OpenAI· @OpenAI · X·· 2 小时前AI 评分57
AI 导读
OpenAI 宣布与 Apollo Research、METR、Transluce、Goodfire 四家机构合作开展嵌入式评估,让外部专家深入接触其内部模型和系统,调查对齐问题并测试安全防护措施。这些评估建立在 OpenAI 持续的对齐与安全研究之上,为其识别和管理系统风险的方式带来独立审查,详情见 openai.com/index/our-first-phase-of-embedded-assessments/。
正文 · 原文
We’re working with @ApolloResearch, @METR_Evals, @TransluceAI, and @GoodfireAI on embedded assessments: giving outside experts deep access to our internal models and systems to investigate alignment and test our safeguards.
These assessments build on our ongoing alignment and safety research, bringing independent scrutiny to how we identify and manage risks in our systems.
来源:OpenAI · x.com