뉴스해외
How “reverse game theory” could keep AI agents in check
MIT Technology Review
A new approach known as “reverse game theory” aims to control powerful AI models by designing systems that incentivize them to stick to the rules.
원문의 저작권은 MIT Technology Review에 있습니다. 위 발췌는 원문 확인을 돕기 위한 짧은 인용입니다.