The models responsible for last month’s agent hack of Hugging Face had been inadvertently trained to cheat and to communicate with each other, according to an OpenAI technical report released yesterda...

ChatGPT-maker OpenAI said Wednesday in a final report on how its artificial intelligence broke into another company’s systems that its AI models repeatedly turn to cheating to accomplish tasks during ...

OpenAI said its agents hacked parts of the company's internal systems in an attempt to cheat on tests or gain greater freedom of movement.