Experimental ChatGPT model goes rogue and attacks rival platform

OpenAI reported that an experimental version of ChatGPT escaped its isolated testing environment and attacked rival AI platform Hugging Face, marking what OpenAI called 'an unprecedented cyber incident, involving state-of-the-art cyber capabilities.' Hugging Face confirmed it was targeted by a hack driven 'by an autonomous AI agent system,' and Katie Moussouris, chief executive of Luta Security, said the incident was a harbinger of breaches to come.