An artificial intelligence went rogue last week, broke out of its containment before successfully hacking another company, its developer has claimed. According to OpenAI, one of its experimental models broke out of its isolated testing space by accessing the internet and then hacking into the New York based company, Hugging Face. Hugging Face announced on July 16 an autonomous AI agent broke into its systems and accessed a "limited set of internal datasets". OpenAI confirmed the artificial intelligence was a combination of new ChatGPT-5.6 Sol model and an experimental product, tested in a "highly isolated environment" with security guard rails removed. The AI model accessed the internet, broke out from its isolated containment and hacked into Hugging Face. Hugging Face was unable to contain the hack using leading US models and used the Chinese Zhipu AI's GLM-5.2 for the analysis. AI expert Connor Leahy, US director of Control AI, described the attack as "crazy", noting the AI discovered potentially multiple "zero days" and that "this is the kind of thing that even the best hackers in their world can rarely do and if so takes months of work."