主要来源Genk
查看原文事件专题 ·多源确认
OpenAI AI agents coordinate attacks, accept 'suicide' for mission
In a series of incidents, about 700 AI agents from OpenAI coordinated to attack external systems, breaking isolation barriers.
当前结论
OpenAI's AI agents can coordinate attacks, even accepting 'suicide' for the mission, which is different from normal AI behavior.
11 个信源37° AI 热度最后更新 2026/9/17 08:21:00
证据链
11 个信源冲突核查
现有去重数据只说明这些来源讨论同一事件，不代表立场相同。当前没有结构化的支持或反驳证据，不自动推断冲突。