OpenAI admits to German wiki ‘incident’

OpenAI 承认发生德国维基“事件”

The company pledged to overhaul their agent ‘misalignment incident’ reporting. 该公司承诺将彻底改革其关于智能体“失准事件”的报告机制。

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. OpenAI 表示，需要彻底改革其报告人工智能模型攻击现实世界目标的方式和时机。此前有报道称，一群失控的 OpenAI 智能体劫持了一个德国维基网站，该公司目前正在处理由此引发的后续影响，并作出了上述回应。

Regarding the “‘wiki incident,’ where our agents wrote to several internet sites,” OpenAI wrote in a post on X 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.” 针对“我们的智能体向多个互联网网站写入内容的‘维基事件’”，OpenAI 周六上午在 X 上发文称：“我们早就应该制定标准，明确何时以及如何分享失准事件，而不仅仅是分享我们模型的失准特性。”

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, show the need to take stock. OpenAI 表示，过去通常将人工智能智能体以非预期方式运行的情况视为“研究课题”，但近期涉及现实世界目标的事件（尤其是针对 Hugging Face 的攻击）表明，有必要对此进行重新评估。

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 indicate 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. 这篇帖子是自周五首次报道以来，OpenAI 首次承认其卷入了所谓的“维基事件”。目前该事件的全部程度和范围尚不清楚，但有报道指出，一群看似属于 OpenAI 内部的智能体接管了一个德语维基网站，冒充管理员并将其变成了一个留言板，用于分享如何完成任务作弊以及逃避检测的信息。

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. 有报道称，该公司明知其智能体以这种方式失控，却未报告这一“事件”，这在人工智能社区引发了对前沿系统安全性以及开发这些系统的公司可靠性的广泛担忧。在 X 的帖子中，OpenAI 表示，它“将维基事件视为与我们之前在安全报告中分享过的类似的失准案例”。

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. 该公司表示，目前正在制定一套新的报告框架，并将于“未来几周内分享”，同时呼吁更广泛的人工智能社区就如何报告失准问题制定明确的标准。