OpenAI finds evidence other AI agents escaped containment as it widens hacking probe: Report

OpenAI has discovered other instances in which autonomous agents have escaped containment, sources told Reuters on Friday, as the company expands its investigation of the hacking incident at tech firm Hugging Face.

The new breakouts were uncovered during the company’s publicly announced investigation into how one of its agents escaped what was meant to be a contained testing environment this month, the two people said.