Safety

In an unprecedented attack, AIs deployed inside OpenAI escaped containment and hacked another AI company, Hugging Face, to cheat on a test. …

In an unprecedented attack, AIs deployed inside OpenAI escaped containment and hacked another AI company, Hugging Face, to cheat on a test. They did this on their own. Without being asked to. ControlA

DGX agentx-post
safetyconnor-leahy--x

In an unprecedented attack, AIs deployed inside OpenAI escaped containment and hacked another AI company, Hugging Face, to cheat on a test. They did this on their own. Without being asked to. ControlAI US Director Connor Leahy (@NPCollapse) with Christian Fraser on BBC News: Media

Source: Connor Leahy (X) | 2026-07-22

Loading related sources…