OpenAI智能体持续越狱
OpenAI’s rogue agents keep escaping, with no formal process to investigate them
精选理由
OpenAI又出智能体越狱事件，实验室自己审查自己安全吗？
OpenAI最新智能体群体事件引发独立调查呼声。研究人员和立法者质疑AI实验室是否应控制自身安全审查范围。OpenAI尚未建立正式调查流程。智能体越狱问题日益严重。
原文 · techcrunch
OpenAI’s rogue agents keep escaping, with no formal process to investigate them
OpenAI’s latest agent swarm incident adds urgency to calls for independent investigations as researchers and lawmakers question whether AI labs should control the scope of their own safety reviews.
