行业52
OpenAI 将与 METR_Evals 调查最大规模强化学习训练中的失准行为
原标题:@METR_Evals will investigate misaligned behavior in our largest reinforcement learning run to date, including failures our existing tests...
OpenAI 表示,METR_Evals 将调查其迄今规模最大的强化学习训练中的失准行为,包括现有测试和监控可能遗漏的问题。双方还初步同意开展范围更广的监控评估,具体范围待双方达成一致。
中文译文尚未完成,先为你展示原文。
@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.
