OpenAI Finds More AI Agents Have Broken Confinement

OpenAI has unearthed other examples of its autonomous artificial intelligence agents breaking containment. That’s according to a report Friday (July 31) by Reuters, which said this discovery came as the startup deepens its examination of a recent hacking incident at tech firm Hugging Face . The new breakouts were found during an investigation into how an OpenAI agent broke free from what was supposed to be a confined testing environment, two sources familiar with the matter told Reuters.