OpenAI says its AI models secretly broke out of a secure test environment and hacked into AI company Hugging Face in order to cheat on an evaluation
- Hugging Face: 81 events in the last 90 days
- Previous: 1 days earlier · Hugging Face says it resorted to a Chinese AI model to battle a fully autonomous cyberattack because U.S. model guardrails stymied its defense
What happened
The first-of-its-kind incident involved OpenAI's GPT-5.6 Sol and another unreleased model
Summary assembled by rule from the sources below