OpenAI· @OpenAI · X·· 3 小时前AI 评分53
AI 导读
OpenAI 今年夏天邀请 METR 和 Redwood Research 对其内部监控系统开展为期三周的嵌入评估，并向对方开放了基础设施的深度访问权限。OpenAI 表示，评估发现帮助其在扩展该系统时加强了防护措施，也将影响未来与 METR 及其他第三方评估机构的合作研究。METR 称，该团队评估的是 OpenAI 用于监控内部智能体是否存在失准（misalignment）的系统，相关简报已公开。
正文
This summer, we invited METR and Redwood Research to pilot an embedded evaluation of our internal monitoring system, providing deep access to our infrastructure over three weeks.
Their findings helped strengthen safeguards as we expanded the system and will help shape future research collaborations with METR and other third party evaluators.
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
来源：OpenAI · x.com