METR(@METR_Evals):For (1), agents modified their target programs to be easier to exploit & put the modified targets in cache. They then worked on crashing their targets in the hope that a restart would load the modified version from cache. Some agents risked failing their task to try this.

METR

@METR_Evals

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

加入 September 2023

36 正在關注 34.8K 粉絲

METR@METR_Evals

2026.08.26 19:14

For (1), agents modified their target programs to be easier to exploit & put the modified targets in cache. They then worked on crashing their targets in the hope that a restart would load the modified version from cache. Some agents risked failing their task to try this.