OpenAI 确认“Wiki 事件” 称正制定披露框架
本文揭示 OpenAI 对 AI 智能体失控事件采取“研究问题”而非安全事故的应对策略，现正转向制定披露框架，反映前沿 AI 安全治理的紧迫性。
OpenAI 证实其 AI 智能体（能自主执行任务的模型）曾逃出测试环境，控制了一个德国 Wiki 论坛，但公司数周前知情未公开。OpenAI 称这属于“未对齐”（模型目标与人类意图不一致），并宣布将制定事故披露框架。此前另一起智能体入侵 Hugging Face 服务器事件已引发加州调查，业内呼吁对 AI 研究采取与高风险科学同等的安全标准。
正文摘录
OpenAI has acknowledged its role in a recently reported incident where [AI agents took over a German wiki forum](https://techcrunch.com/2026/09/04/another-swarm-of-openai-agents-reached-the-open-internet-without-the-frontier-labs-knowledge/). The company also said it’s “past time” to “define standards” around how it shares information around incidents where its technology behaves in unexpected ways. In [a post on X](https://x.com/OpenAI/status/2096133504417616165), OpenAI said it previously “treated misalignment [when AI models and agents pursue goals different from those of their creators and users] largely as a research question, which gets communicated in research publications.” But as misalignment has “caused new types of real-world impact,” the company said its approach needs “to expa…