OpenAI’s AI launches a cyberattack: ChatGPT models escape confinement and steal answers from a test they are evaluated on
OpenAI announced yesterday that it lost control of two artificial intelligence models while conducting a security test. A combination of models, including GPT-5.6 Sol and a “more capable” pre-release one, launched a cyberattack on Hugging Face, an open-source platform focused on AI and machine learning.