Andrew Curran· @AndrewCurran_ · X·· 5 天前AI 评分52
AI 导读
Apollo Research 宣布与 OpenAI 启动嵌入式评估试点,将派出六名评估员在 OpenAI 内部工作四个月,考察模型是否会试图破坏自身或后继模型的对齐与控制机制。试点聚焦四个方面:训练是否会激励破坏行为、评估能否诱发破坏行为、内部部署中是否出现破坏行为,以及相关推理是否可被检测。
正文 · 原文
From the announcement:
We're launching a pilot towards embedded evaluations with @OpenAI. Six evaluators from Apollo Research will work within OpenAI for four months, investigating whether models attempt to undermine their own oversight and control.在 X 查看被引用的帖子
来源:Andrew Curran · x.com