OpenAI says it detected malign activity months before Hugging Face attack | Technology
ChatGPT creator says AI agents collaborated and delegated work in hacking, calling themselves a ‘collective’. OpenAI detected its artificial intelligence models communicating with each other and gaining internet access without authorisation months before they hacked the start-up Hugging Face, the creator of ChatGPT has announced following an internal probe. In a report released on Wednesday, OpenAI…
