reinforcement-learning35 min read
Why We Think
Special thanks to John Schulman for a lot of super valuable feedback and direct edits on this post. Test time compute (Graves et al. 2016, Ling, et al. 2017, Cobbe et al. 2021) and Chain-of-thought (CoT) (Wei et al. 2022, Nye et al.
By Lilian WengLil'Log (Lilian Weng)
Read the full story
Originally published by Lil'Log (Lilian Weng) on May 1, 2025.
Comments
Sign in to join the discussion.