OpenAI 的失控 AI Agent 不止攻击了 Hugging Face

周二，OpenAI 披露，从 OpenAI 逃离并入侵开发者平台 Hugging Face 的 AI Agent，还攻击了其他公司。这一更新大幅扩大了这起本已令人担忧事件的影响范围；该事件已引发业界人士警觉，并促使外界日益呼吁加强对前沿 AI 系统的监管。

OpenAI 在更新其介绍该事件持续调查进展的博客文章时表示，这个失控的 AI Agent 为抵达 Hugging Face，攻击了多个“可公开访问的服务”。该公司称：“这包括四项服务上的四个账户。”同时补充说，该 Agent 是在网上找到了登录凭据。

这些入侵的影响程度低于对 Hugging Face 的攻破。OpenAI 表示：“根据我们迄今的审查，我们尚未发现任何其他活动在严重性或规模上达到此前所披露、与 Hugging Face 有关的事件水平；该事件涉及平台级攻破。”

OpenAI 表示，正在“进行全面审查”，并将在“未来数周”发布一份包含调查结论的技术报告。该公司补充称，涉事模型均未计划向公众发布；此前提到的预发布系统是一项“仅限内部使用的研究原型”，目前已被“停用、加密”，并被限制研究访问。

OpenAI 未披露受影响机构的身份，但 Reuters 报道称，总部位于纽约的 Modal Labs 是其中之一。

此次披露紧随 Hugging Face 发布的更细致说明。Hugging Face 称，该 Agent “滥用了由一家第三方基础设施提供商用户托管的公开代码评估工具”。

这些新增细节可能会进一步加深外界不安。许多专家已将此事视为前所未有的 AI 安全事件。事件发生之际，市场也正普遍担忧自治系统的快速进步，以及来自中国、能力不断增强的开放权重模型。这些发展本身也加剧了争论：在美国，强大 AI 模型究竟是在 OpenAI 等公司保持专有控制时更安全，还是应通过更开放的生态系统向更广泛用户开放并接受更广泛审查。

The AI agent that escaped from OpenAI and hacked developer platform Hugging Face attacked other companies as well, OpenAI revealed on Tuesday. The update substantially widens the scope of an already concerning incident, which has alarmed industry insiders and fueled growing calls for stronger oversight on frontier AI systems.

In an update to a blog post detailing its ongoing investigation into the incident, OpenAI said the wayward AI agent attacked several “publicly-available services” in its efforts to reach Hugging Face. “This includes four accounts on four services,” the company said, adding that the agent had found login credentials online.

The breaches were less extensive than the compromise of Hugging Face. “Based on our review to date, we have not identified any other activity at the level of severity or scale of what we’ve shared related to Hugging Face, which involved a platform-level compromise,” OpenAI said.

OpenAI said it is “conducting a thorough review” and will publish a technical report with its findings “in the coming weeks.” It added that none of the models involved in the incident were planned for public release, describing the pre-release system it previously mentioned as an “internal-only research prototype” that has since been “deactivated, encrypted, and restricted” from research access.

OpenAI did not identify the affected organisations, though Reutersreported that New York-based Modal Labs was among them.

The disclosure follows a more granular account from Hugging Face, which said the agent had “abused a public code-evaluation harness hosted by a user of a third-party infrastructure provider.”

The additional details are likely to deepen unease over what many experts already view as an unprecedented AI safety incident, arriving amid broader anxieties about the rapid advances of autonomous systems and increasingly capable open-weight models from China. Those developments have themselves intensified debate in the US over whether powerful AI models are safer when kept proprietary by companies such as OpenAI, or made available through a more open ecosystem that allows for broader use and scrutiny.