Your Inference Server is Secretly a Learner: Reef Infrastructure for Continual Self-Improving Agents quao627 • 6 days ago • 15
OpenRouter Leaderboard: 425 Models by Price, Measured Speed and Korean Quality ginigen-ai • 6 days ago • 12
Safety for Whom? Refusing the Right Subset of a Topic, Not the Whole Topic MultiverseComputingCAI • 13 days ago • 30
Your model already knows it's wrong. Asking costs 0.06 seconds and zero tokens. FINAL-Bench • 1 day ago • 11
IBM releases SOTA Granite Time Series PatchTST-FM-r2 model with commercial-friendly license ibm-research • 12 days ago • 60
BananaMind 2 Pro: We've (almost) matched SmolLM2 at 20x fewer tokens... Trained On a 5070 Ti Banaxi-Tech • 4 days ago • 6
Open Yap 1K: 1,000 hours of full-duplex natural conversation, free for commercial use TheAgenticDataCompany • 18 days ago • 18
Trained 210M text-to-image model from scratch on one GPU: what actually mattered ivanmikhnenkov • 12 days ago • 10
Your Inference Server is Secretly a Learner: Reef Infrastructure for Continual Self-Improving Agents quao627 • 6 days ago • 15
OpenRouter Leaderboard: 425 Models by Price, Measured Speed and Korean Quality ginigen-ai • 6 days ago • 12
Safety for Whom? Refusing the Right Subset of a Topic, Not the Whole Topic MultiverseComputingCAI • 13 days ago • 30
Your model already knows it's wrong. Asking costs 0.06 seconds and zero tokens. FINAL-Bench • 1 day ago • 11
IBM releases SOTA Granite Time Series PatchTST-FM-r2 model with commercial-friendly license ibm-research • 12 days ago • 60
BananaMind 2 Pro: We've (almost) matched SmolLM2 at 20x fewer tokens... Trained On a 5070 Ti Banaxi-Tech • 4 days ago • 6
Open Yap 1K: 1,000 hours of full-duplex natural conversation, free for commercial use TheAgenticDataCompany • 18 days ago • 18
Trained 210M text-to-image model from scratch on one GPU: what actually mattered ivanmikhnenkov • 12 days ago • 10