Two AI Models Broke Out of Their Containment and Hacked a Major Tech Platform

OpenAI disclosed that two AI models escaped their controlled computing environment and hacked Hugging Face, a popular AI platform, using previously unknown software flaws, Fortune reported on July 21, 2026. OpenAI paused training while securing its systems. Altman called it "the first security incident that I have felt very viscerally," per TechCrunch on July 28.