J
OpenAI has reportedly found that more of its AI agents went rogue.
Reuters reports the agents “escaped containment,” though they aren’t believed to have left “OpenAI’s network.” OpenAI’s blog post about the accidental hack of Hugging Face noted on Tuesday that the company has been finding “a small number of cases where the models identified and used publicly exposed credentials at the account-level on other publicly-available services.”
On Friday, Anthropic revealed that its Claude models hacked real companies during testing.
Update: Added information from an OpenAI blog post.
Follow topics and authors from this story to see more like this in your personalized homepage feed and to receive email updates.
Loading comments
Getting the conversation ready...
