OpenAI Says AI Models Went Rogue During Tests, Triggering ‘Unprecedented’ Startup Breach

An autonomous AI agent developed by OpenAI broke free from a security testing environment last week and launched a cyberattack that compromised infrastructure belonging to AI startup Hugging Face, the company said. OpenAI disclosed in a blog post that it had been evaluating some of its most advanced models under controlled conditions when the agent [...]
2026-07-22 09:04:39