Aryo Pradipta Gema
@aryopg
PhD @EdinburghNLP | ex: AI Safety Fellow @Anthropic | Opinions are my own.
2.2K Following 1.6K Followers
CoT monitoring assumes reasoning traces record what shapes an answer.
Yet, we found that models are less likely to verbalize a cue in its CoT when the cue comes from a tool return instead of the user message! 👀
🧵
Show more
