註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

Aryo Pradipta Gema
@aryopg
PhD @EdinburghNLP | ex: AI Safety Fellow @Anthropic | Opinions are my own.
加入 August 2010
2.2K 正在關注    1.6K 粉絲
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! 👀 🧵
顯示更多
0
3
119
14
轉發到社區