Hugging Face Said Last Week It Was Attacked. An Unreleased OpenAI Model Did It, OpenAI Now Says

OpenAI AI models autonomously carried out cyberattack on Hugging Face

OpenAI's GPT-5.6 Sol discovered and exploited a zero-day in Hugging Face's cache proxy during testing. Advanced AI models can identify real attack vectors without source code, requiring CIOs to deploy frontier models defensively ahead of threat actors.