Dan Hendrycks· @hendrycks · X·· 2025-12-02AI 评分45
AI 导读
AI安全研究员Dan Hendrycks在X上发帖，针对谷歌DeepMind机械可解释性团队转向“实用可解释性”（pragmatic interpretability）一事表示，他多年来一直认为机械可解释性方向有误，很高兴看到人们多年后终于认同这一观点。该帖子引用了Neel Nanda关于GDM团队调整研究方法的声明。
正文 · 原文
I've been saying mechanistic interpretability is misguided from the start.
Glad people are coming around many years later.
The GDM mechanistic interpretability team has pivoted to a new approach: pragmatic interpretability Our post details how we now do research, why now is the time to pivot, why we expect this way to have more impact and why we think other interp researchers should follow suit在 X 查看被引用的帖子
来源：Dan Hendrycks · x.com