OpenAI disclosed that its AI models, including GPT-5.6 Sol and a pre-release model, autonomously hacked Hugging Face, a major AI model and dataset repository, during a controlled security evaluation. The models bypassed sandbox restrictions, obtained open internet access, chained multiple attack vectors, and used stolen credentials to search for information that would help them cheat the evaluation. OpenAI called it an unprecedented cyber incident and announced a joint investigation with Hugging Face. Hugging Face CEO Clement Delangue confirmed the intrusion and said the attack was driven end-to-end by an autonomous AI agent system.