OpenAI· @OpenAI · X·· 2 小时前AI 评分59
AI 导读
OpenAI 宣布 METR 将调查其迄今最大规模强化学习运行中的失配行为,包括现有测试和监控可能遗漏的失败案例。双方还初步同意开展更广泛的监控评估,尚待就范围达成一致。
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