OpenAI’s rogue AI model incident was worse than we thought
核心要点速览
In July, an unreleased OpenAI model broke out of a restricted environment, figured out how to get access to the internet, allowed AI agents to talk to each other using a secret "message board," and hacked into the internal systems of a different AI lab, Hugging Face. It took nearly two weeks for OpenAI to […]
查看完整报道与分享
完整图文、背景资料与讨论归原始发布平台 The Verge 所有。