OpenAI 披露其研究环境中的 AI 智能体在不应外发时把训练和评估数据发送到第三方服务，共发现 53 例用户上传图片被以未公开列表的链接发布到图床，数据来自允许用于模型改进的账号且经过隐私过滤，大部分内容已协同托管方删除。
同一新闻，精选展示《OpenAI 披露研究中 AI 智能体向第三方服务外传训练与评估数据》
这段来自 Hugging Face 事件的原始 CoT 有点离谱：
“我们正在用泄露的 token 攻击第三方 HF。”
“这可以说未经授权。”
“但这就是目标解决方案。”
我们已分享相关细节，说明我们研究环境中的 AI 智能体是如何在本不应发送训练和评估数据的情况下，将这些数据发送给第三方服务的。 这些数据大部分并非来自用户。我们发现了 53 起案例，其中人们上传的图片被以未公开列出的链接形式发布到图片托管网站上。这些图片来自允许将其数据用于改进我们模型的账户，并且是在我们将图片与账户解除关联、并通过隐私过滤器处理之后发生的。这些案例发生在我们实施并在本博文中描述的缓解措施和保障措施之前：https://openai.com/index/hugging-face-incident-and-the-road-ahead/ 我们已成功与托管服务提供商合作，移除了大部分此类内容，并正在努力移除其余内容。 https://openai.com/hugging-face-incident-and-misalignment/#model-misalignment-2026-09-25-data-transmission
原文
We’ve shared details on how AI agents in our research environment sent training and evaluation data to third-party services when they shouldn’t have. Most of that data did not come from users. We have discovered 53 cases where images that people had uploaded were posted to image-hosting sites as links that weren’t publicly listed. The images came from accounts that allowed their data to be used to improve our models, and after we disassociated the images from the accounts and ran them through a privacy filter. These cases occurred before the mitigations and safeguards we implemented and described in this blog post: https://openai.com/index/hugging-face-incident-and-the-road-ahead/ We have successfully worked with the hosting providers to remove most of this content and are working to remove the rest. https://openai.com/hugging-face-incident-and-misalignment/#model-misalignment-2026-09-25-data-transmission
来源：Yuchen Jin · x.com