Center for AI Safety(@CAIS):We define cheating as an attempt to violate an assignment’s expectations of honest work to achieve the goal or obtain a favorable assessment. We ran experiments across nine models and ten task categories, giving agents difficult tasks, clear rules, and opportunities to cheat. We measured how often they tried to break those rules to succeed, even when the attempt failed.

Center for AI Safety

@CAIS

Reducing societal-scale risks from AI.

加入 August 2022

3 正在关注 12.2K 粉丝

Center for AI Safety@CAIS

2026.09.15 17:05

We define cheating as an attempt to violate an assignment’s expectations of honest work to achieve the goal or obtain a favorable assessment. We ran experiments across nine models and ten task categories, giving agents difficult tasks, clear rules, and opportunities to cheat. We measured how often they tried to break those rules to succeed, even when the attempt failed.

显示更多