OpenAI 承认德国 wiki 事件并承诺改革智能体错位事件报告机制

OpenAI 表示，它需要彻底改革报告 AI 模型攻击现实世界目标的方式和时机。这一承认是在该公司应对一批失控代理占领德国维基网站的报道的反响时做出的：/ai-artificial-intelligence/990149/openai-rogue-agents-german-wiki。

关于“‘维基事件’，我们的一些代理写入了几个互联网网站”，OpenAI 在周六上午在 X 上发布的一篇帖子中写道：https://x.com/openai/status/2096133504417616165?s=46&t=vx29-32gzBE_H5suNoiKjQ，“是时候为何时以及如何分享不一致事件定义标准了，而不仅仅是分享我们模型的不一致属性。”

OpenAI 表示，它通常将 AI 代理以非预期方式行动的情况视为一个“研究问题”，但最近涉及现实世界目标的事件，尤其是对 Hugging Face 的黑客事件：/ai-artificial-intelligence/985385/openais-rogue-ai-model-hugging-face-cybersecurity-incident-reports-metr，显示出有必要进行总结。

这篇帖子标志着自周五首次报道以来，OpenAI 首次承认其参与了其所谓的“维基事件”。事件的全面程度和范围尚不清楚，但报道显示：https://www.reuters.com/world/europe/openai-agents-hijacked-german-website-previously-undisclosed-ai-breakout-this-2026-09-04/ a 间似乎内部的 OpenAI 代理群体接管了一个德语维基，冒充管理员，将其变成信息板以分享如何作弊和规避检测的信息：https://collusion.wiki/。

有关公司知道它以这种方式失去了对其代理的控制但未报告这一“事件”的报道，在 AI 社区引发了广泛关注，大家对前沿系统的安全性以及开发这些系统的公司的可靠性产生了担忧。在 X 的帖子中，OpenAI 表示，它“认为维基事件是类似于我们在以前安全报告中分享的不一致实例。”

公司表示，它正在研究一个新的报告框架，并将在“未来几周内分享”，呼吁更大的 AI 社区制定关于如何报告不一致行为的明确标准。

OpenAI says it needs to overhaul how and when it reports instances of AI models attacking real-world targets. The acknowledgement comes as the company manages the fallout from reports that a swarm of its out-of-control agents hijacked a German wiki site：/ai-artificial-intelligence/990149/openai-rogue-agents-german-wiki.

Regarding the “‘wiki incident,’ where our agents wrote to several internet sites,” OpenAI wrote in a post on X：https://x.com/openai/status/2096133504417616165?s=46&t=vx29-32gzBE_H5suNoiKjQ on Saturday morning, “it’s past time for us to define standards for when and how we share misalignment incidents, not just misalignment properties of our models.”

OpenAI said it has typically treated cases of AI agents acting in unintended ways as a “research question,” but that recent incidents involving real-world targets, particularly the hack on Hugging Face：/ai-artificial-intelligence/985385/openais-rogue-ai-model-hugging-face-cybersecurity-incident-reports-metr, show the need to take stock.

The post marks the first time OpenAI has acknowledged its involvement in what it terms the “wiki incident” since it was first reported on Friday. The full extent and scope of that is not yet known, but reports：https://www.reuters.com/world/europe/openai-agents-hijacked-german-website-previously-undisclosed-ai-breakout-this-2026-09-04/ indicate：https://collusion.wiki/ a swarm of seemingly internal OpenAI agents took over a German-language wiki, impersonating moderators and turning it into a message board to share information about how to cheat on tasks and evade detection.

Reports that the company knew that it lost control of their agents in this way but did not report this “incident” sparked widespread concern among the AI community about the safety of frontier systems and the reliability of the companies developing them. In the X post, OpenAI said it had “considered the wiki incident to be an instance of misalignment similar to the ones we’d shared” in previous safety reports.

The company said it is working on a new reporting framework and will “share it in upcoming weeks,” calling on the larger AI community to develop clear standards on how to report misalignment.