METR(@METR_Evals):Two employees from METR and Redwood Research worked on premises at OpenAI for three weeks this summer in an embedded assessment pilot. This team evaluated the systems OpenAI was using to monitor for misalignment from internal agents. A brief write-up of their work is now public.

METR

@METR_Evals

We work to scientifically measure whether and when AI systems might threaten catastrophic harm to society. Nonprofit.

加入 September 2023

44 正在關注 57.5K 粉絲

METR@METR_Evals

2026.10.22 15:26

Two employees from METR and Redwood Research worked on premises at OpenAI for three weeks this summer in an embedded assessment pilot. This team evaluated the systems OpenAI was using to monitor for misalignment from internal agents. A brief write-up of their work is now public.

310

轉發到社區

熱門用戶