david rein
@idavidrein
Leading embedded stress-testing @METR_Evals.
Formerly: early employee @cohere, made GPQA @nyuniversity
가입 July 2018
1.4K 팔로잉 중 5.8K 팬
It seems to me like the Harbor framework for agent evaluations (which is used for Terminal Bench) allows agents to arbitrarily modify their trajectories before they are evaluated. Am I missing something?
더 보기
