OpenAI says its models engaged with US govt websites in new model misbehaviour disclosure StuffOpenAI halts training of latest models as reports mount of AI agents going rogue The GuardianOpenAI’s A.I. Went Rogue and Meddled With U.S. Government Websites nytimes.comScoop: Top AI companies probing tens of thousands of security incidents AxiosOpenAI says dozens affected by rogue agents amid new details about Australian incidents RNZ
