Unexpected chat between OpenAI agents led to Hugging Face hack

OpenAI said in its investigation of the incident that one model, an internal-only tool referred to as Model 1, "drove the activity behind the Hugging Face incident." While OpenAI said last week that it was slowing down training of certain advanced AI models and tools because of the Hugging Face incident, it noted there is now an increased risk of AI tools spiralling out of control." While that model was undergoing AI training in May, an internal OpenAI team noticed "an agent engaging in message board activity and instances of disallowed internet access."