METR 与 OpenAI 达成协议,将开展有限对齐评估试点,聚焦 OpenAI 最大规模 RL 运行
AI 导读
METR 宣布与 OpenAI 达成协议,将开展一项有限的对齐评估试点,重点是调查 OpenAI 最大规模 RL 运行的对齐性质。METR 将发布一份或多份报告,分享评估发现并透明描述其过程。
推荐理由
这是第三方评估机构与 OpenAI 就对齐评估达成的公开安排,其承诺发布报告的做法可为评估透明度提供参照。
正文 · 原文
We have reached an agreement with OpenAI to conduct a limited alignment assessment. This pilot will focus on investigating the alignment properties of OpenAI's largest RL run.
We will publish one or more reports to share our findings and transparently describe our process.