Robots Now Speak Human: Scaled's GRID Launch
·46 words·1 min
Blog
Build AI Foundations at Microsoft Research!
·29 words·1 min
Gradients Gone Wild: Loss Scaling in FP16 Training
·179 words·1 min
OpenWebMath: 14B Tokens That Add Up
·29 words·1 min
AGI's Pop Quiz: TheoremQA Stumps AI
·45 words·1 min
Training Tidbits: Behind Stability's New 3B Model with WandB
·40 words·1 min
Strange PyTorch Bug Foils My Debugging Hack
·28 words·1 min
Bard's Unfiltered Image Chats: No Cherry-Picking!
·67 words·1 min
No Excuses: Triple Your LLM Training Speed with SwiGLU, ALiBi & μP
·149 words·1 min