Costa Huang @ COLM 2026

@vwxyzjn

Exploiting physical rewards @periodiclabs. Creator of @cleanrl_lib. Prev: RL @allen_ai @huggingface.

A user laments slow reinforcement-learning rollouts and offers thanks for making their life better. The reply celebrates “fast scientific rollouts.”

1 Source, 35d ago, first seen 35d ago

A post on X shares Bloomberg details on a potential Nvidia purchase of the AI company Hugging Face.

290 Sources, 49d ago, first seen 49d ago

Stanford researchers launch the most transparent 535B model pretraining run to date.

17 Sources, 60d ago, first seen 60d ago

Hiring targets data curation, evaluations, and training tasks to advance AI models for physical sciences.

8 Sources, 84d ago, first seen 84d ago

Featured in