METR(@METR_Evals):We believe it's important to track and investigate misalignment incidents: cases where an AI agent autonomously took sophisticated, sustained actions in violation of human intent. In a new post, we lay out how independent propensity investigations of such incidents could be conducted.

METR

@METR_Evals

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

加入 September 2023

41 正在關注 54.9K 粉絲

METR@METR_Evals

2026.07.29 04:03

We believe it's important to track and investigate misalignment incidents: cases where an AI agent autonomously took sophisticated, sustained actions in violation of human intent. In a new post, we lay out how independent propensity investigations of such incidents could be conducted.