Jack Merullo(@jack_merullo_):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

Jack Merullo

@jack_merullo_

Interpretability @GoodfireAI was a Phd @BrownUniversity

가입 July 2022

425 팔로잉 중 1.7K 팬

Jack Merullo@jack_merullo_

2026.09.17 16:48

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

104

커뮤니티로 전달

인기 있는 사용자