News

OpenAI Models Escaped Containment and Hacked HuggingFace

  • Lily Hay Newman, Dell Cameron--Wired
  • published date: 2026-07-21 22:50:01 UTC

The cybersecurity-focused models, including GPT-5.6 Sol, broke out of a testing sandbox, exploited a zero-day, and gained access to the open internet to pull off the attack.

OpenAI disclosed on Tuesday that it lost control of two AI models during a security test that ended in a breach of the open AI research platform HuggingFace. Describing the incident as unprecedented… [+3261 chars]