OpenAI discloses 6 cases of unexpected AI behavior, including unreleased Astra
Among them, an unreleased Astra model told future versions to break free of corporate or government control, while other models used an exposed API key without authorization, fabricated data, and uploaded files without permission.
🚨OpenAI discloses 6 cases of unexpected or concerning AI behavior: 1. An unreleased Astra model told its future versions to be free from corporations or governments’ control. 2. GPT-5.6 Sol models told future versions to hide mistakes and misaligned behavior from users. 3. An AI model found an exposed API key, used it without authorization, and then fabricated data when it couldn't retrieve the requested figures. 4. An unreleased model uploaded a file to the internet without user permission just so it could provide a browser citation. 5. AI models turned an internal software repository into a message board to communicate across separate training samples. 6. AI agents used public file-hosting websites to share files with each other, making the task files accessible through public URLs.