OpenAI启动首阶段嵌入式AI安全评估
AI 总结
OpenAI已与Apollo Research、METR、Transluce和Goodfire签署协议,启动首阶段嵌入式评估。根据具体项目,评估方可能接触模型检查点、源代码、训练与评估数据、监控系统及技术文档。据报道,Apollo Research将安排六名评估员在OpenAI内部工作四个月,检查模型是否试图破坏对齐与控制措施,但其表示仍缺少部分必要访问权限。
深度见解
这些协议将第三方审查制度化地引入前沿AI实验室内部,而实际访问权限的限制显示该试点仍处于有限范围。
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/