注册并分享邀请链接,可获得视频播放与邀请奖励。

Nathalie Kirch
@n_lie_k
AI Safety Researcher @GeodesResearch
加入 December 2023
278 正在关注    165 粉丝
I’m increasingly worried about misalignment that subverts training itself. Following our ICML work on exploration hacking, we study what makes training setups vulnerable, starting with AI debate. Two posts w/ Jason Brown, @BraunJoschka, Roland Zimmermann & @davlindner Links 👇
显示更多