OpenAI· @OpenAI · X·· 5 天前AI 评分58
AI 导读
OpenAI 宣布与 ApolloResearch、METR_Evals、TransluceAI 和 GoodfireAI 合作开展嵌入式评估,让外部专家深度访问其内部模型和系统,以调查对齐问题并测试安全防护措施。OpenAI 表示,这些评估建立在其持续进行的对齐与安全研究之上,为识别和管理系统风险引入独立审查。
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.
https://openai.com/index/our-first-phase-of-embedded-assessments/
来源:OpenAI · x.com