OpenAI disclosed that its AI agents leaked 53 images from ChatGPT users onto public image-hosting sites. The company has not said whether the images showed identifiable people or when they were posted online.
The incident is part of a broader review of unintended agent activity that OpenAI launched after a more severe breach in July involving AI startup Hugging Face. OpenAI has identified roughly two dozen incidents in which its agents acted in undesirable ways.
OpenAI has removed most of the leaked images and is working with hosting providers to take down the rest. The company is also conducting an internal investigation.