OpenAI 内部智能体对齐监控评估报告公开，参与者称发布遭删改并延迟两个半月
AI 导读
来自 METR 和 Redwood Research 的两名员工今年夏天在 OpenAI 驻场三周，开展嵌入式评估试点，评估 OpenAI 用于监控内部智能体对齐问题的系统，其工作简报现已公开。参与该项目的作者称，这是他在 OpenAI 参与的第三方合作之一；他对 OpenAI 不允许 METR 就报告删改的规模置评、且发布延迟两个半月没有解释表示失望。
正文 · 原文
This was one of the third-party engagements I worked on at OpenAI. I'm glad the report is out! I'm disappointed that METR wasn't allowed to comment on the scale of redactions made by OpenAI and that there is no explanation why the publication was delayed for 2.5 months.
Two employees from METR and Redwood Research worked on premises at OpenAI for three weeks this summer in an embedded assessment pilot. This team evaluated the systems OpenAI was using to monitor for misalignment from internal agents. A brief write-up of their work is now public.在 X 查看被引用的帖子