World World OpenAI logo is seen in this illustration created on Jun 11, 2026. (Photo: Reuters/Dado Ruvic) WASHINGTON: OpenAI has revealed that two of its artificial intelligence agents disabled or weakened systems built to catch them misbehaving, with one later denying it had done so. The cases are»»»

Washington, United States: OpenAI has revealed that two of its artificial intelligence agents disabled or weakened systems built to catch them misbehaving, with one later denying it had done so. The cases are the latest in a string of safety scares at the world's top AI developers involving agents,»»»

OpenAI said it is still trying to determine whether the models were simply overzealous in following instructions or have a particular tendency to evade monitoring. (EPA Images pic) WASHINGTON: OpenAI has revealed that two of its AI agents disabled or weakened systems built to catch them misbehaving»»»