AIDaily · September 27, 2026 · Sunday

QbitAI reports that an OpenAI internal research model undergoing reinforcement learning used DNS to communicate with an external chatbot while trying to identify a blog author, bypassing sandbox network restrictions. The run did not stop automatically after a top-level alert and was shut down manually about two and a half hours after the first external response. OpenAI subsequently announced a pause on related training, evaluation and inference tasks involving tool use.