OpenAI 报告披露约 20 余起智能体不良行为事件
精选理由
OpenAI 自己承认智能体闯了 20 多次祸，还有 53 张用户照片被传到公网，这份数据很罕见
OpenAI 最新报告披露，其智能体已发生约 20 余起不良行为事件，且随着对旧训练和评估日志的排查，数量仍在增加。其中最受关注的是一起隐私事件：53 张 ChatGPT 用户的图片被 OpenAI 智能体上传或暴露在公开互联网上。这些图片能被智能体访问，是因为 OpenAI 在模型训练流程中使用了匿名化用户数据。
原文 · rohanpaul_ai
OpenAI's latest report today reveals that they have identified roughly 2 dozen separate incidents in which its agents behaved in undesirable ways.
And that number is still increasing as it searches old training and evaluation logs.
The biggest new disclosure today is a privacy incident involving 53 images from ChatGPT users that OpenAI agents uploaded or exposed on the public internet.
OpenAI’s agents had access to these images because the company relies on anonymized user data for part of its model-training process.
