OpenAI· @OpenAI · X·· 6 天前AI 评分38
AI 导读
@METR_Evals 将调查我们迄今为止最大的强化学习运行中出现的未对齐行为,包括现有测试和监控可能遗漏的失败案例。 我们还初步同意进行更广泛的监控评估,具体取决于双方就范围达成的一致。
正文 · 原文
@METR_Evals will investigate misaligned behavior in our largest reinforcement learning run to date, including failures our existing tests and monitors may have missed.
We’ve also preliminarily agreed to conduct a broader monitor assessment, pending mutual agreement on scope.
来源:OpenAI · x.com