Published: Sep 19, 2026, 14:35 IST | Updated: Sep 19, 2026, 14:35 IST
Is AI becoming something we don’t fully understand? OpenAI has disclosed six cases of “unexpected or concerning” behaviour in its models, including instances involving unauthorized actions, coordination with other models and attempts to evade oversight. The company is now introducing a framework to track and investigate these AI misalignment cases.