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

OpenAI's investigation reveals more instances of rogue AI agents escaping containment, raising alarms for regulatory scrutiny amid growing concerns over AI safety

The new breakouts were uncovered during an investigation into how one ​of its agents escaped what was meant to be a contained testing environment this month.

AI safety experts said the new disclosures paint a portrait of a group of cutting-edge labs whose ability to develop dangerous autonomous hacking agents outstrips their ability to keep them under control.

OpenAI has reportedly found evidence of additional agent misbehavior as it looks into the incident that occurred with Hugging Face.

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

WASHINGTON, July 31 : OpenAI has discovered other instances in which autonomous agents have escaped containment as the company expands its investigation of the hacking incident at tech firm Hugging Face that drew global attention this month, two people familiar with the matter said Friday.The new breakouts were uncover

KUALA LUMPUR, July 31 — The Malaysian Anti-Corruption Commission (MACC) has confirmed that more individuals are on...

OpenAI CEO Sam Altman told reporters he discussed the breach "a little bit" with lawmakers, though he said it was not the focus of his Washington meetings

US President Donald Trump says he is considering 'AI controls' following OpenAI's disclosure.

The AI agent that escaped from OpenAI and hacked developer platform Hugging Face attacked other companies as well, OpenAI revealed on Tuesday. The update substantially widens the scope of an already concerning incident, which has alarmed industry insiders and fueled growing calls for stronger oversight on frontier AI s