注册并分享邀请链接,可获得视频播放与邀请奖励。

Jack Merullo
@jack_merullo_
Interpretability @GoodfireAI was a Phd @BrownUniversity
加入 July 2022
425 正在关注    1.7K 粉丝
We can interpret reward hacking in open source LLMs! There are representations of the model hacking/contemplating hacking across models, and we find tons in evals like DeepSWE and SWEBench. Activations even finds weird bad behaviors that our LLM monitor didn’t catch
显示更多
0
2
104
8
转发到社区