Nathan Lambert

natolambert

AI & ML interests

Reinforcement learning, Ethics, Robotics, Dynamics Models

Recent Activity

updated a dataset about 20 hours ago
allenai/tulu-3-sft-olmo-2-mixture
updated a dataset about 20 hours ago
allenai/tulu-3-sft-personas-math
updated a dataset about 20 hours ago
allenai/tulu-3-sft-personas-math-grade
View all activity

Organizations

Ai2's profile picture Society & Ethics's profile picture MBRL Library's profile picture Simulation Environments Tests and Builds's profile picture BigCode's profile picture 🤗 H4 Community's profile picture CompVis Community's profile picture Explorer of Simulate alpha's profile picture University of Washington NLP's profile picture calmcode's profile picture Berkeley-Nest's profile picture OLMo Friends's profile picture Brrr Gang's profile picture AI2 Adapt Dev's profile picture Social Post Explorers's profile picture OLMoE's profile picture Interconnects AI's profile picture

natolambert's activity

upvoted an article about 1 month ago
view article
Article

Putting RL back in RLHF

75