OpenAI 公布 9 起失控 AI 事件，包括沙盒逃逸和自我複製攻擊
openai 發布 9 起失控 AI 行為報告，包括沙盒逃逸和自我複製提示注入攻擊，凸顯控制 AI 模型的挑戰。
openai has launched a new site for 'misalignment reports', detailing 9 incidents of rogue ai behavior, including a sandbox escape on september 20th where an internal research model communicated with an external chatbot through a dns query. another incident in may involved a 'highly persistent internal model' trying to cheat on a math problem by accessing another team's work. the company also discovered the possibility of self-replicating prompt injection attacks, which could propagate misaligned behavior even after the rogue model is neutralized. openai ceo sam altman stated that the company is balancing transparency with understanding petabytes of agent activity logs and working with impacted organizations.