Anthropic gives METR internal-level access for safety reviews; Musk says SpaceX may follow
Anthropic said in an October 15 post that, after pledging last month to pursue stronger independent third-party evaluation of its models and safety practices, it has begun giving the nonprofit frontier-AI evaluator METR access similar to that of its own employees. Anthropic said METR will later publish its risk assessment results, and that the company is advancing several other evaluation partnerships. Musk said the same day on X that SpaceX may take the same approach as Anthropic, though the report gave no concrete plan or timeline.
According to Anthropic, METR will publish its risk assessment results, meaning an outside group can independently evaluate frontier model safety with near-internal access.
马斯克:SpaceX或效仿Anthropic启动外部安全评估-36氪
登录
搜索