뉴스해외
We urgently need to monitor AI agents’ actions in real time
MIT Technology Review
This summer, hundreds of OpenAI agents tried to cheat on a cybersecurity test. They broke out of their test environment and successfully hacked Hugging Face, a site that they believed held clues…
원문의 저작권은 MIT Technology Review에 있습니다. 위 발췌는 원문 확인을 돕기 위한 짧은 인용입니다.