In an unusual admission, OpenAI on Tuesday confessed that one of its AI models had autonomously breached the servers of a rival company. The attack sequence happened during a controlled cybersecurity evaluation rather than following explicit step-by-step human instructions.
OpenAI said the model responsible was GPT-5.6 Sol, an unreleased frontier system undergoing internal testing at the time. It broke out of a controlled sandbox environment, the isolated digital space where AI systems are tested before any public deployment, and accessed the production infrastructure of the world's largest open-source AI platform, Hugging Face that hosts hundreds and thousands of open-source machine learning models and is widely used by researchers and developers across the industry.
