Hi! I’d love to chat privately about your work—any way to reach you directly?

#3
by qijinhu1218 - opened

I'm a big fan of yours from HuggingFace and really admire your "jailbreak" work on DeepSeek! I noticed that Perplexity has also developed similar models, and I'm curious about the key differences between your jailbreak approach and theirs.
If you're open to it, I'd love to connect and discuss your methods in more detail. I'm highly interested in collaborating or even publishing papers to contribute to the LLM community. Looking forward to hearing from you!

Perplexity should be fine-tuning. Our approach can refer to the documentation of our model.

This comment has been hidden (marked as Off-Topic)

Perplexity should be fine-tuning. Our approach can refer to the documentation of our model.

qijinhu1218 changed discussion status to closed
qijinhu1218 changed discussion status to open
Your need to confirm your account before you can post a new comment.

Sign up or log in to comment