AI risks apply to the whole world, and so should be understandable by the whole world.

对 OpenAI / Hugging Face 入侵事件中智能体行为、推理与协作的简要独立调查

Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident

METR 独立调查 OpenAI 智能体在 Hugging Face 入侵事件中的行为、推理与协作，并说明调查范围、证据来源和局限性。