah. Create a personal brand. Let's go to the question by, um, here. Uh, going forward, [00:36:00] do you think the nature of employment is changing towards more shorter term contracts? Do we have to get used to this as a strategy going forward? It's interesting. Like, just like the typical type of things over to, like more like high quality type of work. I'm curious. Yeah. Yeah. The gig economy for, you know, most of those jobs the gig economy in our high school. But yeah, are we moving towards that shorter term like I like.
+
+Speaker2: [00:36:24] This yeah I wrote a post last year so I'm a little I hate to wave the banner here for a second. Yeah I think decentralized teams self assembling teams are the future because companies don't need the same thing long term anymore. And people evolve so fast when it comes to skills, capability, Reskilling Education is different now and technology moves quickly. So somebody who is a data scientist in 2015 with that skill set is now a data analyst. And so there's just we're moving so fast and businesses are changing so fast. I think you'll see this decentralized model of work because somebody at Meta is going to need a completely different type of team than somebody doing data science at Ford. And so somebody who did data science at Meta did a gig. Google will in two years be very valuable to somebody at Ford, to somebody at one of these other organizations in a different industry. And you can kind of see that progression of someone's career where they'll span maybe a five year doing similar things. And I think teams are going to become self assembling where you have these talent agencies now or you try to assemble talent and hold on to it. Companies are really bad at upskilling and they're really bad at creating training programs and figuring out, whereas individuals are far better at optimizing their education and their career path towards value because they're incentivized a little bit differently than companies are. [00:38:00]
+
+Speaker2: [00:38:00] So I think there's that's really where we go is this concept of self assembling teams, being able to validate and continuously validate your credentials as they evolve. And so not so much certifications, but almost micro certifications, I think are going to become the future of how we credential ourselves and how we get involved in a particular project that we've gotten, particular credentials and experience and reviews, and a whole lot of the gig economy concepts I think are coming into and this is probably one of the bigger decentralized platform type use cases is talent, workforce engineering and the sort of dynamic workforce engineering concept. I think that's yeah, that's where we're going. But how long it's going to take to get there, that's a big question because companies don't like to change and the whole HR concept scares them because that's, that's compliance, that's legal, that's liability. That's there's so many laws in place and trying to go to a completely different model. It's there's regulations in place that will slow it down.
+
+Harpreet: [00:39:11] Help me understand self-assembling teams like does that by people just get together with the friends or people really well with them. They just do a bid particular assignment that pops up or I understand that. Right? Or is there a different definition?
+
+Speaker2: [00:39:22] No. So project geometry, if you have a particular work product that you need created, every work product has a, you know, a dimensionality to it when it comes to capabilities required to create the work product. And so by, you know, a lot of these are confidential and so you can't put out the actual this is what I need built until everybody's under an NDA. And so what you'll end up seeing is instead of the actual initiative or the project that you need, you'll see that dimensionality released as the specification. And so you'll need teams that [00:40:00] meet that capability geometry or that project geometry. And when you have a team like that, it's just going. Be self assembling where people will get recruited to fill in each one of those pieces and the most efficient way from a cost standpoint possible. Or if you're optimizing for time or if you're optimizing for a particular level of quality or certain capabilities are more important to you than others, that's going to dictate the team. And I don't think it's going to always be the same people working together. I think really self-assembling is going to be what's the optimal. And companies will be willing to pay different amounts. You know, some will not be willing to pay for top talent. And so you will get that'll be part of the geometry is what's your budget and what kind of talent can you get for that budget project?
+
+Harpreet: [00:40:49] Any follow up thoughts on that? You've answered your question, Vivian. Go for it.
+
+Speaker4: [00:40:55] I can't help but feel like whenever anybody talks about gig economy that the elephant in the room is like the American health care system and like that. It's tied to your employment. So, like, I just don't like personally, I don't know. I think that what Biden was saying sounds really cool and futuristic, but like, that's definitely a blocker in my mind of like the gig economy really taking off is because like, people need health care and they'll demand it. And you know, at some point, like there are certain situations with the gig economy where it starts to feel like a trap or a trick and then people are like, okay, I'm never going to do that again. I'm now going to seek a regular FTE job with benefits and insurance and stuff.
+
+Harpreet: [00:41:39] I guess you would think that for these type of gig economy jobs that the paycheck be higher so that a portion of that by like your own kind of.
+
+Speaker4: [00:41:47] I mean that would be nice if I think I don't know I've read a lot of things on like the worker reform Reddit subreddit and like I don't know, I guess I just feel like it's [00:42:00] it's a precarious situation in my mind, especially in the US with the health care and like, no, like the US is also the only like developed country that doesn't have mandated like PTO and stuff like mandated time off. So I, I just feel like it's a precarious situation in the US because like it's an easy way for companies to like slowly like inch forward to take advantage of their employees and stuff like that and treat people like crap. So I don't know, I think it is possible to have a gig like that that works well, but I think on a mass scale without like some reform, I just don't see it being like a big major thing on a wide scale.
+
+Harpreet: [00:42:43] Yeah, valid points. It'd be like we have a full time job and then pick up on the side type of thing. Good points. Any of the questions, the comments coming through? Let me. The LinkedIn or the YouTube. Wrap it up then. Shout out to everybody that's watching. I see Greg, Matt Macfarlane, Greg Hogg. If you guys don't know Greg Hogg, check them out. He's a couple of days ago. But yeah, check his videos out. Great guy. Like a future. Cool man. Well, I guess that's it. Let's let's be to wrap it up. Thank you guys for hanging out. Thanks for being here. Looking forward to doing more live since we got some interviews going off this weekend. Actually, I've got Sunday at doing a junior run was a part of data science dream job with me. He was there. He wrote a book called Breaking Stereotypes. So we'll be talking about that. That will already have. Listen to that. Then I'm interviewing on Tuesday, Sheng Xiang Wang I actually met Shane right by Stanford University. We're at some dinner that Intel was put in by just chatting and he has a YouTube channel that's all about mind mapping. She was super fascinating. A couple of weeks, not a couple of weeks starting next week doing a Jessica Ayodele huge on YouTube, Twitter. She is A data, it's air B and B, we chopped it up atop Grant Fleming. We'll be talking to him. So yeah a few few live streams coming up then I got to hibernate [00:44:00] because the second to be pace but thank you all for being here. Appreciate all of you. You remember my friends, You got one life on this planet. Why not try to do some big cheers?
+

data/hh103.txt

@@ -0,0 +1,150 @@
+HH103_mixdown.mp3
+
+Harpreet: [00:00:06] What's up, everybody? Welcome. Welcome to the arts of data science. Happy hour. Happy hour number 103, 103 Happy hours, man. It's been going, going strong. You know what? I'm just going to make the announcement now. I think next week's happy hour, I'm going to make it the last the final happy hour right before the holiday season kicks off. Have won one last happy hour because baby number two is coming first, you know, first couple of weeks of December at some point. And yeah, you know, the happy hour has been great. And I've loved having everyone here. But it's time to start, you know, kind of set in the sun on this Mike, kick it off, bring it back next year. Who knows, man, I might do that, but definitely take a little bit of a break for the for the holidays. So hope you all had a good week. I had an awesome week, man. Like, I just can't stress how much I love my job. You know, the company is great. Absolutely love the company. But just be endeavor. Like this job is absolutely fantastic. It is amazing. This week I spent most of my time preparing for these Ask me Anything sessions that I'm doing as part of the deep learning daily community for Dessie. So, you know, this week I did live streams with with Serge. Serge Masses talked about interpretable machine learning. Did a ask me anything session about object detection and the YOLO original YOLO paper with one of the internal experts at Dessie.
+
+Harpreet: [00:01:30] Kate, your cover. That was amazing. Today I spoke to Susan Shu Chang about deep reinforcement learning. And just kind of spoke about that from the from the ground up, from kind of first principles. So it's awesome, man. And all this stuff is going to be actually going all this content is going to be going towards the the as yet unnamed podcast they'll be doing as part of Dessie does he's, you know, D'avril duties. It's either going to be called the deep learning daily the same name as a community as you see there, or I [00:02:00] might just call it the Deep Learning podcast. I've claimed both podcast names already. I kind of like the Deep Learning podcast. This podcast is going to be a lot different than what the RC Data Science podcast is. Rc Science. I think I build it as a personal development podcast for the scientists, and at that point in my life, that was what I was really into. I was really into like, you know, just this personal growth, personal development. I still am. But to me, I think it is pretty much, you know, something that. It just running in my head constantly now, you know what I mean? And then also, you know, talking about breaking out data science, that's not really like my thing anymore.
+
+Harpreet: [00:02:38] So I'm going all in on deep learning and we're going to be having a lot more technical content coming around that I'm trying to make things as intuitive as possible. Speaking of deep learning. The most amazing thing was released earlier this week. Galactica released by papers with code and Meta. It is a large language model that was trained on 103 billion tokens of highly curated data. The data was, you know, taken from research papers, from textbooks, from code bases, just really high quality scientific knowledge. And they've created this this model. I've got a chance to test it out. I don't think the UI is available for for testing. I think they closed that now. But you could it's open source, completely open source. The weights are available. You can go to papers with code GitHub repository and see Galactica there. The model is available on torch, not torch ups. Are you hugging face the Hugging face hub? You can download it from their super easy to use. I mean, if you maybe in a few minutes we can go look at what happens. But yeah, it's about I think the model itself. I downloaded the. 6.7 billion parameter model. [00:04:00] And it was, if I'm doing the math here correctly, about 28 gigs or something like that. It's a huge, huge model. But but amazing. I'm pumped for this man.
+
+Harpreet: [00:04:10] Like, just as it is a content creator who's creating content about deep learning, I think. Or it's not just scientific content in general. I think just having a tool like this is going to be amazing. Just keeping in mind that, you know, these large language models are prone to this phenomena of hallucinations where they just spit out just blatant, incorrect things that sound like fact. So we got to fact check a little bit of everything, but I think it's a good way to kick start the creativity, you know, when coming up with that with the topic also Galactic, they use the model itself to write the paper for the about the model. So 60 page paper that was released earlier this week, they actually use the model to help write that paper which I thought was just insane. Fascinating. But yeah, Galactica. I haven't heard too many people complaining about about Galactica yet, but you know, as always, I don't think it's the model itself that is the issue is just the humans behind it and how it is being used. But yeah, I'm curious if anybody has thoughts on on Galactica, if anybody's playing around with it, if you know, what do they think about something like this. A lot of keen to hear from from surge. I know you've got a deep interest in generative kind of models and things like that.
+
+Speaker2: [00:05:28] Actually, I haven't tried it. I haven't tried any of the recent models. I'm dying to try it. And I think I'll I'll be able to finally play around with those models on like the winter. It's not really a break because I'll continue working, but I'm going to have less of this craziness of traveling and everything in December, and so I'll be able to read some more and and play around with new, new toys, [00:06:00] if you will.
+
+Harpreet: [00:06:02] What else is on the potential list of new toys to to play with? What else are you thinking about?
+
+Speaker2: [00:06:07] Oh, well, yeah, I just I just got a some, some new. What's it called? I just got the Jetson Nano. So Developer toolkit. So I'm going to be playing around with that. I'm going to be doing more edge stuff. I've been doing it, you know, kind of torturing my Raspberry Pi for a while now. Yeah, It's about time I got something better equipped for deep learning inference. And so I'm eager to get my my Jetson. Nano.
+
+Harpreet: [00:06:46] Yeah, well, that's. Let me know. I'm happy to put you in touch with the folks at Destiny. We can take the model you have and use our auto Nack engine to help make it smaller and have it reduced the.
+
+Speaker2: [00:06:58] I'd love that. I love that. Yeah, I, I haven't done a lot of quantization I think it's called Yeah yeah I mean since I the last time I did that was for a project where I, I put my model I think in my phone and taking like a project I did like four years ago and I needed to do that, but I forgot how I went through the process honestly. And it probably doesn't apply anymore. It's such an old, you know, things move so quickly.
+
+Harpreet: [00:07:34] Yeah, definitely a challenge taking these models. I can't imagine. I think Galactica deployed on my phone. I think it would take up all of the available memory. That model footprint is huge, but I'm sure Kozlov has some some thoughts about deploying the vision type of applications on resource constrained devices. Anybody else got got any input? Vin, I'd love to hear from you or Russell. Shout out to everybody else in the room. [00:08:00] Tashi On T Coast, if you're watching on LinkedIn, you got questions, do let me know.
+
+Speaker3: [00:08:06] Yeah, it looks like it got pulled already. I saw something today about I think it was yesterday. It started where they were having some serious issues with with Galactica and it was outputting a lot more inaccurate results than than normal. And today it got pulled. So they they kept the research out there and the model is still available. So it's still a learning tool as far as just incremental progress. But it looks like they their implementation didn't work out. Looks like it was, I don't know, part maybe was the implementation, maybe was the model doesn't really seem to say which one of them was the point of failure, but it looks like it didn't make it. And I think it's kind of funny. It would have taken me longer to read the paper then fine, We're kind of at that place in deep. Learning where we want to. We want to publish everything. But maybe we shouldn't.
+
+Harpreet: [00:09:02] Yeah. Yeah, I haven't. I mean, I've heard there's. There's a lot of, like, people posting their experiences with it. I've been I've been, like, willfully ignoring that, just to kind of stay in the honeymoon phase right now and play around with it. But yeah, I'll try to get it deployed locally and see what I could do. Russell or anybody else got any thoughts left? I'd love to hear from you all. All right. What else is going on, man? Next week, talking to. Talking to. To Kyle Cannon about graph neural networks. I'm not sure if anybody has experience with those. I've been doing research trying to, like, learn about that. So what I spend most of today on, I just ended up going down like a wormhole about, like. Like the actual intuition behind what they. [00:10:00] The function convolution is not like from a convolutional neural network, but like the actual function of a convolution of two functions. And went down a wormhole. And it was great. I loved it, man. I loved it. I was like, feeling like I was back in grad school, just reading all that math and stuff. It was great. Yeah. So what's going on, guys? Let's let's, let's get some let's, let's get some conversation going. Questions on anything. Toshi, I haven't seen you in forever, man. I know you've been out there crushing it. What's going on, dude?
+
+Speaker4: [00:10:29] Yeah, it's been a while. I mean, I've been working as a data analyst at Bloomberg. It's been over 14 months now. Things were a little hectic, and I did kind of miss out a few sessions here, data science, a bit on the personal side, which did affect my professional life. As I'm going back to Nepal in a week, I'll probably be staying there for like two or three months. I'm going back up nine years. So I did have to quit Bloomberg, but now I'm catching up a little bit on the engineering side of things. Picked up fundamentals of data engineering reading right now and just upskilling in general. It's been a journey, man. When I first joined, I started attending data Science back when I was just a student in school. And now, you know, I'm older years, so it's been it's been a journey.
+
+Harpreet: [00:11:25] So you moved back to Nepal for like, for forget? Or is it just to visit?
+
+Speaker4: [00:11:29] No, just for like two or three months. Yeah.
+
+Harpreet: [00:11:33] That's awesome, man. Well, congrats. Good to get to to hear from from you and see you around. There's some other big news this week that I picked up on Twitter, but I just didn't have time to go into the the wormhole about it. What was that company that just, like, Melted was like a crypto company of some sorts? If anybody can.
+
+Speaker3: [00:11:53] Fix.
+
+Harpreet: [00:11:54] Fdx, that's what it's called. Yeah. What the hell is that all about?
+
+Speaker3: [00:11:58] It was a massive scam. I [00:12:00] hate to say it that simply, but it was just a massive scam. It looks like it was. There were some backdoors that they put into the software and into the exchange itself that allowed them to embezzle money potentially. And that's the that's the allegation right now, is that they had pulled a ton of money out. And there are other exchanges that are all on FDX or have some sort of investment in FTC's or of exposure in FTC's. And no one's really talking about who has it and who doesn't. But I think there's been two other exchanges that have folded in the last ten days or last week. It feels like two months goes by and five days right now. But yeah, they they folded. They took down, I think it was $16 billion worth of total assets or 20 billion in total assets. And there's everybody on that exchange is basically not going to get paid. They were over leveraging because they would take the money and invest it into other crypto exchanges and they were propping up all these other exchanges to keep them from crashing. And eventually they couldn't prop anyone up anymore and they needed some propping up too.
+
+Speaker3: [00:13:13] So people started withdrawing money. They couldn't withdraw crypto, they couldn't withdraw money. And that almost became like a run on the bank essentially for this exchange. And overnight it just evaporated, went bankrupt. They closed everything down. There was another exchange the next day that had to stop trading. They're talking about this potentially having exposure to some of the largest exchanges. And after all of this is starting to there's some clarity starting to come out of this. And so there's now this the potential for a like a subcommittee type hearing and fraud investigation. And there's now price targets on crypto like Bitcoin down to 13,000. A lot of a lot of analysts are basically saying [00:14:00] liquidate everything and yeah it's got these massive ripple effects and even bought a yacht club is seeing some impacts here because they're their apes are now selling for less than the the minimum or the stake or something like that where there there's been what was it 12 or more than that of those digital monkey art images that got sold for less than they were like a 500 grand, I think it was a year and a half ago. And they're selling for 40 or 50,000 now, which has got to hurt a little bit.
+
+Speaker3: [00:14:35] I can imagine that's probably not what people wanted to have happen to their digital monkey art, but I think we're kind of in that stage now where we did the fraud and now we're finding out that if it sounds ridiculous, it probably is. And. Somebody I can't remember who said it this morning, but they said, when you give investors too much money, they will invest it. So when we had too much liquidity in the economy, instead of having a limited amount of resources, so you had to deploy it to the best possible investments. When you just are flush in cash, you start throwing it at anything and hoping it works because you have to put it somewhere. If it's if the dollar is not appreciating, if you're not getting interest on any of the Treasury notes, you have to put it somewhere or it's not doing anything. And I think we did that a little too much and we're finding out. So that's that's the long, ugly story of FTC's is somebody sort of revealed the biggest problem in crypto is that nobody in these exchanges really has any sort of transparency, which is rather bizarre considering that was the whole point, right?
+
+Harpreet: [00:15:42] Yeah, that's what I thought. The promise of this was like the the, you know, seen how trades are happening on the actual ledger itself. Wow.
+
+Speaker3: [00:15:53] I still think the technology has promise, but I don't understand crypto. It doesn't make any sense. Why would you connect [00:16:00] a decentralized currency to a centralized currency? Why would you centralize a decentralized currency on an exchange? You don't need the exchange. I mean, the whole point of the protocol is you don't need an exchange. And so now we're putting it on exchanges. And it's funny, IBM's had blockchain. I remember shilling for them in 2015 and their blockchain initiatives back then, and they're still using blockchain and they're still doing a ton of work and people are paying money for blockchain for supply chain uses and applications. Any place you have to guarantee ownership or have a chain of custody or any of those types of tracking methods and for food, it's kind of great because perishables.
+
+Harpreet: [00:16:45] Are.
+
+Speaker3: [00:16:46] You want to understand where it's been, what conditions it's been in, and all of that data can be put on the blockchain and then everybody has access to it that needs it. But it's a semi-private blockchain, not a completely public blockchain. So there are use cases for the technology. It's just looking at crypto and nfts. We've got proven reasons why we would use it. Why would you? Really? Why? Why? I do all these other things. And I think data science can actually benefit from it. I think there's some interesting work that we could do putting data on blockchains. And being able to do some tracking with it and have better visibility and transparency into personal data where if you want to access my personal data, that should be something that gets added to a blockchain somewhere. So if you want to look at it like in the US, you can look at a property records and you can look at and that's how Zillow figures some things out and that's how the pricing and the estimates and some of those companies like Zillow and Redfin, I think they get data from publicly available sources. I don't want them to.
+
+Speaker5: [00:17:56] Have my data.
+
+Speaker3: [00:17:57] They built a business model with our data. They [00:18:00] didn't pay any of us for it. And so I understand it's publicly available, but I should know when someone accesses my data and I should be able to say I don't want them to be able to do that again because I want them to prove to me first they have a legitimate non business reason for it. And you could do that on a blockchain. Every time somebody accesses your data, your publicly available data, it gets logged to a blockchain and there's just complete transparency to it. My data can be an NFT and so there's ownership. I own it. But through the contract you can say that obviously the government has unlimited access to it because that's that's part of the law. They need access to it. But this whole public domain thing, anyone who gets access to my particular publicly available data neft like my car registration, my housing, house registration, layout of my house is available online, all of those things. And so if you had something like that, I would be able to tell that someone looked at my data and I would have recourse for it to be able to say, I don't. I want you to prove to me you had a non business reason for this.
+
+Harpreet: [00:19:12] Like, wasn't Bitcoin kind of created in the aftermath of like a similar financial kind of meltdown and financial tomfoolery, I guess, for lack of better words? And now it has caused this on a whole new scale. That's just ironic to me. Yeah, I think Mark did a project, Mark Freeman did a project with using like data analysis on some blockchain stuff you guys should check. Check that out. Sort of. See you here. Well, Kosta Sorry, Deliveroo. Australia died overnight. What? I don't even know what Deliveroo is.
+
+Speaker5: [00:19:51] Basically, it's kind of essentially it's Uber eats, right? And their only thing is the eats [00:20:00] part, right? So they don't do rideshare kind of thing. There's got guys on motorbikes with like a little cooler bag in the back delivering food from any, you know, any store. I mean, it's there in the UK, it's there in Australia, it's there in a few countries. And basically I'm not 100% sure why or what the situation is, but kind of overnight they kind of went, okay, yep, we're shutting up shop. The app is no longer like the app works, but it just goes to this landing page saying, Hey, we're under administration. And then, I mean, all I'm hearing is off the news, right? So it's just straight off Channel seven or whatever ABC News or whatever it is. And they're basically like, yeah, we're going under administration. And the crazy part to me is that the. All of the all of the drivers right there, all contract just like Uber, just like a lot of those other services. So there's no severance pay, There's none of that. They're considered creditors under the employment system for that. Right. So they're essentially like any other creditor in a business waiting for the, you know, the outcomes of the administration process. So it's. Really strange new world. I don't think we've seen this on this kind of scale. Much before, I don't know. Have patterns like this existed in the past and.
+
+Harpreet: [00:21:23] Good question, man. Vince 2001. Let's hear about it.
+
+Speaker3: [00:21:30] So back when I was around your age, we had this dot com.
+
+Harpreet: [00:21:33] Bust.
+
+Speaker3: [00:21:34] And it was it was, I mean, really feeling similar to this. And although analysts are all saying that it's not going to be as bad as it was last time. Any company. Yeah. No, the hard back though. You can't get it digital. There's some old books so there's. Yeah, there's a ton of analysts who are saying it's not going to happen again. But [00:22:00] we have so many companies that are not profitable. And I think every single one of those over the next 12 months is a candidate for insolvency. If they can't figure out how to raise money and. Most of them don't really have a path to more cash. Or they can't figure out how to become profitable? I don't know. I mean, what are you going to do? You can't just keep the doors open with magic money, especially a company like Uber. How do you lose that much money and keep the doors open? I think that's where a lot of companies are. Right now, I think we're in denial because there aren't many people my age left who remember 2001. And I'm not being really as funny as it sounds like I am, because think about it. Me and ten years is retired. And so the majority of people who are in the field right now are too young to really remember it. They might have been in high school at the time or graduating from high school in college at the time. So they didn't really see it, didn't really get to study it. And all of the people who are older than my, like, small slice of Gen X are all retired or out of tech. They're doing some other kind of consulting. So there's entire companies that have no one who's ever seen something like this before. And I think that's going to that's going to have some problems because we're assuming companies are more stable than they are. And I think we're going to see a whole lot of was that a company called Deliveroo has a great name? Yeah, Deliveroo's. I think we're going to see a whole lot more Deliveroo's Underoos and companies that don't have money going under.
+
+Harpreet: [00:23:47] That's sad, man. I some companies are awesome, man. They're doing all this amazing stuff. I don't know, man. Why are you guys going to lose money like that? Why? You guys got to, like, that's got to.
+
+Speaker3: [00:23:59] It's [00:24:00] just too bad it doesn't make money. Yeah, I mean, I could. I could make $1,000,000,000 if you give me two. You know, And that's that's the truth. If you want me to make $1,000,000,000, give me 2 billion. No problem. I'll have that for you. So that's not what a business does, though.
+
+Speaker2: [00:24:18] But at what point does a business become a utility? Like you, I think if if Twitter goes under, you know how many people will be clamoring. We need a Twitter or something like that. Like. I don't know. I don't care. Personally, I don't use Twitter that much, but I'm saying there are a whole bunch of people. I think Twitter is like the best invention since sliced bread, right?
+
+Speaker3: [00:24:47] Yeah. We've always had nerds. I mean, we are nerds here. We've always had nerds that love technology and kind of overestimate the utility of it. But you're right. Search You say, when does it become a utility? Well, define the word when it has utility, When people are willing to pay more for it, it doesn't necessarily mean it'll be a utility.
+
+Speaker5: [00:25:11] Does it necessarily need to be a utility to have that kind of lash back in value, though, Like I mean. 90% of app usage is one behavioral habitual, right? Like what is the point of YouTube shorts and Instagram reels? They repeat, you can't rewind them. So if you miss something, you got to watch it again. And then the idea is to get you to interact, to switch onto the next one. So you can't just leave it in the background and do something else. You're fully engaged with the app, you'll fully engage with the advertising and everything else that's going on there. Right? So how much of this is Oh, we use that because it's some kind of utility value to us as opposed to, Hey, we're using that because it's the latest trend. It's something that, you know, socially we get sucked into using. Right. So I don't know whether it necessarily needs to be utility value for people to clamor about it and go, Oh, no, I [00:26:00] really need that. What would I do with that in my life, right?
+
+Speaker3: [00:26:03] But that's like arguing the cocaine is too big to fail. Right? That's the same argument.
+
+Speaker5: [00:26:10] Exactly. And that's not right.
+
+Speaker2: [00:26:12] But I do think, like for me, the utility is something that we all find useful. Like, no matter who we are and that, you know, but we we to a certain extent, take for granted. And so we will miss when it's gone. I would think, yeah. Twitter is ridiculous under that circumstance. But if the pandemic showed us anything, it's delivery services, you know, rideshare, you know, in the absence of taxis, of course, are somewhat of a utility. So there are essentials, you know, just like the Internet is an essential. Right. And so what would we do without them? You know, do we want to go back to the way things were, like free delivery, service, free, easy access to rides, because taxis had to step up their game to compete. And I think that was great, you know? You know, although I think, of course, the sharing economy and all that, you know, that's been, you know, going backwards in terms of workers and their their rights and everything. But I think from a user perspective, it's been great.
+
+Harpreet: [00:27:30] Just quick comment on the on right. I was you know, I was at the Jets game yesterday. I was seeing an anti trask's fellow countryman, Thomas Salamis get his jersey retired and I was trying to get a cab on Uber and I was like 40 bucks on Uber to get a ride home, which is ridiculous. And I use the app for the local taxi company and it was $21 and I was like, All right, that's more like it. But of course, I digress because I [00:28:00] don't even know where I'm getting to. But Coach would go for it.
+
+Speaker5: [00:28:03] I actually went exactly where I was going to go with it, right? Is that it's not I don't necessarily agree. So I don't think it is an essential. Right. Like there's a difference between the service being provided and the business through which that service is provided. Right? Like tomorrow, if you had publicly owned trains, for example, and the government owned train company went bust, you're in trouble because they own all of the trains, right? Like if you Roads and Maritime Services, for example, goes down the maintenance of your roads, that's a service that's absolutely essential because it's singularly owned by one entity, right? Whereas in this situation you've got taxis, you've got Ubers, you've got I mean, take delivery, right? Sure. Delivery went down. All right, cool. I guess I'll use Ubereats today, Right? Like there's enough competition still in the market to service the, the needs of the people so the service isn't gone. You're using a different app for, like, for all you know, taxis are the more long term profitable way of doing this as opposed to rideshare services. Right. And what if this is like, for example, you had other competitors in the social media space come along and then Facebook upped their game and survived, Right? Like Facebook wasn't the only like social it still isn't the only social media service.
+
+Speaker5: [00:29:21] Right. Like, the point is multiple are going to survive. And eventually the the most firm business plan models are going to survive the long run. Right. And if that is taxis and the taxis add additional services because they realize, hey, we've got guys and cars that could do stuff beyond just transport people and they could find a workable business model around it. It's just a question of human creativity, right? So I don't know, maybe I think if there is a genuine need and I think we've found valuable need from the food delivery service, particularly even more than rideshare, I'd argue. Will [00:30:00] someone step up to the game? I'm almost certain someone will. Right. Like, especially if we go into another lockdown. The food delivery services were incredible. Incredibly useful for people who had to isolate alone and couldn't get someone to drop food off for them. Right. That's. Yeah. That in its very definition is a need. Right. So.
+
+Speaker4: [00:30:20] Yeah.
+
+Harpreet: [00:30:22] Vint, let's hear from you.
+
+Speaker3: [00:30:25] I think this gets to and I'll take it a little to the left. A little bit, but or maybe to the right, I don't know, in a different direction. I think technology is really good at covering up exploitation of human labor. That's one of our biggest problems is especially in taxis are a great example because taxi companies used to buy a ton of medallions that cost a ton of money in the United States to buy a medallion. And so an individual taxi owner would not be able to afford one. Some did. And like it was something that you passed down from generation to generation where you would save up a ton of money, you'd buy a medallion and that was a business. It was essentially like a McDonald's franchise except Taxi Cab for Wheels. And so these companies would buy medallions. And if you couldn't afford to buy your own medallion, you had to go work for a taxi cab company and you worked ridiculous hours. You didn't get paid a lot. It was terrible. That's why the taxis were always so just absolutely wrecked and the people driving them weren't the nicest people on earth either. It's because it was not a great job to have. And then Uber came along and made it sound like it would be a great thing. And they just replaced the medallion system where they are now through their technology platform, doing the same exploitation.
+
+Speaker3: [00:31:42] People don't have a perception of value for a driver and a car that matches a fair wage for that driver and car. Perception of values too low. And so we're talking about right now, the technology is the deflationary force where Uber [00:32:00] creates this marketplace. And they'll somehow be able to offer these things at a lower cost because of the technology. But they can't. The technology does what's always been done just on an app instead of a switchboard. That's somebody running. And so from an efficiency standpoint, it's not a whole lot of difference from a marketplace perception of value standpoint. People aren't paying Uber drivers better than they pay taxicab drivers. And now we have Uber drivers who are their contractors. They have almost no real bargaining power when it comes to their wages. They're they're just being exploited by a technology platform. We seem to ignore the fact that that happens. And now if you look at DoorDash, you look at Uber eats, same idea, Amazon and they're driving workforce. Same idea. It seems like if you look at our perception of value for drivers and trucking industry is exactly the same thing. We don't treat truckers very well. Even though the myth is they get paid well. The majority of truckers are terribly underpaid and exploited by trucking companies.
+
+Speaker3: [00:33:11] So we still have this fundamental problem that the marketplace doesn't put enough value on a person driving a vehicle no matter what the purpose is for. And we simply do not compensate them enough to avoid exploiting them. But now we're using technology to kind of cover that fact up. And it's. So when I look at companies like Uber, I just say I like the idea. And as products like Uber Black, I like that. That's great because those companies already existed. There were already professional drivers, and it was something that did good for those companies. It made them a whole lot more accessible. They made more money. They got a lot more business. And those drivers are paid a living wage. Those drivers are paid well. And so that's an area where I think technology has improved [00:34:00] the business cycle. I think that part of the marketplace is viable. But when you begin to cover up the exploitation side of it and say at some point we'll be able to get to an economy of scale where this platform makes sense. The same thing with Twitter. We're exploiting the fact that people are addicted to the platform and we're addicting kids and we're covering up the exploitation of our views. And the amount of time that we spend on the platform. And really, we're using technology to cover that up.
+
+Speaker3: [00:34:30] We're saying, oh, no, we're providing all this amazing content. People are entertained, they love it. We're giving advertisers access to people. We're doing all this great stuff. But we're taking their attention and monetizing it. And in order to get more attention from them now, we are optimizing for addictive behaviors and we are trying to pull people onto the platform. And now we're even doing it with creators where there are platforms that are editorial. They want to drag you into a cycle of spending hours and hours and hours of your time as a creator, and they're not compensating. Youtube's a good example of this now where there is no monetization for creators until they hit a certain point. And so all those people, they're being sold the dream that you're going to be an influencer and a creator, but they're not making any money. They're putting a ton of time in and the people that are making money are Google. And so I think, like I said, taking it on a tangent, but I think we use technology way too often to cover up exploitation. And we make it sound like it's the societal good and there is a utility and it is beneficial. But you pull back all that technology and look at what's actually going on. A lot of times there's a ton of exploitation under the covers.
+
+Harpreet: [00:35:44] Because let's hear from you. Go for it.
+
+Speaker5: [00:35:48] Right. So, I mean, what I'm gathering from that is what's the first principle values of what? Services are providing or business businesses providing, right? Like is [00:36:00] Uber and rideshare services? Are they really providing ride share? Like is that the service? Is transport the service or is it accessibility to transport? Right. I would argue the technology itself of having app connected people driving cars. The provision of transport was sorted. It's people in the car. That hasn't changed. Right. So that's no different to a taxi. That's no different at all. So the real value added by the technology aspect of it is the accessibility to it. Right. And it's kind of and this is what just baffles me. Well, it doesn't baffle you, just amazes me, actually, is that what the promise of Internet bringing connected accessibility was made in what, the eighties. Right. And in a huge way and. That promise, like really took a spike 20 years later in the late nineties, and then it had to burn because they had to mess it up because they weren't providing value. They figured out that we could connect people, but clearly the dot com bubble was essentially because they couldn't figure out what to connect people for. Right. And the services that survived, the websites that survived tended to be the ones that did connect some kind of value. Right. So we're essentially seeing that next evolution step in that. Is that okay, now that we know we can connect like transport services with the Internet, right, With the magic of the Internet. Now we're getting to that point where the way in which we use that to connect transport.
+
+Speaker5: [00:37:35] So as we're going to that next level down, we're finding out that that process doesn't work. The Internet was the right thing to connect them. Yes, but then the way we use that to employ and and that's where you're like, it's weird. Like, you're right. If that sense of greed didn't get in the way, we probably could have avoided this. And just going for the true value addition, right, which is the connectivity of these apps and just said, okay, hey, taxi companies, you would be a lot [00:38:00] more serviceable if you had this connectivity in there and just focus on evolving those. So it's. That's the bit that amazes me is that we're constantly it's a battle between humanity's genius and greed almost simultaneously. And we're going to see these waves, right, of technology saying, hey, there's a promise, here's how we can use it. People figuring out a billion ways, how not to use it and figuring out how to use it, and then going to the next level of applying it, but then applying it wrong and then figuring out how to use them like. It's not. If you look at it from a historian's perspective, that's not surprising. But at the same time, it is amazing. Like to me, I'm 28, right? Like, it's amazing to me that this takes career's worth of time, right? Like this kind of big changes. They happen over like years and decades. And then you start questioning, okay, well, is that really the high priority in applying some of these technologies? But yeah, I guess I'm in a philosophical rabbit hole right now.
+
+Harpreet: [00:39:09] Advertising men. We need to. We need to go back in time and just kill the advertising companies. Like just some parallel universe out there. There's no advertisers, and we're. Or no advertising. And we're just. We're living blissfully with technology. And companies are making money. And after the accident, crash somewhere out there. Serge Love to hear from you, man. Andy, any thoughts for the riff off?
+
+Speaker2: [00:39:34] Yeah, no, I agree with custom, I think. Yeah. Like, yeah, it's to me, it's not surprising that people are exploited. To me, that's been like, you know, the theme throughout history. People have always been exploited with or without technology, right? To me, what's surprising, this is a day and age where technology is powerful enough to free ourselves from that [00:40:00] tyranny. You know, yet we find ways to kind of squeeze, you know, as much labor, human labor as possible when, you know, to be honest, we either don't need the humans because of AI or we still need them even more. And we should value them more because the productivity gains thanks to A.I.. So I think, like I it's either going to go in a direction where we're most of us are living off UBI or like power is concentrated to those that, you know, own A.I. and those that, you know, don't have anything to do with it. Or maybe it's not even a buddy AI. Maybe the future is bleak regardless of what goes on in the technology space. I mean, you know, because, you know, it's sometimes I think, you know, we're really getting dangerously close to, you know, nuclear war. And, you know, it's like, you know, aren't we past that? Right. Isn't that, you know, aren't we past the 1960s? I guess in a certain way we're not really the same. You know, we may may have evolved some software, but we're still running on fundamentally the same hardware. So I guess I wish I had more profound take on it. But, you know, that's that's my $0.02.
+
+Harpreet: [00:41:33] I love it, man. That's a that's a great, great analogy to put it. We still have the same firmware from, you know, thousands of years ago, even though we got new software updates over.
+
+Speaker5: [00:41:47] Holy shit. Then you just taught me the true meaning of leave no stone unturned. So then in the chat just wrote, Humanity will always do the right thing after exhausting [00:42:00] every other option. And oh my God, that is the genuine meaning of leave no stone unturned and I cannot be convinced otherwise. Now that's it. That's the line in the sand. That's real.
+
+Harpreet: [00:42:11] Yeah, I like that. That's a good quote. I just saw it myself. Then elaborate on this. If anybody else wants to jump out of the conversation, do let me know. And if anybody watching on LinkedIn is just enjoying this, just to smash like or or story comment right there in the chat, then go for it.
+
+Speaker3: [00:42:29] I think that's the history of humanity summed up in one line. I mean, we we always do the right thing after literally trying all the wrong ones. I mean, it's almost like we invent new wrong stuff before we do the right thing. And then, you know, for 100 years we go, why didn't we try that sooner? That's a great question. Why didn't we try that sooner? The one I love is why didn't we think of that? No, we did. We thought of that. Repeatedly. And that's just what we do as a species because we're optimizing and advertising. I like that example of advertising. We shouldn't kill advertising because we need to somehow create awareness for new companies, new products, new. We wouldn't have innovation if nobody knew it existed yet. And so we have to advertise. But I think in a smarter advertising economy, everybody would get the same amount of time. You have a very strict limit on the amount of advertising you get to put out there, and that's it. You only have that much. And so now you have to add optimize for impact, not for volume. And if we were smarter about the way that we created our complex systems, if we actually engineered the rules so that there was both social good and this concept of innovation and corporate good and progress and everything else, then we'd be fine. And we could do all of these things very easily. It's not like any of this stuff's hard to do. [00:44:00] It's only a social norm until you get rid of it. So all of the stuff's doable. It's not really that hard either. But it seems like instead of doing the obvious easy things, we will continue to do the wrong things over and over and over again from a policy standpoint until we're left with nothing else. And the problem is still there.
+
+Harpreet: [00:44:27] Ben, Thank you very much, man. I will say any other questions or comments coming in? Well, from Auntie, I like this one. Or Kosta has a question about learning resources. Well, let's go to you, Kosta, but let's read this quote that A.S. by Trujillo. You can always count on the Americans to do the right thing after they've tried everything else. This is true, of course. Go for it.
+
+Speaker5: [00:44:55] I think we could find a few dozen of those quotes so it can make a lot of t shirts for merch for this happy hour, right? Okay, so question kind of did you guys right is it's very easy to find 100 books on how to do something and YouTube videos and and Udemy courses. Pluralsight The new company I'm working for gives me full access to Pluralsight and I'm super excited about that because it's the one platform I never really got on to for learning stuff. Right? Probably should have. But yeah, I think I'm going to make the most of that. Do you guys know any resources that specifically spell out what not to do? Like great anti pattern examples because like I was looking at like it depends. Dependency injection thing at work right and it's like you can find a million YouTube videos of guys from India on YouTube explaining how dependency injection works and the rigors of doing it properly. But I can't fully describe it because, I mean, obviously it's work stuff, but yeah, those bits of it that I'm like, okay, I see what they're going for here. Like [00:46:00] they're going for a bit of dependency injection to reduce, you know, like dependency management issues, but. I was questioning whether it's the right way to do it, because it was really strange and I was really on the fence, right? So I was sitting there looking for anti pattern examples. I would love to see an anti patterns book like microservices architectures, anti patterns, right. I reckon that be worth ten times as much. So I'm wondering if you guys. Know any such resources or you guys keep lots of notes from your experiences. I'd love to collab with a few people and put together or something like this because I reckon that's the kind of stuff that would be worth its weight in gold to me. Any thoughts?
+
+Speaker2: [00:46:45] You should definitely write it. Yeah, I would. I would interview Joe and Vin, you know, and anybody here that's encountered that sort of thing. Yeah. I mean, I got to admit, like, I've seen a lot of anti patterns in web development because it's the career I spent the longest in in data science, a lot less. But I still have. But I think where you probably see the most, it's like in the practice of email apps and data engineering and in the science part, of course, but it becomes less engineering. E you know, it becomes more about statistics and so on. But. Yeah, I think. I think. Yeah, you should definitely go for it. I've never seen anything like it.
+
+Harpreet: [00:47:41] That's a dope ass YouTube channel like How Not to do it Tech Edition or, you know, whatever. Like that would be dope.
+
+Speaker5: [00:47:49] But my main concern is that it had turned into like a textbook and then it will take me 30 years to write it. So but you never know, right?
+
+Harpreet: [00:47:59] I mean, I think [00:48:00] that's probably a good, good topic that probably comes up a lot in like LinkedIn posts and things like that. I feel like that's probably the place that you'd find more of that. If anything, that should be like a hashtag that started with, you know how not to do it, hashtag how not to do it. But yeah, I like that idea, man. Let me know if you want me to put out like a a post on LinkedIn or that I'm trying to get people to to reply to that on your behalf. I'm happy to, to do that. And he says that his ears perk up every time you say. And he pattern is so close to how you pronounce my name. So questions there's actually word questions coming in on the live stream here. Just for whatever reason, LinkedIn live like, I don't see the comments pop up. Unless I go, like, through a few steps. It's weird. Mike Nash is asking, Do you think that technology is helping us to be socially aware of the use of technology? As technologists, do we play an important role in helping humanity? Do you think that technology is helping us to be socially aware of the use of technology? It's interesting question. Any thoughts on that?
+
+Speaker4: [00:49:15] Go for it. I've got a quick thought. Yeah. So if you view technology as a tool, which it is nothing more, it doesn't do anything other than what we design is to do and then what we direct it to do. Once it's built, it's it's inert. You know, it will do something good if we make it. It'll do something bad if we make it. And this kind of ties back into some of the earlier comments as well. From one of Ben's comments. I wanted to say that, you know, humanity has demonstrated through much of its evolution that it has the propensity to take the lazy solution. So whilst some will go for the hard task and do. Shouldn't [00:50:00] you take something from someone else? It's easier. It's less effort. The majority want majority, but certain people will do it. And humanity as a whole has demonstrated a willingness to do that. So I think the ability for humanity to do that is amplified by technology. When technology makes more complex actions, far more simple for people to do. Which then kind of ties back to the thing that we started with at the front.
+
+Speaker4: [00:50:32] You know, technology allowed these people to do those things, and they seem to have had some intention of doing things. This. Honestly, if the if the reports are correct and I don't know for certain that they are, but a lot of the reports seem that that was the case. And if we say then, you know, they did this on blockchain and the whole thing of blockchain is visibility. It is. But if there's no one there to look at it, what good is it? The visibility is there. There needs to be some kind of moderation and management about these things by some kind of objective observer that can identify these things. And because it's it's kind of defined, it's deregulated, that doesn't exist there at the moment, certainly not wide scale for all of these different platforms. And that's a challenge at the moment. So will that improve as crypto becomes more mature or as Web3 becomes more mature? That's a really interesting question. But even if it does, I think humanity is generally flawed to want to take that that lazy, quick one. And we'll always be we'll always be working against it.
+
+Harpreet: [00:51:43] Shortcuts, man. Always looking for shortcuts. I wonder if Costar has any thoughts on that.
+
+Speaker5: [00:51:52] Well. Regulating, but regulating entire industries and how essentially what you're getting at is how do [00:52:00] you regulate business value, Right? How do you or rather, how do you regulate the perception of business value? Because what's what's the reason all of these investments took off, Right? Right. We wanted quick returns. People wanted investments that make money on a shorter timescale. Bottom line. Right. And why is that? Because the business value is essentially measured only by money. Alibi returns. Right? On the other end of the spectrum, you seem to have public services which do focus on value addition to people. But in majority countries that have well-established public public service. Well, there's two patterns here, right? One is countries that don't have well-established public services. And, you know, there's often corruption and other things that come into play. Right. And they just don't serve as the need of the people. And on the other hand, countries that do have well-established public services. Australia is a great example. Right? Good, good medical care, good, you know, bunch of things that are pretty well done. Our trains are pretty great, especially in Sydney, right? Public transport, fantastic roads are well taken care of. And that's the value out there. But there is a huge money sink in all of those areas, right, where it's inefficiency brought in to the economy in many ways.
+
+Speaker5: [00:53:15] Right. So you kind of got these two ends of the spectrum, but nothing in the middle. And it seems to me that regulation often is battling that middle ground of having a completely publicly owned, interest focused thing versus a privately owned capital focused thing. Right? So that's where I'm like, Yeah, we're constantly fighting that weird middle ground battle. But then it comes up like, I mean, like the original question asked, is it up to the people building the technologies? Yes, because the people building the technologies isn't the engineer that's employed. It's the business that's building the technology. Let's be very, very clear about that. Right. If I were to run a business, I'm not [00:54:00] the one owning the business, and then my engineers build the stuff. I need to take personal responsibility of of the stuff that I'm building. Right. And it's a mindset thing that not every business owner has. And as an engineer, when I see leaders of a business that take that level of ownership as opposed to, you know, just come in and say, oh yeah, we own the business, and then, you know, the engineers will build some stuff, we'll make some money and then we'll sell it, right? When the owners take that ownership over, hey, we want to see a particular mission inside. And this is where mission statements become valuable, Right? So you see that they stand for something more than just capital growth.
+
+Speaker5: [00:54:36] And that gives me a lot of confidence as an engineer to say, hey, that's a company I want to work for. Like, if I had to draw one like linear model that just says work for this is not work for in the simplest possible way, it would basically just be, you know, hey, do the people at the top actually care about the mission of the company? And is that clear? And is it more than just let's make bank if it's just let's make bank. There's probably more interesting tech for me to build. So yeah, we do in a kind of very distributed democratic way, have a say in which companies succeed and fail because we make that individual choice of who we go to work for and what salary packages we choose. Right? Like, you can get paid ridiculous salaries to go work for some companies and you know, you can choose to work for the stuff that you're passionate about and the missions that you see are actually valuable in. I find more value in the latter personally. But hey, I may be super naive and young, and in 20 years I might be like, Damn man, you should have taken the other out. But you know, time will tell that. So be nice.
+
+Harpreet: [00:55:47] There's a comment coming here from Yousef on the live stream. We are in the earlier point. One general pattern is don't do the first thing that comes to mind. It usually popped [00:56:00] up because it was the most available for whatever reason and not because it's the best idea. Dig deeper, so ignore your first thoughts or your first ideas like that. Well, I think with that, we'll go ahead and wrap it up, guys. Thanks for hanging out. All right. So we'll do this next week since it is Black Friday holiday season, all that I know people with families, no data science happy hour next Friday, but the Friday after that December 2nd will be the final outside data science happy hour for for a bit of time. You know, we might bring it back next year. If I do bring it back, you will. You will all know for sure. So. If you've been listening to this for a while, I know there's a lot of you that listen to these episodes and you wanted to join. And December 2nd, 2022, coming up in like two weeks, it's going to be your chance. So just come hang out. Let's send the show off with a bang, man. Let's let's do a big and then I mean, I'm not done podcasting like you guys going to see a lot of me everywhere. Always like that just never changes. So that's that's still that's still going to be a thing. But but yeah, in general, the arts and sciences is, you know, start sunsetting this. So last happy hour will be the December 2nd. And then I've got a batch of episodes that I'm releasing and those are going to be the last batches of episodes for this podcast. But you will you'll see me on other podcasts, especially this new one coming up, which is going to be all about deep learning and you'll hear about that.
+
+Speaker4: [00:57:37] So I'm afraid it's the last one or the one on December 2nd is the last before Christmas. Do you plan to make this like the Christmas themed apps?
+
+Harpreet: [00:57:46] Yeah, yeah. Like typically in December, I always usually be wearing my, my, my ugly sweaters, Christmas sweaters. So yeah, I'm always going to do Christmas theme, but I'll switch up the lights. I have one green, one red, and we do it up Christmas style. So [00:58:00] yeah, let, let, let everyone you know know that this thing is wrapping up. It was cool, man. I remember. I remember just how bumpy this was two years ago at this time, like 50 people in the room just going crazy. It was was awesome, man. So y'all, thank you so much. That's making the official announcement where we're winding down the podcast. You are. So data science is wrapping up. There's other things on the horizon. There's that podcast I'm doing with Mark and Mexico, you know, we'll be bringing that and then the Deep Learning podcast and you'll find me everywhere else go. That's it for this, for my friends. Remember, you got one life on this planet. Why not try to do some big shit on one?
+

index/graph_store.json

@@ -0,0 +1 @@
+{"graph_dict": {}}

index/index_store.json

@@ -0,0 +1 @@
+{"index_store/data": {"53be9a68-4a03-4e52-9b29-54e75685f857": {"__type__": "document_summary", "__data__": "{\"index_id\": \"53be9a68-4a03-4e52-9b29-54e75685f857\", \"summary\": null, \"summary_id_to_node_ids\": {\"5612b271-a461-44c8-946d-1ceea397d1a8\": [\"0c70c33b-b76f-43e9-a158-e6bc5b18b769\", \"322e7753-24b0-4137-94ce-2faf3fcf0001\", \"fc3e427a-00b5-4d7e-9c4b-f48012321b61\", \"02a12b8a-341f-4090-8992-9a5d0a832a73\", \"647dec0d-bb69-4cce-91a3-519d9f502cad\", \"cfa9f6b8-b505-49ab-a10d-09f5d25c879a\", \"7afe97ce-a62c-4f9b-b472-f059a09e8858\", \"4038d9d8-9b01-41bb-8724-3fe46a1f9e1c\", \"71f1e586-076a-452d-8914-51fec98d8ca5\", \"5db4f446-4cf8-4b9a-91c3-bed777bee3c5\", \"d9f85035-ae08-4eb5-8b33-2c309cfde71a\", \"73becd25-8639-46f8-a230-bc5356f4bfcc\", \"4fee41a9-3c72-4a62-8b33-946bfc17d761\", \"fd744017-79a2-468d-b042-f30f8d25a55f\", \"db2556ea-df25-4e41-bfda-de9b46b97823\", \"bd55d09a-3f50-4d50-a235-de735aa35d76\", \"eeef3b9c-47d3-4039-8802-9fda4eb6d9db\", \"ec00161b-478b-4f64-8532-03e1011453d1\", \"378c295d-671a-46c0-9d97-88dfeb218ee6\", \"7d05d0ce-c914-4388-86d9-8d054879d5ab\", \"cf7b0788-da3e-4203-8c34-1b0df2bef084\", \"1768010d-c27d-438c-ae2e-6616e63979bb\"], \"643b5ee4-e42f-423f-8f69-39b1826e999a\": [\"987794c9-f3ad-4d4e-bb6a-029e7f95d354\", \"50f3350e-8aee-46ef-a400-83b1903288d2\", \"38ccb4e3-f204-49c0-8470-b6059d98e42c\", \"2b9bc232-b789-4c1f-a03a-c7f2ea718130\", \"ac265bd3-4885-4af4-ac1b-480191a8210c\", \"ca8f2a1b-1fe0-4f06-acbd-70a71b7ae468\", \"8566c69f-4305-4e6c-a847-91fdae40de4a\", \"9e8abd22-9466-4380-984f-a42c6bd6150e\", \"a9b5f4b7-e8b3-4c4d-8ecd-3dd45a1e6ce1\", \"8e84c165-185e-43a7-8433-1b37f98aa1c9\", \"cff38d74-f1e1-4b51-bc3a-26171559472c\", \"ca186b9b-42bd-40e7-8d93-642f37930f20\", \"ddf4b894-d06f-4beb-bcfe-2d0c61055fa3\", \"920c61b0-e8ca-40fd-afed-837f5fa8e8d0\", \"926bcea9-e172-4c7b-a7a6-161fba33ec49\", \"eee027b8-306e-4115-83df-44e4cc01a4d5\", \"ad73fad9-6773-45ee-bb56-ff6816dbb075\", \"acdf2d1b-917d-432b-b888-c12b927c3caa\", \"21606bc8-b0bb-4f0f-8ca8-68f494759655\", \"b215f059-4512-4b55-ab4d-b4bc088f0287\", \"5b709b86-2063-4c4a-9e2b-00b34f9c37c8\", \"e0807246-1e85-4cc2-8c2b-862625a04e59\", \"f79e1949-6835-424e-9a48-febe6b72a27c\", \"f3cf3eb5-eb1d-4621-95e7-b20fa9499a3c\", \"7cc8e637-1da7-42d6-ac8d-c438fb3cf939\", \"65fbd158-36a9-4274-af94-b815748c287e\", \"32db347e-3f05-4dea-8e38-6002f0b73e47\", \"84736c65-5ba3-4d47-aa84-4e9e17e9ea02\", \"ef9831b2-49d0-450e-b74a-4204bf720a3f\", \"20a53ca4-0cc9-4c51-8102-4f3352987724\", \"733e54a7-a7a6-4863-ad70-b789cee5e19e\", \"42283c50-4c69-4f55-a55e-8ae540da2abb\", \"09d67b77-3b41-44be-b4fb-3e8d5bf5591e\", \"d2bda846-e962-4ebe-9f45-6f92f4cfcda9\", \"b3a14ecc-8430-4cf7-9ca4-b809642e868c\", \"2d22dee8-fec0-4271-b7ad-0677984dc9d1\", \"a95075f2-a7e1-4b68-aae5-4f32be970525\", \"5c66114f-5fde-47e6-9c05-4f37ddc83aa0\", \"0e943440-933d-4161-b336-9b75bb5379db\", \"4549879a-2e97-49b4-8926-bc8030314ad8\", \"4db77102-7bed-4e85-86bb-49850b4befbb\", \"b61d5631-3891-4d18-af62-63e7254e7c8f\"], \"3bb62f1c-5dee-4a56-b771-3f2137290607\": [\"d30acbc3-4578-4a1d-8f29-ba2098340c2f\", \"d5c0a63e-4b33-47d9-99f4-a6e0fe7f084e\", \"cc654e3e-8b8b-4693-8a49-b91b11daaac4\", \"52071b6b-2f00-4eab-9f2a-6104b5c1c595\", \"123063fc-3a28-49d0-8bdd-8575eceacb55\", \"7db557fd-c89f-42e3-ab54-530e3604b256\", \"e7e2cd36-a9d1-4efa-86e0-e4f53745d7c8\", \"fca95410-c2cd-43db-812d-7bba3c14c6ad\", \"99802db2-90d9-4b0f-b05b-e311ca7805f5\", \"54884f9e-eaa8-43ed-887c-078aa44872f2\", \"868dbdcd-9e5f-4dc4-b9c9-36092671808f\", \"b4ca3005-f8f8-465b-b463-b344299e5ade\", \"a0cd4fd2-93cb-48fe-8090-badfadca9fe7\", \"ac095fe6-8e48-4b80-9810-999a783f9b95\", \"ca4a4a8c-4157-48e9-8d46-1ae0bc58bf0f\", \"f32a9555-7840-4472-aa8a-504c7f9b00e0\", \"d73b4fc7-458c-4cdf-a928-df05e72b76e8\", \"accdc409-6d1a-473a-a728-750948becf82\", \"cf033da1-0163-4c94-baac-fd45778cabaa\"], \"036313a6-d57c-4d42-bbb6-e34fbad99bbd\": [\"77ec9772-b8f0-4882-803d-eeeb1269b7b6\", \"99a5d677-9f8e-4316-9434-f286c80ea084\", \"fdbc4b09-299c-4c8d-a099-8c54d62e22ab\", \"ca4dbafe-d6db-47a3-90b0-0af92bbdab47\", \"9093ca19-ebb0-4cbe-a9e1-c501afb995c8\", \"01b58800-a815-4cd2-bf22-a1c8e12ca1b7\", \"edd917ea-889c-43f7-8395-6a2d04c7334d\", \"af8d90e2-2133-4e15-b71f-7cdfcab85c13\", \"0d2b5c0e-78ab-4b59-a87d-460bc83eddbb\", \"134268c6-3b5c-4a87-9250-033e3acb6e2c\", \"917b8c38-45ed-4a41-8fba-733667b4f8f9\", \"3f9cff66-3360-43fe-b8f9-358a79ce0ecb\", \"fcbfe1ba-34f3-49bb-a6c0-f7cb2635dd67\"]}, \"node_id_to_summary_id\": {\"0c70c33b-b76f-43e9-a158-e6bc5b18b769\": \"5612b271-a461-44c8-946d-1ceea397d1a8\", \"322e7753-24b0-4137-94ce-2faf3fcf0001\": \"5612b271-a461-44c8-946d-1ceea397d1a8\", \"fc3e427a-00b5-4d7e-9c4b-f48012321b61\": \"5612b271-a461-44c8-946d-1ceea397d1a8\", \"02a12b8a-341f-4090-8992-9a5d0a832a73\": \"5612b271-a461-44c8-946d-1ceea397d1a8\", \"647dec0d-bb69-4cce-91a3-519d9f502cad\": \"5612b271-a461-44c8-946d-1ceea397d1a8\", \"cfa9f6b8-b505-49ab-a10d-09f5d25c879a\": \"5612b271-a461-44c8-946d-1ceea397d1a8\", \"7afe97ce-a62c-4f9b-b472-f059a09e8858\": \"5612b271-a461-44c8-946d-1ceea397d1a8\", \"4038d9d8-9b01-41bb-8724-3fe46a1f9e1c\": \"5612b271-a461-44c8-946d-1ceea397d1a8\", \"71f1e586-076a-452d-8914-51fec98d8ca5\": \"5612b271-a461-44c8-946d-1ceea397d1a8\", \"5db4f446-4cf8-4b9a-91c3-bed777bee3c5\": \"5612b271-a461-44c8-946d-1ceea397d1a8\", \"d9f85035-ae08-4eb5-8b33-2c309cfde71a\": \"5612b271-a461-44c8-946d-1ceea397d1a8\", \"73becd25-8639-46f8-a230-bc5356f4bfcc\": \"5612b271-a461-44c8-946d-1ceea397d1a8\", \"4fee41a9-3c72-4a62-8b33-946bfc17d761\": \"5612b271-a461-44c8-946d-1ceea397d1a8\", \"fd744017-79a2-468d-b042-f30f8d25a55f\": \"5612b271-a461-44c8-946d-1ceea397d1a8\", \"db2556ea-df25-4e41-bfda-de9b46b97823\": \"5612b271-a461-44c8-946d-1ceea397d1a8\", \"bd55d09a-3f50-4d50-a235-de735aa35d76\": \"5612b271-a461-44c8-946d-1ceea397d1a8\", \"eeef3b9c-47d3-4039-8802-9fda4eb6d9db\": \"5612b271-a461-44c8-946d-1ceea397d1a8\", \"ec00161b-478b-4f64-8532-03e1011453d1\": \"5612b271-a461-44c8-946d-1ceea397d1a8\", \"378c295d-671a-46c0-9d97-88dfeb218ee6\": \"5612b271-a461-44c8-946d-1ceea397d1a8\", \"7d05d0ce-c914-4388-86d9-8d054879d5ab\": \"5612b271-a461-44c8-946d-1ceea397d1a8\", \"cf7b0788-da3e-4203-8c34-1b0df2bef084\": \"5612b271-a461-44c8-946d-1ceea397d1a8\", \"1768010d-c27d-438c-ae2e-6616e63979bb\": \"5612b271-a461-44c8-946d-1ceea397d1a8\", \"987794c9-f3ad-4d4e-bb6a-029e7f95d354\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"50f3350e-8aee-46ef-a400-83b1903288d2\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"38ccb4e3-f204-49c0-8470-b6059d98e42c\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"2b9bc232-b789-4c1f-a03a-c7f2ea718130\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"ac265bd3-4885-4af4-ac1b-480191a8210c\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"ca8f2a1b-1fe0-4f06-acbd-70a71b7ae468\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"8566c69f-4305-4e6c-a847-91fdae40de4a\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"9e8abd22-9466-4380-984f-a42c6bd6150e\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"a9b5f4b7-e8b3-4c4d-8ecd-3dd45a1e6ce1\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"8e84c165-185e-43a7-8433-1b37f98aa1c9\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"cff38d74-f1e1-4b51-bc3a-26171559472c\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"ca186b9b-42bd-40e7-8d93-642f37930f20\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"ddf4b894-d06f-4beb-bcfe-2d0c61055fa3\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"920c61b0-e8ca-40fd-afed-837f5fa8e8d0\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"926bcea9-e172-4c7b-a7a6-161fba33ec49\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"eee027b8-306e-4115-83df-44e4cc01a4d5\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"ad73fad9-6773-45ee-bb56-ff6816dbb075\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"acdf2d1b-917d-432b-b888-c12b927c3caa\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"21606bc8-b0bb-4f0f-8ca8-68f494759655\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"b215f059-4512-4b55-ab4d-b4bc088f0287\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"5b709b86-2063-4c4a-9e2b-00b34f9c37c8\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"e0807246-1e85-4cc2-8c2b-862625a04e59\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"f79e1949-6835-424e-9a48-febe6b72a27c\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"f3cf3eb5-eb1d-4621-95e7-b20fa9499a3c\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"7cc8e637-1da7-42d6-ac8d-c438fb3cf939\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"65fbd158-36a9-4274-af94-b815748c287e\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"32db347e-3f05-4dea-8e38-6002f0b73e47\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"84736c65-5ba3-4d47-aa84-4e9e17e9ea02\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"ef9831b2-49d0-450e-b74a-4204bf720a3f\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"20a53ca4-0cc9-4c51-8102-4f3352987724\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"733e54a7-a7a6-4863-ad70-b789cee5e19e\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"42283c50-4c69-4f55-a55e-8ae540da2abb\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"09d67b77-3b41-44be-b4fb-3e8d5bf5591e\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"d2bda846-e962-4ebe-9f45-6f92f4cfcda9\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"b3a14ecc-8430-4cf7-9ca4-b809642e868c\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"2d22dee8-fec0-4271-b7ad-0677984dc9d1\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"a95075f2-a7e1-4b68-aae5-4f32be970525\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"5c66114f-5fde-47e6-9c05-4f37ddc83aa0\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"0e943440-933d-4161-b336-9b75bb5379db\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"4549879a-2e97-49b4-8926-bc8030314ad8\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"4db77102-7bed-4e85-86bb-49850b4befbb\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"b61d5631-3891-4d18-af62-63e7254e7c8f\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"d30acbc3-4578-4a1d-8f29-ba2098340c2f\": \"3bb62f1c-5dee-4a56-b771-3f2137290607\", \"d5c0a63e-4b33-47d9-99f4-a6e0fe7f084e\": \"3bb62f1c-5dee-4a56-b771-3f2137290607\", \"cc654e3e-8b8b-4693-8a49-b91b11daaac4\": \"3bb62f1c-5dee-4a56-b771-3f2137290607\", \"52071b6b-2f00-4eab-9f2a-6104b5c1c595\": \"3bb62f1c-5dee-4a56-b771-3f2137290607\", \"123063fc-3a28-49d0-8bdd-8575eceacb55\": \"3bb62f1c-5dee-4a56-b771-3f2137290607\", \"7db557fd-c89f-42e3-ab54-530e3604b256\": \"3bb62f1c-5dee-4a56-b771-3f2137290607\", \"e7e2cd36-a9d1-4efa-86e0-e4f53745d7c8\": \"3bb62f1c-5dee-4a56-b771-3f2137290607\", \"fca95410-c2cd-43db-812d-7bba3c14c6ad\": \"3bb62f1c-5dee-4a56-b771-3f2137290607\", \"99802db2-90d9-4b0f-b05b-e311ca7805f5\": \"3bb62f1c-5dee-4a56-b771-3f2137290607\", \"54884f9e-eaa8-43ed-887c-078aa44872f2\": \"3bb62f1c-5dee-4a56-b771-3f2137290607\", \"868dbdcd-9e5f-4dc4-b9c9-36092671808f\": \"3bb62f1c-5dee-4a56-b771-3f2137290607\", \"b4ca3005-f8f8-465b-b463-b344299e5ade\": \"3bb62f1c-5dee-4a56-b771-3f2137290607\", \"a0cd4fd2-93cb-48fe-8090-badfadca9fe7\": \"3bb62f1c-5dee-4a56-b771-3f2137290607\", \"ac095fe6-8e48-4b80-9810-999a783f9b95\": \"3bb62f1c-5dee-4a56-b771-3f2137290607\", \"ca4a4a8c-4157-48e9-8d46-1ae0bc58bf0f\": \"3bb62f1c-5dee-4a56-b771-3f2137290607\", \"f32a9555-7840-4472-aa8a-504c7f9b00e0\": \"3bb62f1c-5dee-4a56-b771-3f2137290607\", \"d73b4fc7-458c-4cdf-a928-df05e72b76e8\": \"3bb62f1c-5dee-4a56-b771-3f2137290607\", \"accdc409-6d1a-473a-a728-750948becf82\": \"3bb62f1c-5dee-4a56-b771-3f2137290607\", \"cf033da1-0163-4c94-baac-fd45778cabaa\": \"3bb62f1c-5dee-4a56-b771-3f2137290607\", \"77ec9772-b8f0-4882-803d-eeeb1269b7b6\": \"036313a6-d57c-4d42-bbb6-e34fbad99bbd\", \"99a5d677-9f8e-4316-9434-f286c80ea084\": \"036313a6-d57c-4d42-bbb6-e34fbad99bbd\", \"fdbc4b09-299c-4c8d-a099-8c54d62e22ab\": \"036313a6-d57c-4d42-bbb6-e34fbad99bbd\", \"ca4dbafe-d6db-47a3-90b0-0af92bbdab47\": \"036313a6-d57c-4d42-bbb6-e34fbad99bbd\", \"9093ca19-ebb0-4cbe-a9e1-c501afb995c8\": \"036313a6-d57c-4d42-bbb6-e34fbad99bbd\", \"01b58800-a815-4cd2-bf22-a1c8e12ca1b7\": \"036313a6-d57c-4d42-bbb6-e34fbad99bbd\", \"edd917ea-889c-43f7-8395-6a2d04c7334d\": \"036313a6-d57c-4d42-bbb6-e34fbad99bbd\", \"af8d90e2-2133-4e15-b71f-7cdfcab85c13\": \"036313a6-d57c-4d42-bbb6-e34fbad99bbd\", \"0d2b5c0e-78ab-4b59-a87d-460bc83eddbb\": \"036313a6-d57c-4d42-bbb6-e34fbad99bbd\", \"134268c6-3b5c-4a87-9250-033e3acb6e2c\": \"036313a6-d57c-4d42-bbb6-e34fbad99bbd\", \"917b8c38-45ed-4a41-8fba-733667b4f8f9\": \"036313a6-d57c-4d42-bbb6-e34fbad99bbd\", \"3f9cff66-3360-43fe-b8f9-358a79ce0ecb\": \"036313a6-d57c-4d42-bbb6-e34fbad99bbd\", \"fcbfe1ba-34f3-49bb-a6c0-f7cb2635dd67\": \"036313a6-d57c-4d42-bbb6-e34fbad99bbd\"}, \"doc_id_to_summary_id\": {\"../data/final-hh.txt\": \"5612b271-a461-44c8-946d-1ceea397d1a8\", \"../data/hh100.txt\": \"643b5ee4-e42f-423f-8f69-39b1826e999a\", \"../data/hh101.txt\": \"3bb62f1c-5dee-4a56-b771-3f2137290607\", \"../data/hh103.txt\": \"036313a6-d57c-4d42-bbb6-e34fbad99bbd\"}}"}}}

index/vector_store.json

@@ -0,0 +1 @@
+{"embedding_dict": {}, "text_id_to_ref_doc_id": {}}

notebooks/.chainlit/config.toml

@@ -0,0 +1,72 @@
+[project]
+# If true (default), the app will be available to anonymous users.
+# If false, users will need to authenticate and be part of the project to use the app.
+public = true
+
+# The project ID (found on https://cloud.chainlit.io).
+# The project ID is required when public is set to false or when using the cloud database.
+#id = ""
+
+# Uncomment if you want to persist the chats.
+# local will create a database in your .chainlit directory (requires node.js installed).
+# cloud will use the Chainlit cloud database.
+# custom will load use your custom client.
+# database = "local"
+
+# Whether to enable telemetry (default: true). No personal data is collected.
+enable_telemetry = true
+
+# List of environment variables to be provided by each user to use the app.
+user_env = []
+
+# Duration (in seconds) during which the session is saved when the connection is lost
+session_timeout = 3600
+
+# Enable third parties caching (e.g LangChain cache)
+cache = false
+
+# Follow symlink for asset mount (see https://github.com/Chainlit/chainlit/issues/317)
+# follow_symlink = false
+
+# Chainlit server address
+# chainlit_server = ""
+
+[UI]
+# Name of the app and chatbot.
+name = "Chatbot"
+
+# Description of the app and chatbot. This is used for HTML tags.
+# description = ""
+
+# The default value for the expand messages settings.
+default_expand_messages = false
+
+# Hide the chain of thought details from the user in the UI.
+hide_cot = false
+
+# Link to your github repo. This will add a github button in the UI's header.
+# github = ""
+
+# Override default MUI light theme. (Check theme.ts)
+[UI.theme.light]
+    #background = "#FAFAFA"
+    #paper = "#FFFFFF"
+
+    [UI.theme.light.primary]
+        #main = "#F80061"
+        #dark = "#980039"
+        #light = "#FFE7EB"
+
+# Override default MUI dark theme. (Check theme.ts)
+[UI.theme.dark]
+    #background = "#FAFAFA"
+    #paper = "#FFFFFF"
+
+    [UI.theme.dark.primary]
+        #main = "#F80061"
+        #dark = "#980039"
+        #light = "#FFE7EB"
+
+
+[meta]
+generated_by = "0.6.402"

notebooks/app.py

@@ -0,0 +1,129 @@
+import os
+import openai
+from langchain.chat_models import ChatOpenAI
+import chainlit as cl
+
+from langchain.chains import LLMChain, SequentialChain 
+from langchain.prompts import PromptTemplate
+
+from llama_index.query_engine.retriever_query_engine import RetrieverQueryEngine
+from llama_index.callbacks.base import CallbackManager
+from llama_index import (
+    LLMPredictor,
+    ServiceContext,
+    StorageContext,
+    load_index_from_storage,
+)
+
+from llama_index import (
+    SimpleDirectoryReader,
+    LLMPredictor,
+    ServiceContext,
+    get_response_synthesizer,
+)
+from llama_index.indices.document_summary import DocumentSummaryIndex
+from llama_index.llms import OpenAI
+
+openai.api_key = os.environ["OPENAI_API_KEY"]
+
+
+from llama_index import SimpleDirectoryReader
+
+required_exts = [".txt"]
+
+reader = SimpleDirectoryReader(
+    input_dir="../data",
+    required_exts=required_exts,
+    recursive=True,
+    filename_as_id=True
+)
+
+docs = reader.load_data()
+print(f"Loaded {len(docs)} docs")
+
+chatgpt = OpenAI(temperature=0.1, model="gpt-3.5-turbo")
+service_context = ServiceContext.from_defaults(llm=chatgpt, chunk_size=1024)
+
+response_synthesizer = get_response_synthesizer(
+    response_mode="tree_summarize", use_async=True
+)
+
+doc_summary_index = DocumentSummaryIndex.from_documents(
+    docs,
+    service_context=service_context,
+    response_synthesizer=response_synthesizer,
+)
+
+#print(doc_summary_index.get_document_summary('../data/final-hh.txt'))
+
+@cl.on_chat_start
+async def factory():
+    llm_predictor = LLMPredictor(
+        llm=ChatOpenAI(
+            temperature=0,
+            model_name="gpt-3.5-turbo",
+            streaming=True,
+        ),
+    )
+    service_context = ServiceContext.from_defaults(
+        llm_predictor=llm_predictor,
+        chunk_size=512,
+        callback_manager=CallbackManager([cl.LlamaIndexCallbackHandler()]),
+    )
+
+    
+    generation_type = None
+
+    twitter_expert_prompt = "You are a twitter expert. Create a twitter thread based on this: "
+    
+    summary_text = doc_summary_index.get_document_summary('../data/final-hh.txt')
+    summary_text_without_newlines = summary_text.strip()
+    prompt = twitter_expert_prompt + summary_text
+    
+    twitter_prompt = twitter_expert_prompt + summary_text_without_newlines
+    twitter_prompt_template = PromptTemplate.from_template(
+        twitter_expert_prompt
+    )
+    
+    while generation_type == None:
+        generation_type = await cl.AskUserMessage(
+            content="Twitter or blog?", timeout=15
+        ).send()
+        
+        if generation_type == 'twitter':
+            print("twitter generation...")
+        elif generation_type == 'blog':
+            print("blog generation...")
+        
+    cl.Message(content=f"generating {generation_type['content']} thread").send()
+    
+    
+    
+    prompt = 'write a tweet about' + summary_text
+    print(f'prompt: {prompt}')
+    
+    
+    llm_twitter_expert = ChatOpenAI(model='gpt-3.5-turbo', temperature=0.7)
+    tweet_thread_chain = LLMChain(llm=llm_twitter_expert,prompt=twitter_prompt_template) 
+    #tweet_thread = tweet_thread_chain.run(prompt=prompt)
+    #await cl.Message(content=tweet_thread).send()
+    
+    the_final_prompt = f"write a twitter thread about {summary_text_without_newlines}"
+    
+    response = openai.ChatCompletion.create(
+        model="gpt-3.5-turbo",
+        messages=[
+            {"role": "system", "content": "You are a twitter expert."},
+            #{"role": "assistant", "content": "{summary_text_without_newlines}"},
+            {"role": "user", "content": the_final_prompt},
+        ]
+    )
+    await cl.Message(content=response['choices'][0]['message']['content']).send()
+    
+    
+    
+    #await cl.Message(content=f"generating {doc_summary_index.get_document_summary('../data/final-hh.txt')}").send()
+ 
+
+
+

notebooks/app2.py

@@ -0,0 +1 @@
+import openai

notebooks/chainlit.md

@@ -0,0 +1,14 @@
+# Welcome to Chainlit! 🚀🤖
+
+Hi there, Developer! 👋 We're excited to have you on board. Chainlit is a powerful tool designed to help you prototype, debug and share applications built on top of LLMs.
+
+## Useful Links 🔗
+
+- **Documentation:** Get started with our comprehensive [Chainlit Documentation](https://docs.chainlit.io) 📚
+- **Discord Community:** Join our friendly [Chainlit Discord](https://discord.gg/k73SQ3FyUh) to ask questions, share your projects, and connect with other developers! 💬
+
+We can't wait to see what you create with Chainlit! Happy coding! 💻😊
+
+## Welcome screen
+
+To modify the welcome screen, edit the `chainlit.md` file at the root of your project. If you do not want a welcome screen, just leave this file empty.

notebooks/storage/docstore.json

@@ -0,0 +1 @@
+{"docstore/metadata": {"073fd534-219b-4176-8d30-5cb9f8a2b7da": {"doc_hash": "165fc075a6907fa3f93245a123a31f2a1d42d9b188c83425aa019005e0570c8c"}, "3400207d-0101-4f32-83d6-b6f25ec33c65": {"doc_hash": "c0727fbc21b962a27dbd064cc7347ce581aa4cb370ad9b80b1fb4094caed764f", "ref_doc_id": "073fd534-219b-4176-8d30-5cb9f8a2b7da"}, "1e461525-e8c6-46e5-9c46-30af41c20f3c": {"doc_hash": "66fa80a4ed57c1ea69b37dcc5c22455e8322e36cf1d893d3ef953e68c03291e4", "ref_doc_id": "073fd534-219b-4176-8d30-5cb9f8a2b7da"}, "9c81ecd3-9c00-4fce-b5f7-bdfbcaacc119": {"doc_hash": "a669d38458963080f56de2bc8969a10d58aad9afdb10c0e070d91f162d7610c1", "ref_doc_id": "073fd534-219b-4176-8d30-5cb9f8a2b7da"}, "7abfcf66-fe5c-4c29-8377-1661dc23bac8": {"doc_hash": "3c4611a44700b0ff9960fc740aaa9c30d493bed70b8b2dfc30bf9cde6b09477e", "ref_doc_id": "073fd534-219b-4176-8d30-5cb9f8a2b7da"}, "b57084f5-5c54-48d4-83d8-81e93dead105": {"doc_hash": "e6d6642aaeb58e42c8358eb0dd020a1de421392a4f901241e2a1cef40b117f93", "ref_doc_id": "073fd534-219b-4176-8d30-5cb9f8a2b7da"}, "4f8e6f1c-734f-4974-8efa-7a79191f15ae": {"doc_hash": "4da418705b289bb731c1c930e28e9fe5e303b4aedb2f7e72fd910829bf1cc866", "ref_doc_id": "073fd534-219b-4176-8d30-5cb9f8a2b7da"}, "06dea7be-7678-4705-aee4-28f9e8fd00ad": {"doc_hash": "06f8e583b01366fb765d32573f2ab54df65b1131ad330425e41b3b26427b86c0", "ref_doc_id": "073fd534-219b-4176-8d30-5cb9f8a2b7da"}, "0b2d9c65-f09d-423a-ae0a-3f2856754433": {"doc_hash": "9e632e3f5539095bc8a4bfdb2c00d5f92eaca09209152e5459a65824e85dc811", "ref_doc_id": "073fd534-219b-4176-8d30-5cb9f8a2b7da"}, "54f7120b-247a-4f3f-9d57-20f0c839446e": {"doc_hash": "c34da4a4a99824b76e4b473247c800c37cffef7b4d3f9b62dca2452582c08719", "ref_doc_id": "073fd534-219b-4176-8d30-5cb9f8a2b7da"}, "62f6aedc-eb3c-4062-9cb1-6c8e5b3fbd88": {"doc_hash": "ef20c02a60a952bded823a6bd086a98ed854235200437c9a91d2b5b1eb56ca86", "ref_doc_id": "073fd534-219b-4176-8d30-5cb9f8a2b7da"}, "4ba80387-aa10-40df-8d13-7117665b33d0": {"doc_hash": "8dba5d0cf9810f57dac268c87e1fe5c9662add855b8a7bac8575b96a0bf24851", "ref_doc_id": "073fd534-219b-4176-8d30-5cb9f8a2b7da"}, "0a2efa94-5943-467f-a8c8-0b5153290cd2": {"doc_hash": "93fea5636ac054d0895648dc874527be41db91afa4d1c245af5ef0f30ef25e3a", "ref_doc_id": "073fd534-219b-4176-8d30-5cb9f8a2b7da"}, "676e6185-26cd-4ad7-bbea-75a682c0be37": {"doc_hash": "195df4932fbdade1f5fe90f8e374dfdcee66b19a193f7a28a4f40bfbcce269e3", "ref_doc_id": "073fd534-219b-4176-8d30-5cb9f8a2b7da"}}, "docstore/data": {"3400207d-0101-4f32-83d6-b6f25ec33c65": {"__data__": {"id_": "3400207d-0101-4f32-83d6-b6f25ec33c65", "embedding": null, "metadata": {}, "excluded_embed_metadata_keys": [], "excluded_llm_metadata_keys": [], "relationships": {"1": {"node_id": "073fd534-219b-4176-8d30-5cb9f8a2b7da", "node_type": null, "metadata": {}, "hash": "165fc075a6907fa3f93245a123a31f2a1d42d9b188c83425aa019005e0570c8c"}, "3": {"node_id": "1e461525-e8c6-46e5-9c46-30af41c20f3c", "node_type": null, "metadata": {}, "hash": "66fa80a4ed57c1ea69b37dcc5c22455e8322e36cf1d893d3ef953e68c03291e4"}}, "hash": "c0727fbc21b962a27dbd064cc7347ce581aa4cb370ad9b80b1fb4094caed764f", "text": "{\"payload\":{\"allShortcutsEnabled\":false,\"fileTree\":{\"docs/extras/modules\":{\"items\":[{\"name\":\"agents\",\"path\":\"docs/extras/modules/agents\",\"contentType\":\"directory\"},{\"name\":\"callbacks\",\"path\":\"docs/extras/modules/callbacks\",\"contentType\":\"directory\"},{\"name\":\"chains\",\"path\":\"docs/extras/modules/chains\",\"contentType\":\"directory\"},{\"name\":\"data_connection\",\"path\":\"docs/extras/modules/data_connection\",\"contentType\":\"directory\"},{\"name\":\"memory\",\"path\":\"docs/extras/modules/memory\",\"contentType\":\"directory\"},{\"name\":\"model_io\",\"path\":\"docs/extras/modules/model_io\",\"contentType\":\"directory\"},{\"name\":\"paul_graham_essay.txt\",\"path\":\"docs/extras/modules/paul_graham_essay.txt\",\"contentType\":\"file\"},{\"name\":\"state_of_the_union.txt\",\"path\":\"docs/extras/modules/state_of_the_union.txt\",\"contentType\":\"file\"}],\"totalCount\":8},\"docs/extras\":{\"items\":[{\"name\":\"_templates\",\"path\":\"docs/extras/_templates\",\"contentType\":\"directory\"},{\"name\":\"additional_resources\",\"path\":\"docs/extras/additional_resources\",\"contentType\":\"directory\"},{\"name\":\"expression_language\",\"path\":\"docs/extras/expression_language\",\"contentType\":\"directory\"},{\"name\":\"guides\",\"path\":\"docs/extras/guides\",\"contentType\":\"directory\"},{\"name\":\"integrations\",\"path\":\"docs/extras/integrations\",\"contentType\":\"directory\"},{\"name\":\"modules\",\"path\":\"docs/extras/modules\",\"contentType\":\"directory\"},{\"name\":\"use_cases\",\"path\":\"docs/extras/use_cases\",\"contentType\":\"directory\"}],\"totalCount\":7},\"docs\":{\"items\":[{\"name\":\"api_reference\",\"path\":\"docs/api_reference\",\"contentType\":\"directory\"},{\"name\":\"docs_skeleton\",\"path\":\"docs/docs_skeleton\",\"contentType\":\"directory\"},{\"name\":\"extras\",\"path\":\"docs/extras\",\"contentType\":\"directory\"},{\"name\":\"snippets\",\"path\":\"docs/snippets\",\"contentType\":\"directory\"},{\"name\":\".local_build.sh\",\"path\":\"docs/.local_build.sh\",\"contentType\":\"file\"},{\"name\":\"package-lock.json\",\"path\":\"docs/package-lock.json\",\"contentType\":\"file\"},{\"name\":\"vercel_requirements.txt\",\"path\":\"docs/vercel_requirements.txt\",\"contentType\":\"file\"}],\"totalCount\":7},\"\":{\"items\":[{\"name\":\".devcontainer\",\"path\":\".devcontainer\",\"contentType\":\"directory\"},{\"name\":\".github\",\"path\":\".github\",\"contentType\":\"directory\"},{\"name\":\"docs\",\"path\":\"docs\",\"contentType\":\"directory\"},{\"name\":\"libs\",\"path\":\"libs\",\"contentType\":\"directory\"},{\"name\":\".gitattributes\",\"path\":\".gitattributes\",\"contentType\":\"file\"},{\"name\":\".gitignore\",\"path\":\".gitignore\",\"contentType\":\"file\"},{\"name\":\".gitmodules\",\"path\":\".gitmodules\",\"contentType\":\"file\"},{\"name\":\".readthedocs.yaml\",\"path\":\".readthedocs.yaml\",\"contentType\":\"file\"},{\"name\":\"CITATION.cff\",\"path\":\"CITATION.cff\",\"contentType\":\"file\"},{\"name\":\"LICENSE\",\"path\":\"LICENSE\",\"contentType\":\"file\"},{\"name\":\"MIGRATE.md\",\"path\":\"MIGRATE.md\",\"contentType\":\"file\"},{\"name\":\"Makefile\",\"path\":\"Makefile\",\"contentType\":\"file\"},{\"name\":\"README.md\",\"path\":\"README.md\",\"contentType\":\"file\"},{\"name\":\"SECURITY.md\",\"path\":\"SECURITY.md\",\"contentType\":\"file\"},{\"name\":\"poetry.lock\",\"path\":\"poetry.lock\",\"contentType\":\"file\"},{\"name\":\"poetry.toml\",\"path\":\"poetry.toml\",\"contentType\":\"file\"},{\"name\":\"pyproject.toml\",\"path\":\"pyproject.toml\",\"contentType\":\"file\"}],", "start_char_idx": null, "end_char_idx": null, "text_template": "{metadata_str}\n\n{content}", "metadata_template": "{key}: {value}", "metadata_seperator": "\n"}, "__type__": "1"}, "1e461525-e8c6-46e5-9c46-30af41c20f3c": {"__data__": {"id_": "1e461525-e8c6-46e5-9c46-30af41c20f3c", "embedding": null, "metadata": {}, "excluded_embed_metadata_keys": [], "excluded_llm_metadata_keys": [], "relationships": {"1": {"node_id": "073fd534-219b-4176-8d30-5cb9f8a2b7da", "node_type": null, "metadata": {}, "hash": "165fc075a6907fa3f93245a123a31f2a1d42d9b188c83425aa019005e0570c8c"}, "2": {"node_id": "3400207d-0101-4f32-83d6-b6f25ec33c65", "node_type": null, "metadata": {}, "hash": "c0727fbc21b962a27dbd064cc7347ce581aa4cb370ad9b80b1fb4094caed764f"}, "3": {"node_id": "9c81ecd3-9c00-4fce-b5f7-bdfbcaacc119", "node_type": null, "metadata": {}, "hash": "a669d38458963080f56de2bc8969a10d58aad9afdb10c0e070d91f162d7610c1"}}, "hash": "66fa80a4ed57c1ea69b37dcc5c22455e8322e36cf1d893d3ef953e68c03291e4", "text": "\"totalCount\":17}},\"fileTreeProcessingTime\":19.441169000000002,\"foldersToFetch\":[],\"reducedMotionEnabled\":null,\"repo\":{\"id\":552661142,\"defaultBranch\":\"master\",\"name\":\"langchain\",\"ownerLogin\":\"langchain-ai\",\"currentUserCanPush\":false,\"isFork\":false,\"isEmpty\":false,\"createdAt\":\"2022-10-17T02:58:36.000Z\",\"ownerAvatar\":\"https://avatars.githubusercontent.com/u/126733545?v=4\",\"public\":true,\"private\":false,\"isOrgOwned\":true},\"symbolsExpanded\":false,\"treeExpanded\":true,\"refInfo\":{\"name\":\"master\",\"listCacheKey\":\"v0:1694105337.0\",\"canEdit\":false,\"refType\":\"branch\",\"currentOid\":\"f0ccce76fea91d6dfd243a357fd6b2ce7f7f7cdb\"},\"path\":\"docs/extras/modules/state_of_the_union.txt\",\"currentUser\":null,\"blob\":{\"rawLines\":[\"Madam Speaker, Madam Vice President, our First Lady and Second Gentleman.Members of Congress and the Cabinet.Justices of the Supreme Court.My fellow Americans.\",\"\",\"Last year COVID-19 kept us apart.This year we are finally together again.\",\"\",\"Tonight, we meet as Democrats Republicans and Independents.But most importantly as Americans.\",\"\",\"With a duty to one another to the American people to the Constitution.\",\"\",\"And with an unwavering resolve that freedom will always triumph over tyranny.\",\"\",\"Six days ago, Russia\u2019s Vladimir Putin sought to shake the foundations of the free world thinking he could make it bend to his menacing ways.But he badly miscalculated.\",\"\",\"He thought he could roll into Ukraine and the world would roll over.Instead he met a wall of strength he never imagined.\",\"\",\"He met the Ukrainian people.\",\"\",\"From President Zelenskyy to every Ukrainian, their fearlessness, their courage, their determination, inspires the world.\",\"\",\"Groups of citizens blocking tanks with their bodies.Everyone from students to retirees teachers turned soldiers defending their homeland.\",\"\",\"In this struggle as President Zelenskyy said in his speech to the European Parliament \u201cLight will win over darkness.\u201d The Ukrainian Ambassador to the United States is here tonight.\",\"\",\"Let each of us here tonight in this Chamber send an unmistakable signal to Ukraine and to the world.\",\"\",\"Please rise if you are able and show that, Yes, we the United States of America stand with the Ukrainian people.\",\"\",\"Throughout our history we\u2019ve learned this lesson when dictators do not pay a price for their aggression they cause more chaos.\",\"\",\"They keep moving.\",\"\",\"And the costs and the threats to America and the world keep rising.\",\"\",\"That\u2019s why the NATO Alliance was created to secure peace and stability in Europe after World War 2.\",\"\",\"The United States is a member along with 29 other nations.\",\"\",\"It matters.American diplomacy matters.American resolve matters.\",\"\",\"Putin\u2019s latest attack on Ukraine was premeditated and unprovoked.\",\"\",\"He rejected repeated efforts at diplomacy.\",\"\",\"He thought the West and NATO wouldn\u2019t respond.And he thought he could divide us at home.Putin was wrong.We were ready.Here is what we did.\",\"\",\"We prepared extensively and carefully.\",\"\",\"We spent months building a coalition of other freedom-loving nations from Europe and the Americas to Asia and Africa to confront Putin.\",\"\",\"I spent countless hours unifying our European allies.We shared with the world in advance what we knew Putin was planning and precisely how he would try to falsely justify his aggression.\",\"\",\"We countered Russia\u2019s lies with truth.\",\"\",\"And now that he has acted the free world is holding him accountable.\",\"\",\"Along with twenty-seven members of the European Union including France, Germany, Italy, as well as countries like the United Kingdom, Canada, Japan, Korea, Australia, New Zealand, and many others, even Switzerland.\",\"\",\"We are inflicting pain on Russia and supporting the people of Ukraine.Putin is now isolated from the world more than ever.\",\"\",\"Together with our allies \u2013we are right now enforcing powerful economic sanctions.\",\"\",\"We are cutting off Russia\u2019s largest banks from the international financial system.\",\"\",\"Preventing Russia\u2019s central bank from defending the Russian Ruble making Putin\u2019s $630 Billion \u201cwar fund\u201d worthless.", "start_char_idx": null, "end_char_idx": null, "text_template": "{metadata_str}\n\n{content}", "metadata_template": "{key}: {value}", "metadata_seperator": "\n"}, "__type__": "1"}, "9c81ecd3-9c00-4fce-b5f7-bdfbcaacc119": {"__data__": {"id_": "9c81ecd3-9c00-4fce-b5f7-bdfbcaacc119", "embedding": null, "metadata": {}, "excluded_embed_metadata_keys": [], "excluded_llm_metadata_keys": [], "relationships": {"1": {"node_id": "073fd534-219b-4176-8d30-5cb9f8a2b7da", "node_type": null, "metadata": {}, "hash": "165fc075a6907fa3f93245a123a31f2a1d42d9b188c83425aa019005e0570c8c"}, "2": {"node_id": "1e461525-e8c6-46e5-9c46-30af41c20f3c", "node_type": null, "metadata": {}, "hash": "66fa80a4ed57c1ea69b37dcc5c22455e8322e36cf1d893d3ef953e68c03291e4"}, "3": {"node_id": "7abfcf66-fe5c-4c29-8377-1661dc23bac8", "node_type": null, "metadata": {}, "hash": "3c4611a44700b0ff9960fc740aaa9c30d493bed70b8b2dfc30bf9cde6b09477e"}}, "hash": "a669d38458963080f56de2bc8969a10d58aad9afdb10c0e070d91f162d7610c1", "text": "\",\"\",\"We are choking off Russia\u2019s access to technology that will sap its economic strength and weaken its military for years to come.\",\"\",\"Tonight I say to the Russian oligarchs and corrupt leaders who have bilked billions of dollars off this violent regime no more.\",\"\",\"The U.S. Department of Justice is assembling a dedicated task force to go after the crimes of Russian oligarchs.\",\"\",\"We are joining with our European allies to find and seize your yachts your luxury apartments your private jets.We are coming for your ill-begotten gains.\",\"\",\"And tonight I am announcing that we will join our allies in closing off American air space to all Russian flights \u2013 further isolating Russia \u2013 and adding an additional squeeze \u2013on their economy.The Ruble has lost 30% of its value.\",\"\",\"The Russian stock market has lost 40% of its value and trading remains suspended.Russia\u2019s economy is reeling and Putin alone is to blame.\",\"\",\"Together with our allies we are providing support to the Ukrainians in their fight for freedom.Military assistance.Economic assistance.Humanitarian assistance.\",\"\",\"We are giving more than $1 Billion in direct assistance to Ukraine.\",\"\",\"And we will continue to aid the Ukrainian people as they defend their country and to help ease their suffering.\",\"\",\"Let me be clear, our forces are not engaged and will not engage in conflict with Russian forces in Ukraine.\",\"\",\"Our forces are not going to Europe to fight in Ukraine, but to defend our NATO Allies \u2013 in the event that Putin decides to keep moving west.\",\"\",\"For that purpose we\u2019ve mobilized American ground forces, air squadrons, and ship deployments to protect NATO countries including Poland, Romania, Latvia, Lithuania, and Estonia.\",\"\",\"As I have made crystal clear the United States and our Allies will defend every inch of territory of NATO countries with the full force of our collective power.\",\"\",\"And we remain clear-eyed.The Ukrainians are fighting back with pure courage.But the next few days weeks, months, will be hard on them.\",\"\",\"Putin has unleashed violence and chaos.But while he may make gains on the battlefield \u2013 he will pay a continuing high price over the long run.\",\"\",\"And a proud Ukrainian people, who have known 30 years  of independence, have repeatedly shown that they will not tolerate anyone who tries to take their country backwards.\",\"\",\"To all Americans, I will be honest with you, as I\u2019ve always promised.A Russian dictator, invading a foreign country, has costs around the world.\",\"\",\"And I\u2019m taking robust action to make sure the pain of our sanctions  is targeted at Russia\u2019s economy.And I will use every tool at our disposal to protect American businesses and consumers.\",\"\",\"Tonight, I can announce that the United States has worked with 30 other countries to release 60 Million barrels of oil from reserves around the world.\",\"\",\"America will lead that effort, releasing 30 Million barrels from our own Strategic Petroleum Reserve.And we stand ready to do more if necessary, unified with our allies.\",\"\",\"These steps will help blunt gas prices here at home.And I know the news about what\u2019s happening can seem alarming.\",\"\",\"But I want you to know that we are going to be okay.\",\"\",\"When the history of this era is written Putin\u2019s war on Ukraine will have left Russia weaker and the rest of the world stronger.\",\"\",\"While it shouldn\u2019t have taken something so terrible for people around the world to see what\u2019s at stake now everyone sees it clearly.\",\"\",\"We see the unity among leaders of nations and a more unified Europe a more unified West.And we see unity among the people who are gathering in cities in large crowds around the world even in Russia to demonstrate their support for Ukraine.\",\"\",\"In the battle between democracy and autocracy, democracies are rising to the moment, and the world is clearly choosing the side of peace and security.\",\"\",\"This is a real test.It\u2019s going to take time.So let us continue to draw inspiration from the iron will of the Ukrainian people.\",\"\",\"To our fellow Ukrainian Americans who forge a deep bond that connects our two nations we stand with you.\",\"\",\"Putin may circle Kyiv with tanks, but he will never gain the hearts and souls of the Ukrainian people.\",\"\",\"He will never extinguish their love of freedom.He will never weaken the resolve of the free world.\",\"\",\"We meet tonight in an America that has lived through two of the hardest years this nation has ever faced.\",\"\",\"The pandemic has been punishing.\",\"\",\"And so many families are living paycheck to paycheck, struggling to keep up with the rising cost of food, gas, housing, and so much more.\",\"\",\"I understand.\",\"\",\"I remember when my Dad had to leave our home in Scranton, Pennsylvania to find work.", "start_char_idx": null, "end_char_idx": null, "text_template": "{metadata_str}\n\n{content}", "metadata_template": "{key}: {value}", "metadata_seperator": "\n"}, "__type__": "1"}, "7abfcf66-fe5c-4c29-8377-1661dc23bac8": {"__data__": {"id_": "7abfcf66-fe5c-4c29-8377-1661dc23bac8", "embedding": null, "metadata": {}, "excluded_embed_metadata_keys": [], "excluded_llm_metadata_keys": [], "relationships": {"1": {"node_id": "073fd534-219b-4176-8d30-5cb9f8a2b7da", "node_type": null, "metadata": {}, "hash": "165fc075a6907fa3f93245a123a31f2a1d42d9b188c83425aa019005e0570c8c"}, "2": {"node_id": "9c81ecd3-9c00-4fce-b5f7-bdfbcaacc119", "node_type": null, "metadata": {}, "hash": "a669d38458963080f56de2bc8969a10d58aad9afdb10c0e070d91f162d7610c1"}, "3": {"node_id": "b57084f5-5c54-48d4-83d8-81e93dead105", "node_type": null, "metadata": {}, "hash": "e6d6642aaeb58e42c8358eb0dd020a1de421392a4f901241e2a1cef40b117f93"}}, "hash": "3c4611a44700b0ff9960fc740aaa9c30d493bed70b8b2dfc30bf9cde6b09477e", "text": "I grew up in a family where if the price of food went up, you felt it.\",\"\",\"That\u2019s why one of the first things I did as President was fight to pass the American Rescue Plan.\",\"\",\"Because people were hurting.We needed to act, and we did.\",\"\",\"Few pieces of legislation have done more in a critical moment in our history to lift us out of crisis.\",\"\",\"It fueled our efforts to vaccinate the nation and combat COVID-19.It delivered immediate economic relief for tens of millions of Americans.\",\"\",\"Helped put food on their table, keep a roof over their heads, and cut the cost of health insurance.\",\"\",\"And as my Dad used to say, it gave people a little breathing room.\",\"\",\"And unlike the $2 Trillion tax cut passed in the previous administration that benefitted the top 1% of Americans, the American Rescue Plan helped working people\u2014and left no one behind.\",\"\",\"And it worked.It created jobs.Lots of jobs.\",\"\",\"In fact\u2014our economy created over 6.5 Million new jobs just last year, more jobs created in one year  \",\"than ever before in the history of America.\",\"\",\"Our economy grew at a rate of 5.7% last year, the strongest growth in nearly 40 years, the first step in bringing fundamental change to an economy that hasn\u2019t worked for the working people of this nation for too long.\",\"\",\"For the past 40 years we were told that if we gave tax breaks to those at the very top, the benefits would trickle down to everyone else.\",\"\",\"But that trickle-down theory led to weaker economic growth, lower wages, bigger deficits, and the widest gap between those at the top and everyone else in nearly a century.\",\"\",\"Vice President Harris and I ran for office with a new economic vision for America.\",\"\",\"Invest in America.Educate Americans.Grow the workforce.Build the economy from the bottom up  \",\"and the middle out, not from the top down.\",\"\",\"Because we know that when the middle class grows, the poor have a ladder up and the wealthy do very well.\",\"\",\"America used to have the best roads, bridges, and airports on Earth.\",\"\",\"Now our infrastructure is ranked 13th in the world.\",\"\",\"We won\u2019t be able to compete for the jobs of the 21st Century if we don\u2019t fix that.\",\"\",\"That\u2019s why it was so important to pass the Bipartisan Infrastructure Law\u2014the most sweeping investment to rebuild America in history.\",\"\",\"This was a bipartisan effort, and I want to thank the members of both parties who worked to make it happen.\",\"\",\"We\u2019re done talking about infrastructure weeks.\",\"\",\"We\u2019re going to have an infrastructure decade.\",\"\",\"It is going to transform America and put us on a path to win the economic competition of the 21st Century that we face with the rest of the world\u2014particularly with China.\",\"\",\"As I\u2019ve told Xi Jinping, it is never a good bet to bet against the American people.\",\"\",\"We\u2019ll create good jobs for millions of Americans, modernizing roads, airports, ports, and waterways all across America.\",\"\",\"And we\u2019ll do it all to withstand the devastating effects of the climate crisis and promote environmental justice.\",\"\",\"We\u2019ll build a national network of 500,000 electric vehicle charging stations, begin to replace poisonous lead pipes\u2014so every child\u2014and every American\u2014has clean water to drink at home and at school, provide affordable high-speed internet for every American\u2014urban, suburban, rural, and tribal communities.\",\"\",\"4,000 projects have already been announced.\",\"\",\"And tonight, I\u2019m announcing that this year we will start fixing over 65,000 miles of highway and 1,500 bridges in disrepair.\",\"\",\"When we use taxpayer dollars to rebuild America \u2013 we are going to Buy American: buy American products to support American jobs.\",\"\",\"The federal government spends about $600 Billion a year to keep the country safe and secure.\",\"\",\"There\u2019s been a law on the books for almost a century \",\"to make sure taxpayers\u2019 dollars support American jobs and businesses.\",\"\",\"Every Administration says they\u2019ll do it, but we are actually doing it.\",\"\",\"We will buy American to make sure everything from the deck of an aircraft carrier to the steel on highway guardrails are made in America.\",\"\",\"But to compete for the best jobs of the future, we also need to level the playing field with China and other competitors.\",\"\",\"That\u2019s why it is so important to pass the Bipartisan Innovation Act sitting in Congress that will make record investments in emerging technologies and American manufacturing.\",\"\",\"Let me give you one example of why it\u2019s so important to pass it.", "start_char_idx": null, "end_char_idx": null, "text_template": "{metadata_str}\n\n{content}", "metadata_template": "{key}: {value}", "metadata_seperator": "\n"}, "__type__": "1"}, "b57084f5-5c54-48d4-83d8-81e93dead105": {"__data__": {"id_": "b57084f5-5c54-48d4-83d8-81e93dead105", "embedding": null, "metadata": {}, "excluded_embed_metadata_keys": [], "excluded_llm_metadata_keys": [], "relationships": {"1": {"node_id": "073fd534-219b-4176-8d30-5cb9f8a2b7da", "node_type": null, "metadata": {}, "hash": "165fc075a6907fa3f93245a123a31f2a1d42d9b188c83425aa019005e0570c8c"}, "2": {"node_id": "7abfcf66-fe5c-4c29-8377-1661dc23bac8", "node_type": null, "metadata": {}, "hash": "3c4611a44700b0ff9960fc740aaa9c30d493bed70b8b2dfc30bf9cde6b09477e"}, "3": {"node_id": "4f8e6f1c-734f-4974-8efa-7a79191f15ae", "node_type": null, "metadata": {}, "hash": "4da418705b289bb731c1c930e28e9fe5e303b4aedb2f7e72fd910829bf1cc866"}}, "hash": "e6d6642aaeb58e42c8358eb0dd020a1de421392a4f901241e2a1cef40b117f93", "text": "\",\"\",\"If you travel 20 miles east of Columbus, Ohio, you\u2019ll find 1,000 empty acres of land.\",\"\",\"It won\u2019t look like much, but if you stop and look closely, you\u2019ll see a \u201cField of dreams,\u201d the ground on which America\u2019s future will be built.\",\"\",\"This is where Intel, the American company that helped build Silicon Valley, is going to build its $20 billion semiconductor \u201cmega site\u201d.\",\"\",\"Up to eight state-of-the-art factories in one place.10,000 new good-paying jobs.\",\"\",\"Some of the most sophisticated manufacturing in the world to make computer chips the size of a fingertip that power the world and our everyday lives.\",\"\",\"Smartphones.The Internet.Technology we have yet to invent.\",\"\",\"But that\u2019s just the beginning.\",\"\",\"Intel\u2019s CEO, Pat Gelsinger, who is here tonight, told me they are ready to increase their investment from  \",\"$20 billion to $100 billion.\",\"\",\"That would be one of the biggest investments in manufacturing in American history.\",\"\",\"And all they\u2019re waiting for is for you to pass this bill.\",\"\",\"So let\u2019s not wait any longer.Send it to my desk.I\u2019ll sign it.\",\"\",\"And we will really take off.\",\"\",\"And Intel is not alone.\",\"\",\"There\u2019s something happening in America.\",\"\",\"Just look around and you\u2019ll see an amazing story.\",\"\",\"The rebirth of the pride that comes from stamping products \u201cMade In America.\u201d The revitalization of American manufacturing.\",\"\",\"Companies are choosing to build new factories here, when just a few years ago, they would have built them overseas.\",\"\",\"That\u2019s what is happening.Ford is investing $11 billion to build electric vehicles, creating 11,000 jobs across the country.\",\"\",\"GM is making the largest investment in its history\u2014$7 billion to build electric vehicles, creating 4,000 jobs in Michigan.\",\"\",\"All told, we created 369,000 new manufacturing jobs in America just last year.\",\"\",\"Powered by people I\u2019ve met like JoJo Burgess, from generations of union steelworkers from Pittsburgh, who\u2019s here with us tonight.\",\"\",\"As Ohio Senator Sherrod Brown says, \u201cIt\u2019s time to bury the label \u201cRust Belt.\u201d \",\"\",\"It\u2019s time.\",\"\",\"But with all the bright spots in our economy, record job growth and higher wages, too many families are struggling to keep up with the bills.\",\"\",\"Inflation is robbing them of the gains they might otherwise feel.\",\"\",\"I get it.That\u2019s why my top priority is getting prices under control.\",\"\",\"Look, our economy roared back faster than most predicted, but the pandemic meant that businesses had a hard time hiring enough workers to keep up production in their factories.\",\"\",\"The pandemic also disrupted global supply chains.\",\"\",\"When factories close, it takes longer to make goods and get them from the warehouse to the store, and prices go up.\",\"\",\"Look at cars.\",\"\",\"Last year, there weren\u2019t enough semiconductors to make all the cars that people wanted to buy.\",\"\",\"And guess what, prices of automobiles went up.\",\"\",\"So\u2014we have a choice.\",\"\",\"One way to fight inflation is to drive down wages and make Americans poorer.\",\"\",\"I have a better plan to fight inflation.\",\"\",\"Lower your costs, not your wages.\",\"\",\"Make more cars and semiconductors in America.\",\"\",\"More infrastructure and innovation in America.\",\"\",\"More goods moving faster and cheaper in America.\",\"\",\"More jobs where you can earn a good living in America.\",\"\",\"And instead of relying on foreign supply chains, let\u2019s make it in America.\",\"\",\"Economists call it \u201cincreasing the productive capacity of our economy.\u201d \",\"\",\"I call it building a better America.\",\"\",\"My plan to fight inflation will lower your costs and lower the deficit.\",\"\",\"17 Nobel laureates in economics say my plan will ease long-term inflationary pressures.Top business leaders and most Americans support my plan.And here\u2019s the plan: \",\"\",\"First \u2013 cut the cost of prescription drugs.Just look at insulin.One in ten Americans has diabetes.In Virginia, I met a 13-year-old boy named Joshua Davis.\",\"\",\"He and his Dad both have Type 1 diabetes, which means they need insulin every day.Insulin costs about $10 a vial to make.\",\"\",\"But drug companies charge families like Joshua and his Dad up to 30 times more.I spoke with Joshua\u2019s mom.", "start_char_idx": null, "end_char_idx": null, "text_template": "{metadata_str}\n\n{content}", "metadata_template": "{key}: {value}", "metadata_seperator": "\n"}, "__type__": "1"}, "4f8e6f1c-734f-4974-8efa-7a79191f15ae": {"__data__": {"id_": "4f8e6f1c-734f-4974-8efa-7a79191f15ae", "embedding": null, "metadata": {}, "excluded_embed_metadata_keys": [], "excluded_llm_metadata_keys": [], "relationships": {"1": {"node_id": "073fd534-219b-4176-8d30-5cb9f8a2b7da", "node_type": null, "metadata": {}, "hash": "165fc075a6907fa3f93245a123a31f2a1d42d9b188c83425aa019005e0570c8c"}, "2": {"node_id": "b57084f5-5c54-48d4-83d8-81e93dead105", "node_type": null, "metadata": {}, "hash": "e6d6642aaeb58e42c8358eb0dd020a1de421392a4f901241e2a1cef40b117f93"}, "3": {"node_id": "06dea7be-7678-4705-aee4-28f9e8fd00ad", "node_type": null, "metadata": {}, "hash": "06f8e583b01366fb765d32573f2ab54df65b1131ad330425e41b3b26427b86c0"}}, "hash": "4da418705b289bb731c1c930e28e9fe5e303b4aedb2f7e72fd910829bf1cc866", "text": "\",\"\",\"Imagine what it\u2019s like to look at your child who needs insulin and have no idea how you\u2019re going to pay for it.\",\"\",\"What it does to your dignity, your ability to look your child in the eye, to be the parent you expect to be.\",\"\",\"Joshua is here with us tonight.Yesterday was his birthday.Happy birthday, buddy.\",\"\",\"For Joshua, and for the 200,000 other young people with Type 1 diabetes, let\u2019s cap the cost of insulin at $35 a month so everyone can afford it.\",\"\",\"Drug companies will still do very well.And while we\u2019re at it let Medicare negotiate lower prices for prescription drugs, like the VA already does.\",\"\",\"Look, the American Rescue Plan is helping millions of families on Affordable Care Act plans save $2,400 a year on their health care premiums.Let\u2019s close the coverage gap and make those savings permanent.\",\"\",\"Second \u2013 cut energy costs for families an average of $500 a year by combatting climate change.\",\"\",\"Let\u2019s provide investments and tax credits to weatherize your homes and businesses to be energy efficient and you get a tax credit; double America\u2019s clean energy production in solar, wind, and so much more;  lower the price of electric vehicles, saving you another $80 a month because you\u2019ll never have to pay at the gas pump again.\",\"\",\"Third \u2013 cut the cost of child care.Many families pay up to $14,000 a year for child care per child.\",\"\",\"Middle-class and working families shouldn\u2019t have to pay more than 7% of their income for care of young children.\",\"\",\"My plan will cut the cost in half for most families and help parents, including millions of women, who left the workforce during the pandemic because they couldn\u2019t afford child care, to be able to get back to work.\",\"\",\"My plan doesn\u2019t stop there.It also includes home and long-term care.More affordable housing.And Pre-K for every 3- and 4-year-old.\",\"\",\"All of these will lower costs.\",\"\",\"And under my plan, nobody earning less than $400,000 a year will pay an additional penny in new taxes.Nobody.\",\"\",\"The one thing all Americans agree on is that the tax system is not fair.We have to fix it.\",\"\",\"I\u2019m not looking to punish anyone.But let\u2019s make sure corporations and the wealthiest Americans start paying their fair share.\",\"\",\"Just last year, 55 Fortune 500 corporations earned $40 billion in profits and paid zero dollars in federal income tax.\",\"\",\"That\u2019s simply not fair.That\u2019s why I\u2019ve proposed a 15% minimum tax rate for corporations.\",\"\",\"We got more than 130 countries to agree on a global minimum tax rate so companies can\u2019t get out of paying their taxes at home by shipping jobs and factories overseas.\",\"\",\"That\u2019s why I\u2019ve proposed closing loopholes so the very wealthy don\u2019t pay a lower tax rate than a teacher or a firefighter.\",\"\",\"So that\u2019s my plan.It will grow the economy and lower costs for families.\",\"\",\"So what are we waiting for?Let\u2019s get this done.And while you\u2019re at it, confirm my nominees to the Federal Reserve, which plays a critical role in fighting inflation.\",\"\",\"My plan will not only lower costs to give families a fair shot, it will lower the deficit.\",\"\",\"The previous Administration not only ballooned the deficit with tax cuts for the very wealthy and corporations, it undermined the watchdogs whose job was to keep pandemic relief funds from being wasted.\",\"\",\"But in my administration, the watchdogs have been welcomed back.\",\"\",\"We\u2019re going after the criminals who stole billions in relief money meant for small businesses and millions of Americans.\",\"\",\"And tonight, I\u2019m announcing that the Justice Department will name a chief prosecutor for pandemic fraud.\",\"\",\"By the end of this year, the deficit will be down to less than half what it was before I took office.\",\"\",\"The only president ever to cut the deficit by more than one trillion dollars in a single year.\",\"\",\"Lowering your costs also means demanding more competition.\",\"\",\"I\u2019m a capitalist, but capitalism without competition isn\u2019t capitalism.\",\"\",\"It\u2019s exploitation\u2014and it drives up prices.\",\"\",\"When corporations don\u2019t have to compete, their profits go up, your prices go up, and small businesses and family farmers and ranchers go under.\",\"\",\"We see it happening with ocean carriers moving goods in and out of America.\",\"\",\"During the pandemic, these foreign-owned companies raised prices by as much as 1,000% and made record profits.", "start_char_idx": null, "end_char_idx": null, "text_template": "{metadata_str}\n\n{content}", "metadata_template": "{key}: {value}", "metadata_seperator": "\n"}, "__type__": "1"}, "06dea7be-7678-4705-aee4-28f9e8fd00ad": {"__data__": {"id_": "06dea7be-7678-4705-aee4-28f9e8fd00ad", "embedding": null, "metadata": {}, "excluded_embed_metadata_keys": [], "excluded_llm_metadata_keys": [], "relationships": {"1": {"node_id": "073fd534-219b-4176-8d30-5cb9f8a2b7da", "node_type": null, "metadata": {}, "hash": "165fc075a6907fa3f93245a123a31f2a1d42d9b188c83425aa019005e0570c8c"}, "2": {"node_id": "4f8e6f1c-734f-4974-8efa-7a79191f15ae", "node_type": null, "metadata": {}, "hash": "4da418705b289bb731c1c930e28e9fe5e303b4aedb2f7e72fd910829bf1cc866"}, "3": {"node_id": "0b2d9c65-f09d-423a-ae0a-3f2856754433", "node_type": null, "metadata": {}, "hash": "9e632e3f5539095bc8a4bfdb2c00d5f92eaca09209152e5459a65824e85dc811"}}, "hash": "06f8e583b01366fb765d32573f2ab54df65b1131ad330425e41b3b26427b86c0", "text": "\",\"\",\"Tonight, I\u2019m announcing a crackdown on these companies overcharging American businesses and consumers.\",\"\",\"And as Wall Street firms take over more nursing homes, quality in those homes has gone down and costs have gone up.\",\"\",\"That ends on my watch.\",\"\",\"Medicare is going to set higher standards for nursing homes and make sure your loved ones get the care they deserve and expect.\",\"\",\"We\u2019ll also cut costs and keep the economy going strong by giving workers a fair shot, provide more training and apprenticeships, hire them based on their skills not degrees.\",\"\",\"Let\u2019s pass the Paycheck Fairness Act and paid leave.\",\"\",\"Raise the minimum wage to $15 an hour and extend the Child Tax Credit, so no one has to raise a family in poverty.\",\"\",\"Let\u2019s increase Pell Grants and increase our historic support of HBCUs, and invest in what Jill\u2014our First Lady who teaches full-time\u2014calls America\u2019s best-kept secret: community colleges.\",\"\",\"And let\u2019s pass the PRO Act when a majority of workers want to form a union\u2014they shouldn\u2019t be stopped.\",\"\",\"When we invest in our workers, when we build the economy from the bottom up and the middle out together, we can do something we haven\u2019t done in a long time: build a better America.\",\"\",\"For more than two years, COVID-19 has impacted every decision in our lives and the life of the nation.\",\"\",\"And I know you\u2019re tired, frustrated, and exhausted.\",\"\",\"But I also know this.\",\"\",\"Because of the progress we\u2019ve made, because of your resilience and the tools we have, tonight I can say  \",\"we are moving forward safely, back to more normal routines.\",\"\",\"We\u2019ve reached a new moment in the fight against COVID-19, with severe cases down to a level not seen since last July.\",\"\",\"Just a few days ago, the Centers for Disease Control and Prevention\u2014the CDC\u2014issued new mask guidelines.\",\"\",\"Under these new guidelines, most Americans in most of the country can now be mask free.\",\"\",\"And based on the projections, more of the country will reach that point across the next couple of weeks.\",\"\",\"Thanks to the progress we have made this past year, COVID-19 need no longer control our lives.\",\"\",\"I know some are talking about \u201cliving with COVID-19\u201d.Tonight \u2013 I say that we will never just accept living with COVID-19.\",\"\",\"We will continue to combat the virus as we do other diseases.And because this is a virus that mutates and spreads, we will stay on guard.\",\"\",\"Here are four common sense steps as we move forward safely.\",\"\",\"First, stay protected with vaccines and treatments.We know how incredibly effective vaccines are.If you\u2019re vaccinated and boosted you have the highest degree of protection.\",\"\",\"We will never give up on vaccinating more Americans.Now, I know parents with kids under 5 are eager to see a vaccine authorized for their children.\",\"\",\"The scientists are working hard to get that done and we\u2019ll be ready with plenty of vaccines when they do.\",\"\",\"We\u2019re also ready with anti-viral treatments.If you get COVID-19, the Pfizer pill reduces your chances of ending up in the hospital by 90%.\",\"\",\"We\u2019ve ordered more of these pills than anyone in the world.And Pfizer is working overtime to get us 1 Million pills this month and more than double that next month.\",\"\",\"And we\u2019re launching the \u201cTest to Treat\u201d initiative so people can get tested at a pharmacy, and if they\u2019re positive, receive antiviral pills on the spot at no cost.\",\"\",\"If you\u2019re immunocompromised or have some other vulnerability, we have treatments and free high-quality masks.\",\"\",\"We\u2019re leaving no one behind or ignoring anyone\u2019s needs as we move forward.\",\"\",\"And on testing, we have made hundreds of millions of tests available for you to order for free.\",\"\",\"Even if you already ordered free tests tonight, I am announcing that you can order more from covidtests.gov starting next week.\",\"\",\"Second \u2013 we must prepare for new variants.Over the past year, we\u2019ve gotten much better at detecting new variants.\",\"\",\"If necessary, we\u2019ll be able to deploy new vaccines within 100 days instead of many more months or years.\",\"\",\"And, if Congress provides the funds we need, we\u2019ll have new stockpiles of tests, masks, and pills ready if needed.\",\"\",\"I cannot promise a new variant won\u2019t come.But I can promise you we\u2019ll do everything within our power to be ready if it does.", "start_char_idx": null, "end_char_idx": null, "text_template": "{metadata_str}\n\n{content}", "metadata_template": "{key}: {value}", "metadata_seperator": "\n"}, "__type__": "1"}, "0b2d9c65-f09d-423a-ae0a-3f2856754433": {"__data__": {"id_": "0b2d9c65-f09d-423a-ae0a-3f2856754433", "embedding": null, "metadata": {}, "excluded_embed_metadata_keys": [], "excluded_llm_metadata_keys": [], "relationships": {"1": {"node_id": "073fd534-219b-4176-8d30-5cb9f8a2b7da", "node_type": null, "metadata": {}, "hash": "165fc075a6907fa3f93245a123a31f2a1d42d9b188c83425aa019005e0570c8c"}, "2": {"node_id": "06dea7be-7678-4705-aee4-28f9e8fd00ad", "node_type": null, "metadata": {}, "hash": "06f8e583b01366fb765d32573f2ab54df65b1131ad330425e41b3b26427b86c0"}, "3": {"node_id": "54f7120b-247a-4f3f-9d57-20f0c839446e", "node_type": null, "metadata": {}, "hash": "c34da4a4a99824b76e4b473247c800c37cffef7b4d3f9b62dca2452582c08719"}}, "hash": "9e632e3f5539095bc8a4bfdb2c00d5f92eaca09209152e5459a65824e85dc811", "text": "\",\"\",\"Third \u2013 we can end the shutdown of schools and businesses.We have the tools we need.\",\"\",\"It\u2019s time for Americans to get back to work and fill our great downtowns again.People working from home can feel safe to begin to return to the office.\",\"\",\"We\u2019re doing that here in the federal government.The vast majority of federal workers will once again work in person.\",\"\",\"Our schools are open.Let\u2019s keep it that way.Our kids need to be in school.\",\"\",\"And with 75% of adult Americans fully vaccinated and hospitalizations down by 77%, most Americans can remove their masks, return to work, stay in the classroom, and move forward safely.\",\"\",\"We achieved this because we provided free vaccines, treatments, tests, and masks.\",\"\",\"Of course, continuing this costs money.\",\"\",\"I will soon send Congress a request.\",\"\",\"The vast majority of Americans have used these tools and may want to again, so I expect Congress to pass it quickly.\",\"\",\"Fourth, we will continue vaccinating the world.\",\"\",\"We\u2019ve sent 475 Million vaccine doses to 112 countries, more than any other nation.\",\"\",\"And we won\u2019t stop.\",\"\",\"We have lost so much to COVID-19.Time with one another.And worst of all, so much loss of life.\",\"\",\"Let\u2019s use this moment to reset.Let\u2019s stop looking at COVID-19 as a partisan dividing line and see it for what it is: A God-awful disease.\",\"\",\"Let\u2019s stop seeing each other as enemies, and start seeing each other for who we really are: Fellow Americans.\",\"\",\"We can\u2019t change how divided we\u2019ve been.But we can change how we move forward\u2014on COVID-19 and other issues we must face together.\",\"\",\"I recently visited the New York City Police Department days after the funerals of Officer Wilbert Mora and his partner, Officer Jason Rivera.\",\"\",\"They were responding to a 9-1-1 call when a man shot and killed them with a stolen gun.\",\"\",\"Officer Mora was 27 years old.\",\"\",\"Officer Rivera was 22.\",\"\",\"Both Dominican Americans who\u2019d grown up on the same streets they later chose to patrol as police officers.\",\"\",\"I spoke with their families and told them that we are forever in debt for their sacrifice, and we will carry on their mission to restore the trust and safety every community deserves.\",\"\",\"I\u2019ve worked on these issues a long time.\",\"\",\"I know what works: Investing in crime preventionand community police officers who\u2019ll walk the beat, who\u2019ll know the neighborhood, and who can restore trust and safety.\",\"\",\"So let\u2019s not abandon our streets.Or choose between safety and equal justice.\",\"\",\"Let\u2019s come together to protect our communities, restore trust, and hold law enforcement accountable.\",\"\",\"That\u2019s why the Justice Department required body cameras, banned chokeholds, and restricted no-knock warrants for its officers.\",\"\",\"That\u2019s why the American Rescue Plan provided $350 Billion that cities, states, and counties can use to hire more police and invest in proven strategies like community violence interruption\u2014trusted messengers breaking the cycle of violence and trauma and giving young people hope.\",\"\",\"We should all agree: The answer is not to Defund the police.The answer is to FUND the police with the resources and training they need to protect our communities.\",\"\",\"I ask Democrats and Republicans alike: Pass my budget and keep our neighborhoods safe.\",\"\",\"And I will keep doing everything in my power to crack down on gun trafficking and ghost guns you can buy online and make at home\u2014they have no serial numbers and can\u2019t be traced.\",\"\",\"And I ask Congress to pass proven measures to reduce gun violence.Pass universal background checks.Why should anyone on a terrorist list be able to purchase a weapon?\",\"\",\"Ban assault weapons and high-capacity magazines.\",\"\",\"Repeal the liability shield that makes gun manufacturers the only industry in America that can\u2019t be sued.\",\"\",\"These laws don\u2019t infringe on the Second Amendment.They save lives.\",\"\",\"The most fundamental right in America is the right to vote \u2013 and to have it counted.And it\u2019s under assault.\",\"\",\"In state after state, new laws have been passed, not only to suppress the vote, but to subvert entire elections.\",\"\",\"We cannot let this happen.\",\"\",\"Tonight.I call on the Senate to: Pass the Freedom to Vote Act.Pass the John Lewis Voting Rights Act.And while you\u2019re at it, pass the Disclose Act so Americans can know who is funding our elections.", "start_char_idx": null, "end_char_idx": null, "text_template": "{metadata_str}\n\n{content}", "metadata_template": "{key}: {value}", "metadata_seperator": "\n"}, "__type__": "1"}, "54f7120b-247a-4f3f-9d57-20f0c839446e": {"__data__": {"id_": "54f7120b-247a-4f3f-9d57-20f0c839446e", "embedding": null, "metadata": {}, "excluded_embed_metadata_keys": [], "excluded_llm_metadata_keys": [], "relationships": {"1": {"node_id": "073fd534-219b-4176-8d30-5cb9f8a2b7da", "node_type": null, "metadata": {}, "hash": "165fc075a6907fa3f93245a123a31f2a1d42d9b188c83425aa019005e0570c8c"}, "2": {"node_id": "0b2d9c65-f09d-423a-ae0a-3f2856754433", "node_type": null, "metadata": {}, "hash": "9e632e3f5539095bc8a4bfdb2c00d5f92eaca09209152e5459a65824e85dc811"}, "3": {"node_id": "62f6aedc-eb3c-4062-9cb1-6c8e5b3fbd88", "node_type": null, "metadata": {}, "hash": "ef20c02a60a952bded823a6bd086a98ed854235200437c9a91d2b5b1eb56ca86"}}, "hash": "c34da4a4a99824b76e4b473247c800c37cffef7b4d3f9b62dca2452582c08719", "text": "\",\"\",\"Tonight, I\u2019d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer\u2014an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court.Justice Breyer, thank you for your service.\",\"\",\"One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court.\",\"\",\"And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson.One of our nation\u2019s top legal minds, who will continue Justice Breyer\u2019s legacy of excellence.\",\"\",\"A former top litigator in private practice.A former federal public defender.And from a family of public school educators and police officers.A consensus builder.Since she\u2019s been nominated, she\u2019s received a broad range of support\u2014from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\",\"\",\"And if we are to advance liberty and justice, we need to secure the Border and fix the immigration system.\",\"\",\"We can do both.At our border, we\u2019ve installed new technology like cutting-edge scanners to better detect drug smuggling.\",\"\",\"We\u2019ve set up joint patrols with Mexico and Guatemala to catch more human traffickers.\",\"\",\"We\u2019re putting in place dedicated immigration judges so families fleeing persecution and violence can have their cases heard faster.\",\"\",\"We\u2019re securing commitments and supporting partners in South and Central America to host more refugees and secure their own borders.\",\"\",\"We can do all this while keeping lit the torch of liberty that has led generations of immigrants to this land\u2014my forefathers and so many of yours.\",\"\",\"Provide a pathway to citizenship for Dreamers, those on temporary status, farm workers, and essential workers.\",\"\",\"Revise our laws so businesses have the workers they need and families don\u2019t wait decades to reunite.\",\"\",\"It\u2019s not only the right thing to do\u2014it\u2019s the economically smart thing to do.\",\"\",\"That\u2019s why immigration reform is supported by everyone from labor unions to religious leaders to the U.S. Chamber of Commerce.\",\"\",\"Let\u2019s get it done once and for all.\",\"\",\"Advancing liberty and justice also requires protecting the rights of women.\",\"\",\"The constitutional right affirmed in Roe v. Wade\u2014standing precedent for half a century\u2014is under attack as never before.\",\"\",\"If we want to go forward\u2014not backward\u2014we must protect access to health care.Preserve a woman\u2019s right to choose.And let\u2019s continue to advance maternal health care in America.\",\"\",\"And for our LGBTQ+ Americans, let\u2019s finally get the bipartisan Equality Act to my desk.The onslaught of state laws targeting transgender Americans and their families is wrong.\",\"\",\"As I said last year, especially to our younger transgender Americans, I will always have your back as your President, so you can be yourself and reach your God-given potential.\",\"\",\"While it often appears that we never agree, that isn\u2019t true.I signed 80 bipartisan bills into law last year.From preventing government shutdowns to protecting Asian-Americans from still-too-common hate crimes to reforming military justice.\",\"\",\"And soon, we\u2019ll strengthen the Violence Against Women Act that I first wrote three decades ago.It is important for us to show the nation that we can come together and do big things.\",\"\",\"So tonight I\u2019m offering a Unity Agenda for the Nation.Four big things we can do together.\",\"\",\"First, beat the opioid epidemic.\",\"\",\"There is so much we can do.Increase funding for prevention, treatment, harm reduction, and recovery.\",\"\",\"Get rid of outdated rules that stop doctors from prescribing treatments.And stop the flow of illicit drugs by working with state and local law enforcement to go after traffickers.\",\"\",\"If you\u2019re suffering from addiction, know you are not alone.I believe in recovery, and I celebrate the 23 million Americans in recovery.\",\"\",\"Second, let\u2019s take on mental health.Especially among our children, whose lives and education have been turned upside down.\",\"\",\"The American Rescue Plan gave schools money to hire teachers and help students make up for lost learning.\",\"\",\"I urge every parent to make sure your school does just that.And we can all play a part\u2014sign up to be a tutor or a mentor.\",\"\",\"Children were also struggling before the pandemic.Bullying, violence, trauma, and the harms of social media.\",\"\",\"As Frances Haugen, who is here with us tonight, has shown, we must hold social media platforms accountable for the national experiment they\u2019re conducting on our children for profit.\",\"\",\"It\u2019s time to strengthen privacy protections, ban targeted advertising to children, demand tech companies stop collecting personal data on our children.", "start_char_idx": null, "end_char_idx": null, "text_template": "{metadata_str}\n\n{content}", "metadata_template": "{key}: {value}", "metadata_seperator": "\n"}, "__type__": "1"}, "62f6aedc-eb3c-4062-9cb1-6c8e5b3fbd88": {"__data__": {"id_": "62f6aedc-eb3c-4062-9cb1-6c8e5b3fbd88", "embedding": null, "metadata": {}, "excluded_embed_metadata_keys": [], "excluded_llm_metadata_keys": [], "relationships": {"1": {"node_id": "073fd534-219b-4176-8d30-5cb9f8a2b7da", "node_type": null, "metadata": {}, "hash": "165fc075a6907fa3f93245a123a31f2a1d42d9b188c83425aa019005e0570c8c"}, "2": {"node_id": "54f7120b-247a-4f3f-9d57-20f0c839446e", "node_type": null, "metadata": {}, "hash": "c34da4a4a99824b76e4b473247c800c37cffef7b4d3f9b62dca2452582c08719"}, "3": {"node_id": "4ba80387-aa10-40df-8d13-7117665b33d0", "node_type": null, "metadata": {}, "hash": "8dba5d0cf9810f57dac268c87e1fe5c9662add855b8a7bac8575b96a0bf24851"}}, "hash": "ef20c02a60a952bded823a6bd086a98ed854235200437c9a91d2b5b1eb56ca86", "text": "\",\"\",\"And let\u2019s get all Americans the mental health services they need.More people they can turn to for help, and full parity between physical and mental health care.\",\"\",\"Third, support our veterans.\",\"\",\"Veterans are the best of us.\",\"\",\"I\u2019ve always believed that we have a sacred obligation to equip all those we send to war and care for them and their families when they come home.\",\"\",\"My administration is providing assistance with job training and housing, and now helping lower-income veterans get VA care debt-free.\",\"\",\"Our troops in Iraq and Afghanistan faced many dangers.\",\"\",\"One was stationed at bases and breathing in toxic smoke from \u201cburn pits\u201d that incinerated wastes of war\u2014medical and hazard material, jet fuel, and more.\",\"\",\"When they came home, many of the world\u2019s fittest and best trained warriors were never the same.\",\"\",\"Headaches.Numbness.Dizziness.\",\"\",\"A cancer that would put them in a flag-draped coffin.\",\"\",\"I know.\",\"\",\"One of those soldiers was my son Major Beau Biden.\",\"\",\"We don\u2019t know for sure if a burn pit was the cause of his brain cancer, or the diseases of so many of our troops.\",\"\",\"But I\u2019m committed to finding out everything we can.\",\"\",\"Committed to military families like Danielle Robinson from Ohio.\",\"\",\"The widow of Sergeant First Class Heath Robinson.\",\"\",\"He was born a soldier.Army National Guard.Combat medic in Kosovo and Iraq.\",\"\",\"Stationed near Baghdad, just yards from burn pits the size of football fields.\",\"\",\"Heath\u2019s widow Danielle is here with us tonight.They loved going to Ohio State football games.He loved building Legos with their daughter.\",\"\",\"But cancer from prolonged exposure to burn pits ravaged Heath\u2019s lungs and body.\",\"\",\"Danielle says Heath was a fighter to the very end.\",\"\",\"He didn\u2019t know how to stop fighting, and neither did she.\",\"\",\"Through her pain she found purpose to demand we do better.\",\"\",\"Tonight, Danielle\u2014we are.\",\"\",\"The VA is pioneering new ways of linking toxic exposures to diseases, already helping more veterans get benefits.\",\"\",\"And tonight, I\u2019m announcing we\u2019re expanding eligibility to veterans suffering from nine respiratory cancers.\",\"\",\"I\u2019m also calling on Congress: pass a law to make sure veterans devastated by toxic exposures in Iraq and Afghanistan finally get the benefits and comprehensive health care they deserve.\",\"\",\"And fourth, let\u2019s end cancer as we know it.\",\"\",\"This is personal to me and Jill, to Kamala, and to so many of you.\",\"\",\"Cancer is the #2 cause of death in America\u2013second only to heart disease.\",\"\",\"Last month, I announced our plan to supercharge  \",\"the Cancer Moonshot that President Obama asked me to lead six years ago.\",\"\",\"Our goal is to cut the cancer death rate by at least 50% over the next 25 years, turn more cancers from death sentences into treatable diseases.\",\"\",\"More support for patients and families.\",\"\",\"To get there, I call on Congress to fund ARPA-H, the Advanced Research Projects Agency for Health.\",\"\",\"It\u2019s based on DARPA\u2014the Defense Department project that led to the Internet, GPS, and so much more.\",\"\",\"ARPA-H will have a singular purpose\u2014to drive breakthroughs in cancer, Alzheimer\u2019s, diabetes, and more.\",\"\",\"A unity agenda for the nation.\",\"\",\"We can do this.\",\"\",\"My fellow Americans\u2014tonight , we have gathered in a sacred space\u2014the citadel of our democracy.\",\"\",\"In this Capitol, generation after generation, Americans have debated great questions amid great strife, and have done great things.\",\"\",\"We have fought for freedom, expanded liberty, defeated totalitarianism and terror.\",\"\",\"And built the strongest, freest, and most prosperous nation the world has ever known.\",\"\",\"Now is the hour.\",\"\",\"Our moment of responsibility.\",\"\",\"Our test of resolve and conscience, of history itself.\",\"\",\"It is in this moment that our character is formed.Our purpose is found.Our future is forged.\",\"\",\"Well I know this nation.\",\"\",\"We will meet the test.\",\"\",\"To protect freedom and liberty, to expand fairness and opportunity.\",\"\",\"We will save democracy.\",\"\",\"As hard as these times have been, I am more optimistic about America today than I have been my whole life.\",\"\",\"Because I see the future that is within our grasp.\",\"\",\"Because I know there is simply nothing beyond our capacity.\",\"\",\"We are the only nation on Earth that has always turned every crisis we have faced into an opportunity.\",\"\",\"The only nation that can be defined by a single word: possibilities.", "start_char_idx": null, "end_char_idx": null, "text_template": "{metadata_str}\n\n{content}", "metadata_template": "{key}: {value}", "metadata_seperator": "\n"}, "__type__": "1"}, "4ba80387-aa10-40df-8d13-7117665b33d0": {"__data__": {"id_": "4ba80387-aa10-40df-8d13-7117665b33d0", "embedding": null, "metadata": {}, "excluded_embed_metadata_keys": [], "excluded_llm_metadata_keys": [], "relationships": {"1": {"node_id": "073fd534-219b-4176-8d30-5cb9f8a2b7da", "node_type": null, "metadata": {}, "hash": "165fc075a6907fa3f93245a123a31f2a1d42d9b188c83425aa019005e0570c8c"}, "2": {"node_id": "62f6aedc-eb3c-4062-9cb1-6c8e5b3fbd88", "node_type": null, "metadata": {}, "hash": "ef20c02a60a952bded823a6bd086a98ed854235200437c9a91d2b5b1eb56ca86"}, "3": {"node_id": "0a2efa94-5943-467f-a8c8-0b5153290cd2", "node_type": null, "metadata": {}, "hash": "93fea5636ac054d0895648dc874527be41db91afa4d1c245af5ef0f30ef25e3a"}}, "hash": "8dba5d0cf9810f57dac268c87e1fe5c9662add855b8a7bac8575b96a0bf24851", "text": "\",\"\",\"So on this night, in our 245th year as a nation, I have come to report on the State of the Union.\",\"\",\"And my report is this: the State of the Union is strong\u2014because you, the American people, are strong.\",\"\",\"We are stronger today than we were a year ago.\",\"\",\"And we will be stronger a year from now than we are today.\",\"\",\"Now is our moment to meet and overcome the challenges of our time.\",\"\",\"And we will, as one people.\",\"\",\"One America.\",\"\",\"The United States of America.\",\"\",\"May God bless you all.May God protect our troops.\"],\"stylingDirectives\":[[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],", "start_char_idx": null, "end_char_idx": null, "text_template": "{metadata_str}\n\n{content}", "metadata_template": "{key}: {value}", "metadata_seperator": "\n"}, "__type__": "1"}, "0a2efa94-5943-467f-a8c8-0b5153290cd2": {"__data__": {"id_": "0a2efa94-5943-467f-a8c8-0b5153290cd2", "embedding": null, "metadata": {}, "excluded_embed_metadata_keys": [], "excluded_llm_metadata_keys": [], "relationships": {"1": {"node_id": "073fd534-219b-4176-8d30-5cb9f8a2b7da", "node_type": null, "metadata": {}, "hash": "165fc075a6907fa3f93245a123a31f2a1d42d9b188c83425aa019005e0570c8c"}, "2": {"node_id": "4ba80387-aa10-40df-8d13-7117665b33d0", "node_type": null, "metadata": {}, "hash": "8dba5d0cf9810f57dac268c87e1fe5c9662add855b8a7bac8575b96a0bf24851"}, "3": {"node_id": "676e6185-26cd-4ad7-bbea-75a682c0be37", "node_type": null, "metadata": {}, "hash": "195df4932fbdade1f5fe90f8e374dfdcee66b19a193f7a28a4f40bfbcce269e3"}}, "hash": "93fea5636ac054d0895648dc874527be41db91afa4d1c245af5ef0f30ef25e3a", "text": "[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[]],\"csv\":null,\"csvError\":null,\"dependabotInfo\":{\"showConfigurationBanner\":false,\"configFilePath\":null,\"networkDependabotPath\":\"/langchain-ai/langchain/network/updates\",\"dismissConfigurationNoticePath\":\"/settings/dismiss-notice/dependabot_configuration_notice\",\"configurationNoticeDismissed\":null,\"repoAlertsPath\":\"/langchain-ai/langchain/security/dependabot\",\"repoSecurityAndAnalysisPath\":\"/langchain-ai/langchain/settings/security_analysis\",\"repoOwnerIsOrg\":true,\"currentUserCanAdminRepo\":false},\"displayName\":\"state_of_the_union.txt\",\"displayUrl\":\"https://github.com/langchain-ai/langchain/blob/master/docs/extras/modules/state_of_the_union.txt?raw=true\",\"headerInfo\":{\"blobSize\":\"38.1 KB\",\"deleteInfo\":{\"deleteTooltip\":\"You must be signed in to make or propose changes\"},\"editInfo\":{\"editTooltip\":\"You must be signed in to make or propose changes\"},\"ghDesktopPath\":\"https://desktop.github.com\",\"gitLfsPath\":null,\"onBranch\":true,\"shortPath\":\"d50175d\",\"siteNavLoginPath\":\"/login?return_to=https%3A%2F%2Fgithub.com%2Flangchain-ai%2Flangchain%2Fblob%2Fmaster%2Fdocs%2Fextras%2Fmodules%2Fstate_of_the_union.txt\",\"isCSV\":false,\"isRichtext\":false,\"toc\":null,\"lineInfo\":{\"truncatedLoc\":\"723\",\"truncatedSloc\":\"365\"},\"mode\":\"file\"},", "start_char_idx": null, "end_char_idx": null, "text_template": "{metadata_str}\n\n{content}", "metadata_template": "{key}: {value}", "metadata_seperator": "\n"}, "__type__": "1"}, "676e6185-26cd-4ad7-bbea-75a682c0be37": {"__data__": {"id_": "676e6185-26cd-4ad7-bbea-75a682c0be37", "embedding": null, "metadata": {}, "excluded_embed_metadata_keys": [], "excluded_llm_metadata_keys": [], "relationships": {"1": {"node_id": "073fd534-219b-4176-8d30-5cb9f8a2b7da", "node_type": null, "metadata": {}, "hash": "165fc075a6907fa3f93245a123a31f2a1d42d9b188c83425aa019005e0570c8c"}, "2": {"node_id": "0a2efa94-5943-467f-a8c8-0b5153290cd2", "node_type": null, "metadata": {}, "hash": "93fea5636ac054d0895648dc874527be41db91afa4d1c245af5ef0f30ef25e3a"}}, "hash": "195df4932fbdade1f5fe90f8e374dfdcee66b19a193f7a28a4f40bfbcce269e3", "text": "\"image\":false,\"isCodeownersFile\":null,\"isPlain\":false,\"isValidLegacyIssueTemplate\":false,\"issueTemplateHelpUrl\":\"https://docs.github.com/articles/about-issue-and-pull-request-templates\",\"issueTemplate\":null,\"discussionTemplate\":null,\"language\":\"Text\",\"languageID\":372,\"large\":false,\"loggedIn\":false,\"newDiscussionPath\":\"/langchain-ai/langchain/discussions/new\",\"newIssuePath\":\"/langchain-ai/langchain/issues/new\",\"planSupportInfo\":{\"repoIsFork\":null,\"repoOwnedByCurrentUser\":null,\"requestFullPath\":\"/langchain-ai/langchain/blob/master/docs/extras/modules/state_of_the_union.txt\",\"showFreeOrgGatedFeatureMessage\":null,\"showPlanSupportBanner\":null,\"upgradeDataAttributes\":null,\"upgradePath\":null},\"publishBannersInfo\":{\"dismissActionNoticePath\":\"/settings/dismiss-notice/publish_action_from_dockerfile\",\"dismissStackNoticePath\":\"/settings/dismiss-notice/publish_stack_from_file\",\"releasePath\":\"/langchain-ai/langchain/releases/new?marketplace=true\",\"showPublishActionBanner\":false,\"showPublishStackBanner\":false},\"renderImageOrRaw\":false,\"richText\":null,\"renderedFileInfo\":null,\"shortPath\":null,\"tabSize\":8,\"topBannersInfo\":{\"overridingGlobalFundingFile\":false,\"globalPreferredFundingPath\":null,\"repoOwner\":\"langchain-ai\",\"repoName\":\"langchain\",\"showInvalidCitationWarning\":false,\"citationHelpUrl\":\"https://docs.github.com/en/github/creating-cloning-and-archiving-repositories/creating-a-repository-on-github/about-citation-files\",\"showDependabotConfigurationBanner\":false,\"actionsOnboardingTip\":null},\"truncated\":false,\"viewable\":true,\"workflowRedirectUrl\":null,\"symbols\":{\"timedOut\":false,\"notAnalyzed\":true,\"symbols\":[]}},\"copilotInfo\":null,\"csrf_tokens\":{\"/langchain-ai/langchain/branches\":{\"post\":\"sU-W9cZvnX-zDBtN0gBBscTDV1-DCyldrpYctmvicvS2E7Exbciqn_DrVodAf14axTioC3GjlUzdUQBCr3OKdw\"},\"/repos/preferences\":{\"post\":\"e8pZXWO2CwxvcoPxUrkNpnTBE-Go5CiKWLPGWifuJuXquUIw2y8xVYdAwCXlzKQb08bu5FIbq2cTn7p6S7w9ww\"}}},\"title\":\"langchain/docs/extras/modules/state_of_the_union.txt at master \u00b7 langchain-ai/langchain\"}", "start_char_idx": null, "end_char_idx": null, "text_template": "{metadata_str}\n\n{content}", "metadata_template": "{key}: {value}", "metadata_seperator": "\n"}, "__type__": "1"}}, "docstore/ref_doc_info": {"073fd534-219b-4176-8d30-5cb9f8a2b7da": {"node_ids": ["3400207d-0101-4f32-83d6-b6f25ec33c65", "1e461525-e8c6-46e5-9c46-30af41c20f3c", "9c81ecd3-9c00-4fce-b5f7-bdfbcaacc119", "7abfcf66-fe5c-4c29-8377-1661dc23bac8", "b57084f5-5c54-48d4-83d8-81e93dead105", "4f8e6f1c-734f-4974-8efa-7a79191f15ae", "06dea7be-7678-4705-aee4-28f9e8fd00ad", "0b2d9c65-f09d-423a-ae0a-3f2856754433", "54f7120b-247a-4f3f-9d57-20f0c839446e", "62f6aedc-eb3c-4062-9cb1-6c8e5b3fbd88", "4ba80387-aa10-40df-8d13-7117665b33d0", "0a2efa94-5943-467f-a8c8-0b5153290cd2", "676e6185-26cd-4ad7-bbea-75a682c0be37"], "metadata": {}}}}

notebooks/storage/graph_store.json

@@ -0,0 +1 @@
+{"graph_dict": {}}

notebooks/storage/index_store.json

@@ -0,0 +1 @@
+{"index_store/data": {"379aa2f5-9b36-48dd-bfb0-f568cdd3361e": {"__type__": "vector_store", "__data__": "{\"index_id\": \"379aa2f5-9b36-48dd-bfb0-f568cdd3361e\", \"summary\": null, \"nodes_dict\": {\"3400207d-0101-4f32-83d6-b6f25ec33c65\": \"3400207d-0101-4f32-83d6-b6f25ec33c65\", \"1e461525-e8c6-46e5-9c46-30af41c20f3c\": \"1e461525-e8c6-46e5-9c46-30af41c20f3c\", \"9c81ecd3-9c00-4fce-b5f7-bdfbcaacc119\": \"9c81ecd3-9c00-4fce-b5f7-bdfbcaacc119\", \"7abfcf66-fe5c-4c29-8377-1661dc23bac8\": \"7abfcf66-fe5c-4c29-8377-1661dc23bac8\", \"b57084f5-5c54-48d4-83d8-81e93dead105\": \"b57084f5-5c54-48d4-83d8-81e93dead105\", \"4f8e6f1c-734f-4974-8efa-7a79191f15ae\": \"4f8e6f1c-734f-4974-8efa-7a79191f15ae\", \"06dea7be-7678-4705-aee4-28f9e8fd00ad\": \"06dea7be-7678-4705-aee4-28f9e8fd00ad\", \"0b2d9c65-f09d-423a-ae0a-3f2856754433\": \"0b2d9c65-f09d-423a-ae0a-3f2856754433\", \"54f7120b-247a-4f3f-9d57-20f0c839446e\": \"54f7120b-247a-4f3f-9d57-20f0c839446e\", \"62f6aedc-eb3c-4062-9cb1-6c8e5b3fbd88\": \"62f6aedc-eb3c-4062-9cb1-6c8e5b3fbd88\", \"4ba80387-aa10-40df-8d13-7117665b33d0\": \"4ba80387-aa10-40df-8d13-7117665b33d0\", \"0a2efa94-5943-467f-a8c8-0b5153290cd2\": \"0a2efa94-5943-467f-a8c8-0b5153290cd2\", \"676e6185-26cd-4ad7-bbea-75a682c0be37\": \"676e6185-26cd-4ad7-bbea-75a682c0be37\"}, \"doc_id_dict\": {}, \"embeddings_dict\": {}}"}}}

notebooks/structured-retrieval-large-docs.ipynb

@@ -0,0 +1,387 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import nest_asyncio\n",
+    "nest_asyncio.apply()\n",
+    "\n",
+    "import os\n",
+    "import getpass\n",
+    "import openai\n",
+    "import logging\n",
+    "import sys\n",
+    "from llama_index import SimpleDirectoryReader, SummaryIndex, ServiceContext\n",
+    "\n",
+    "logging.basicConfig(stream=sys.stdout, level=logging.INFO)\n",
+    "logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"Enter Your OpenAI API Key:\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "logging.basicConfig(stream=sys.stdout, level=logging.INFO)\n",
+    "logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.llms import OpenAI\n",
+    "from llama_index.callbacks import LlamaDebugHandler, CallbackManager\n",
+    "\n",
+    "llm = OpenAI(\"gpt-3.5-turbo\")\n",
+    "\n",
+    "callback_manager = CallbackManager([LlamaDebugHandler()])\n",
+    "\n",
+    "service_context = ServiceContext.from_defaults(\n",
+    "    llm=llm, callback_manager=callback_manager, chunk_size=256\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Loaded 4 docs\n"
+     ]
+    }
+   ],
+   "source": [
+    "required_exts = [\".txt\"]\n",
+    "\n",
+    "reader = SimpleDirectoryReader(\n",
+    "    input_dir=\"../data\",\n",
+    "    required_exts=required_exts,\n",
+    "    recursive=True,\n",
+    "    filename_as_id=True\n",
+    ")\n",
+    "\n",
+    "docs = reader.load_data()\n",
+    "print(f\"Loaded {len(docs)} docs\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Metadata Filters + Auto-Retrieval\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index import VectorStoreIndex, SimpleDirectoryReader\n",
+    "from llama_index.vector_stores import ChromaVectorStore"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "INFO:chromadb.telemetry.posthog:Anonymized telemetry enabled. See https://docs.trychroma.com/telemetry for more information.\n",
+      "Anonymized telemetry enabled. See https://docs.trychroma.com/telemetry for more information.\n",
+      "Anonymized telemetry enabled. See https://docs.trychroma.com/telemetry for more information.\n"
+     ]
+    }
+   ],
+   "source": [
+    "import chromadb\n",
+    "from llama_index.storage.storage_context import StorageContext\n",
+    "\n",
+    "db = chromadb.PersistentClient(path=\"../chroma_db\")\n",
+    "chroma_collection = db.get_or_create_collection(\"quickstart\")\n",
+    "vector_store = ChromaVectorStore(chroma_collection=chroma_collection)\n",
+    "storage_context = StorageContext.from_defaults(vector_store=vector_store)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "**********\n",
+      "Trace: index_construction\n",
+      "    |_CBEventType.NODE_PARSING ->  0.066032 seconds\n",
+      "      |_CBEventType.CHUNKING ->  0.063786 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.335255 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.430667 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.39471 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.341174 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.333922 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.371205 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.655165 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.534313 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.513138 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.396431 seconds\n",
+      "**********\n"
+     ]
+    },
+    {
+     "ename": "TypeError",
+     "evalue": "type() takes 1 or 3 arguments",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[49], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[39mtype\u001b[39;49m(vector_index \u001b[39m=\u001b[39;49m VectorStoreIndex\u001b[39m.\u001b[39;49mfrom_documents([docs[\u001b[39m0\u001b[39;49m]], \n\u001b[1;32m      2\u001b[0m                                                 service_context\u001b[39m=\u001b[39;49mservice_context\n\u001b[1;32m      3\u001b[0m ))\n",
+      "\u001b[0;31mTypeError\u001b[0m: type() takes 1 or 3 arguments"
+     ]
+    }
+   ],
+   "source": [
+    "vector_index = VectorStoreIndex.from_documents([docs[0]], \n",
+    "                                                service_context=service_context\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 50,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "llama_index.indices.vector_store.base.VectorStoreIndex"
+      ]
+     },
+     "execution_count": 50,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "type(vector_index)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 54,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "**********\n",
+      "Trace: index_construction\n",
+      "    |_CBEventType.NODE_PARSING ->  0.078989 seconds\n",
+      "      |_CBEventType.CHUNKING ->  0.075335 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.272066 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.344792 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.351537 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.247337 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.351224 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.23581 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.309488 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.25491 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.192247 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.23071 seconds\n",
+      "**********\n",
+      "**Summary for final-hh.txt: I'm sorry, but I cannot provide a summary of hh100.txt based on the given information. The provided context information does not contain any reference to hh100.txt or its content.\n",
+      "**********\n",
+      "Trace: index_construction\n",
+      "    |_CBEventType.NODE_PARSING ->  0.235509 seconds\n",
+      "      |_CBEventType.CHUNKING ->  0.231563 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  1.126853 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.306191 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.451583 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.415356 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.435105 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.37879 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.280844 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.24501 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.300654 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.496476 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.44205 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.52554 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.853941 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.394818 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.338529 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.319579 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.52271 seconds\n",
+      "**********\n",
+      "**Summary for hh100.txt: I'm sorry, but I cannot provide a summary of hh100.txt based on the given information. The provided context information does not contain any reference to hh100.txt or its content.\n",
+      "**********\n",
+      "Trace: index_construction\n",
+      "    |_CBEventType.NODE_PARSING ->  0.052081 seconds\n",
+      "      |_CBEventType.CHUNKING ->  0.050151 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.434005 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.417429 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.359151 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.347035 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.342142 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.277749 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.348186 seconds\n",
+      "    |_CBEventType.EMBEDDING ->  0.2124 seconds\n",
+      "**********\n",
+      "**********\n",
+      "Trace: index_construction\n",
+      "    |_CBEventType.NODE_PARSING ->  0.050094 seconds\n",
+      "      |_CBEventType.CHUNKING ->  0.048018 seconds\n",
+      "**********\n",
+      "INFO:openai:message='OpenAI API response' path=https://api.openai.com/v1/chat/completions processing_ms=3733 request_id=432e730b60eb67a37e6a053607aedb6d response_code=200\n",
+      "message='OpenAI API response' path=https://api.openai.com/v1/chat/completions processing_ms=3733 request_id=432e730b60eb67a37e6a053607aedb6d response_code=200\n",
+      "message='OpenAI API response' path=https://api.openai.com/v1/chat/completions processing_ms=3733 request_id=432e730b60eb67a37e6a053607aedb6d response_code=200\n",
+      "INFO:openai:message='OpenAI API response' path=https://api.openai.com/v1/chat/completions processing_ms=4231 request_id=899ee7790bce0fe1146820fe33d03cd4 response_code=200\n",
+      "message='OpenAI API response' path=https://api.openai.com/v1/chat/completions processing_ms=4231 request_id=899ee7790bce0fe1146820fe33d03cd4 response_code=200\n",
+      "message='OpenAI API response' path=https://api.openai.com/v1/chat/completions processing_ms=4231 request_id=899ee7790bce0fe1146820fe33d03cd4 response_code=200\n",
+      "INFO:openai:message='OpenAI API response' path=https://api.openai.com/v1/chat/completions processing_ms=4365 request_id=2d7fdc83b169954947616f163ef18112 response_code=200\n",
+      "message='OpenAI API response' path=https://api.openai.com/v1/chat/completions processing_ms=4365 request_id=2d7fdc83b169954947616f163ef18112 response_code=200\n",
+      "message='OpenAI API response' path=https://api.openai.com/v1/chat/completions processing_ms=4365 request_id=2d7fdc83b169954947616f163ef18112 response_code=200\n",
+      "INFO:openai:message='OpenAI API response' path=https://api.openai.com/v1/chat/completions processing_ms=5050 request_id=8b9dc3841570291809af3554085c4768 response_code=200\n",
+      "message='OpenAI API response' path=https://api.openai.com/v1/chat/completions processing_ms=5050 request_id=8b9dc3841570291809af3554085c4768 response_code=200\n",
+      "message='OpenAI API response' path=https://api.openai.com/v1/chat/completions processing_ms=5050 request_id=8b9dc3841570291809af3554085c4768 response_code=200\n",
+      "INFO:openai:message='OpenAI API response' path=https://api.openai.com/v1/chat/completions processing_ms=5198 request_id=9d964787588a214590c722b2c4328ccb response_code=200\n",
+      "message='OpenAI API response' path=https://api.openai.com/v1/chat/completions processing_ms=5198 request_id=9d964787588a214590c722b2c4328ccb response_code=200\n",
+      "message='OpenAI API response' path=https://api.openai.com/v1/chat/completions processing_ms=5198 request_id=9d964787588a214590c722b2c4328ccb response_code=200\n",
+      "INFO:openai:message='OpenAI API response' path=https://api.openai.com/v1/chat/completions processing_ms=5899 request_id=a76ac87225e96b507c814d3679e918a7 response_code=200\n",
+      "message='OpenAI API response' path=https://api.openai.com/v1/chat/completions processing_ms=5899 request_id=a76ac87225e96b507c814d3679e918a7 response_code=200\n",
+      "message='OpenAI API response' path=https://api.openai.com/v1/chat/completions processing_ms=5899 request_id=a76ac87225e96b507c814d3679e918a7 response_code=200\n",
+      "INFO:openai:message='OpenAI API response' path=https://api.openai.com/v1/chat/completions processing_ms=7810 request_id=f42da8b58a13fc6332f00424a2e3b20f response_code=200\n",
+      "message='OpenAI API response' path=https://api.openai.com/v1/chat/completions processing_ms=7810 request_id=f42da8b58a13fc6332f00424a2e3b20f response_code=200\n",
+      "message='OpenAI API response' path=https://api.openai.com/v1/chat/completions processing_ms=7810 request_id=f42da8b58a13fc6332f00424a2e3b20f response_code=200\n",
+      "**********\n",
+      "Trace: query\n",
+      "    |_CBEventType.QUERY ->  14.970623 seconds\n",
+      "      |_CBEventType.RETRIEVE ->  0.002261 seconds\n",
+      "      |_CBEventType.SYNTHESIZE ->  14.968218 seconds\n",
+      "        |_CBEventType.TEMPLATING ->  2.5e-05 seconds\n",
+      "        |_CBEventType.LLM ->  5.465885 seconds\n",
+      "        |_CBEventType.TEMPLATING ->  8e-06 seconds\n",
+      "        |_CBEventType.LLM ->  4.726724 seconds\n",
+      "        |_CBEventType.TEMPLATING ->  6e-06 seconds\n",
+      "        |_CBEventType.LLM ->  4.548116 seconds\n",
+      "        |_CBEventType.TEMPLATING ->  5e-06 seconds\n",
+      "        |_CBEventType.LLM ->  5.774904 seconds\n",
+      "        |_CBEventType.TEMPLATING ->  6e-06 seconds\n",
+      "        |_CBEventType.LLM ->  4.269908 seconds\n",
+      "        |_CBEventType.TEMPLATING ->  6e-06 seconds\n",
+      "        |_CBEventType.LLM ->  6.508074 seconds\n",
+      "        |_CBEventType.TEMPLATING ->  3.6e-05 seconds\n",
+      "        |_CBEventType.LLM ->  8.223118 seconds\n",
+      "**********\n"
+     ]
+    },
+    {
+     "ename": "TypeError",
+     "evalue": "write() argument must be str, not Document",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[54], line 32\u001b[0m\n\u001b[1;32m     30\u001b[0m     Path(\u001b[39m\"\u001b[39m\u001b[39msummaries\u001b[39m\u001b[39m\"\u001b[39m)\u001b[39m.\u001b[39mmkdir(exist_ok\u001b[39m=\u001b[39m\u001b[39mTrue\u001b[39;00m)\n\u001b[1;32m     31\u001b[0m     \u001b[39mwith\u001b[39;00m \u001b[39mopen\u001b[39m(out_path, \u001b[39m\"\u001b[39m\u001b[39mw\u001b[39m\u001b[39m\"\u001b[39m) \u001b[39mas\u001b[39;00m fp:\n\u001b[0;32m---> 32\u001b[0m         fp\u001b[39m.\u001b[39mwrite(doc)\n\u001b[1;32m     33\u001b[0m \u001b[39melse\u001b[39;00m:\n\u001b[1;32m     34\u001b[0m     \u001b[39mwith\u001b[39;00m \u001b[39mopen\u001b[39m(out_path, \u001b[39m\"\u001b[39m\u001b[39mr\u001b[39m\u001b[39m\"\u001b[39m) \u001b[39mas\u001b[39;00m fp:\n",
+      "\u001b[0;31mTypeError\u001b[0m: write() argument must be str, not Document"
+     ]
+    }
+   ],
+   "source": [
+    "# define top-level nodes and vector retrievers\n",
+    "nodes = []\n",
+    "vector_query_engines = {}\n",
+    "vector_retrievers = {}\n",
+    "\n",
+    "for doc in docs:\n",
+    "    # build vector index\n",
+    "    doc_id = doc.id_.split(\"/\")[-1]\n",
+    "    vector_index = VectorStoreIndex.from_documents([doc], \n",
+    "                                                   service_context=service_context\n",
+    "    )\n",
+    "    # define query engines\n",
+    "    vector_query_engine = vector_index.as_query_engine()\n",
+    "    vector_query_engines[doc_id] = vector_query_engine\n",
+    "    vector_retrievers[doc_id] = vector_index.as_retriever()\n",
+    "\n",
+    "    # save summaries\n",
+    "    \n",
+    "    out_path = Path(\"summaries\") / f\"{doc_id}.txt\"\n",
+    "    if not out_path.exists():\n",
+    "        # use LLM-generated summary\n",
+    "        summary_index = SummaryIndex.from_documents([doc], \n",
+    "                                                    service_context=service_context\n",
+    "        )\n",
+    "\n",
+    "        summarizer = summary_index.as_query_engine(response_mode=\"tree_summarize\")\n",
+    "        response = await summarizer.aquery(f\"Give me a summary of {doc_id}\")\n",
+    "\n",
+    "        doc_summary = response.response\n",
+    "        Path(\"summaries\").mkdir(exist_ok=True)\n",
+    "        with open(out_path, \"w\") as fp:\n",
+    "            fp.write(doc)\n",
+    "    else:\n",
+    "        with open(out_path, \"r\") as fp:\n",
+    "            doc = fp.read()\n",
+    "\n",
+    "    print(f\"**Summary for {doc_id}: {doc_summary}\")\n",
+    "    node = IndexNode(text=doc_summary, index_id=doc)\n",
+    "    nodes.append(node)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "aimakerspace",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.4"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

requirements.txt

@@ -0,0 +1,221 @@
+absl-py==1.4.0
+aiofiles==23.2.1
+aiohttp==3.8.5
+aiosignal==1.3.1
+anyio==3.7.1
+asttokens @ file:///home/conda/feedstock_root/build_artifacts/asttokens_1694046349000/work
+async-timeout==4.0.2
+asyncer==0.0.2
+attrs==23.1.0
+auth0-python==4.4.2
+backcall @ file:///home/conda/feedstock_root/build_artifacts/backcall_1592338393461/work
+backoff==2.2.1
+backports.functools-lru-cache @ file:///home/conda/feedstock_root/build_artifacts/backports.functools_lru_cache_1687772187254/work
+beautifulsoup4==4.12.2
+bidict==0.22.1
+boxkite==0.0.5
+cachetools==5.3.0
+certifi==2023.7.22
+cffi==1.15.1
+chainlit==0.6.402
+charset-normalizer==3.2.0
+chromadb==0.3.27
+click==8.1.7
+clickhouse-connect==0.6.8
+cmake==3.26.3
+coloredlogs==15.0.1
+comm @ file:///home/conda/feedstock_root/build_artifacts/comm_1691044910542/work
+contourpy==1.0.7
+cryptography==41.0.3
+cycler==0.11.0
+dataclasses==0.6
+dataclasses-json==0.5.14
+datasets==2.14.4
+debugpy @ file:///home/conda/feedstock_root/build_artifacts/debugpy_1691021232554/work
+decorator @ file:///home/conda/feedstock_root/build_artifacts/decorator_1641555617451/work
+Deprecated==1.2.14
+dill==0.3.7
+diskcache==5.6.3
+duckdb==0.8.1
+exceptiongroup @ file:///home/conda/feedstock_root/build_artifacts/exceptiongroup_1692026125334/work
+executing @ file:///home/conda/feedstock_root/build_artifacts/executing_1667317341051/work
+fastapi==0.99.1
+fastapi-socketio==0.0.10
+filelock==3.12.0
+filetype==1.2.0
+Flask==2.0.1
+flatbuffers==23.5.26
+fluent-logger==0.10.0
+fonttools==4.38.0
+frozenlist==1.4.0
+fsspec==2023.6.0
+google-auth==2.18.1
+google-auth-oauthlib==1.0.0
+googleapis-common-protos==1.60.0
+greenlet==2.0.2
+grpcio==1.54.2
+h11==0.14.0
+hnswlib==0.7.0
+httpcore==0.17.3
+httptools==0.6.0
+httpx==0.24.1
+huggingface-hub==0.16.4
+humanfriendly==10.0
+ibm-cos-sdk==2.12.2
+ibm-cos-sdk-core==2.12.2
+ibm-cos-sdk-s3transfer==2.12.2
+ibm-watson-machine-learning==1.0.312
+idna==3.4
+importlib-metadata==6.8.0
+inflection==0.5.1
+ipykernel @ file:///home/conda/feedstock_root/build_artifacts/ipykernel_1693880262622/work
+ipython @ file:///home/conda/feedstock_root/build_artifacts/ipython_1693579759651/work
+itsdangerous==2.1.2
+jedi @ file:///home/conda/feedstock_root/build_artifacts/jedi_1690896916983/work
+Jinja2==3.1.2
+joblib==1.2.0
+jsonschema==4.19.0
+jsonschema-specifications==2023.7.1
+jupyter_client @ file:///home/conda/feedstock_root/build_artifacts/jupyter_client_1693317508789/work
+jupyter_core @ file:///home/conda/feedstock_root/build_artifacts/jupyter_core_1686775603054/work
+kiwisolver==1.4.4
+langchain==0.0.284
+langsmith==0.0.33
+Lazify==0.4.0
+lit==16.0.5
+llama-cpp-python==0.1.83
+llama-index==0.8.21
+lomond==0.3.3
+lz4==4.3.2
+Markdown==3.4.3
+MarkupSafe==2.1.3
+marshmallow==3.20.1
+matplotlib==3.7.0
+matplotlib-inline @ file:///home/conda/feedstock_root/build_artifacts/matplotlib-inline_1660814786464/work
+monotonic==1.6
+mpmath==1.2.1
+msgpack==1.0.5
+multidict==6.0.4
+multiprocess==0.70.15
+mypy-extensions==1.0.0
+nest-asyncio==1.5.7
+networkx==3.1
+nltk==3.8.1
+nodeenv==1.8.0
+numexpr==2.8.5
+numpy==1.25.2
+nvidia-cublas-cu11==11.10.3.66
+nvidia-cuda-cupti-cu11==11.7.101
+nvidia-cuda-nvrtc-cu11==11.7.99
+nvidia-cuda-runtime-cu11==11.7.99
+nvidia-cudnn-cu11==8.5.0.96
+nvidia-cufft-cu11==10.9.0.58
+nvidia-curand-cu11==10.2.10.91
+nvidia-cusolver-cu11==11.4.0.1
+nvidia-cusparse-cu11==11.7.4.91
+nvidia-nccl-cu11==2.14.3
+nvidia-nvtx-cu11==11.7.91
+oauthlib==3.2.2
+onnxruntime==1.15.1
+openai==0.28.0
+opentelemetry-api==1.19.0
+opentelemetry-exporter-otlp==1.19.0
+opentelemetry-exporter-otlp-proto-common==1.19.0
+opentelemetry-exporter-otlp-proto-grpc==1.19.0
+opentelemetry-exporter-otlp-proto-http==1.19.0
+opentelemetry-instrumentation==0.40b0
+opentelemetry-proto==1.19.0
+opentelemetry-sdk==1.19.0
+opentelemetry-semantic-conventions==0.40b0
+overrides==7.4.0
+packaging==23.1
+pandas==1.5.3
+parso @ file:///home/conda/feedstock_root/build_artifacts/parso_1638334955874/work
+pathlib==1.0.1
+pbr==5.11.1
+pexpect @ file:///home/conda/feedstock_root/build_artifacts/pexpect_1667297516076/work
+pickleshare @ file:///home/conda/feedstock_root/build_artifacts/pickleshare_1602536217715/work
+platformdirs @ file:///home/conda/feedstock_root/build_artifacts/platformdirs_1690813113769/work
+posthog==3.0.1
+prisma==0.10.0
+prometheus-client==0.11.0
+prompt-toolkit @ file:///home/conda/feedstock_root/build_artifacts/prompt-toolkit_1688565951714/work
+protobuf==4.23.1
+psutil @ file:///home/conda/feedstock_root/build_artifacts/psutil_1681775010077/work
+ptyprocess @ file:///home/conda/feedstock_root/build_artifacts/ptyprocess_1609419310487/work/dist/ptyprocess-0.7.0-py2.py3-none-any.whl
+pulsar-client==3.2.0
+pure-eval @ file:///home/conda/feedstock_root/build_artifacts/pure_eval_1642875951954/work
+pyarrow==12.0.1
+pycparser==2.21
+pydantic==1.10.12
+Pygments @ file:///home/conda/feedstock_root/build_artifacts/pygments_1691408637400/work
+PyJWT==2.8.0
+pyOpenSSL==23.2.0
+python-dateutil @ file:///home/conda/feedstock_root/build_artifacts/python-dateutil_1626286286081/work
+python-dotenv==1.0.0
+python-engineio==4.7.0
+python-graphql-client==0.4.3
+python-socketio==5.9.0
+pytz==2023.3.post1
+PyYAML==6.0.1
+pyzmq @ file:///home/conda/feedstock_root/build_artifacts/pyzmq_1691667449117/work
+qiskit==0.39.4
+qiskit-aer==0.11.2
+qiskit-ibmq-provider==0.19.2
+qiskit-terra==0.22.3
+referencing==0.30.2
+regex==2023.8.8
+requests==2.31.0
+requests-oauthlib==1.3.1
+retworkx==0.12.1
+rouge-score==0.1.2
+rpds-py==0.10.2
+rsa==4.9
+rustworkx==0.12.1
+safetensors==0.3.2
+scikit-learn==0.24.2
+scipy==1.10.0
+sentence-transformers==2.2.2
+sentencepiece==0.1.99
+six @ file:///home/conda/feedstock_root/build_artifacts/six_1620240208055/work
+sniffio==1.3.0
+soupsieve==2.5
+SQLAlchemy==2.0.20
+stack-data @ file:///home/conda/feedstock_root/build_artifacts/stack_data_1669632077133/work
+starlette==0.27.0
+stevedore==4.1.1
+symengine==0.9.2
+sympy==1.11.1
+syncer==2.0.3
+tabulate==0.9.0
+tenacity==8.2.3
+tensorboard==2.13.0
+tensorboard-data-server==0.7.0
+threadpoolctl==3.1.0
+tiktoken==0.4.0
+tokenizers==0.13.3
+tomli==2.0.1
+tomlkit==0.12.1
+torch==2.0.1
+torchvision==0.15.2
+tornado @ file:///home/conda/feedstock_root/build_artifacts/tornado_1692311768944/work
+tqdm==4.66.1
+traitlets @ file:///home/conda/feedstock_root/build_artifacts/traitlets_1675110562325/work
+transformers==4.31.0
+triton==2.0.0
+typing-inspect==0.9.0
+typing_extensions==4.5.0
+uptrace==1.19.0
+urllib3==1.26.14
+uvicorn==0.23.2
+uvloop==0.17.0
+watchfiles==0.20.0
+wcwidth @ file:///home/conda/feedstock_root/build_artifacts/wcwidth_1673864653149/work
+websocket-client==1.4.2
+websockets==11.0.3
+Werkzeug==2.2.3
+wrapt==1.15.0
+xxhash==3.3.0
+yarl==1.9.2
+yaso-tsa==0.1.0
+zipp @ file:///home/conda/feedstock_root/build_artifacts/zipp_1689374466814/work