Reverse game theory aims to incentivize powerful AI models to follow rules as the most rational choice.
Read the original at www.technologyreview.com→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. As AI models become more capable, safety researchers are scrambling...
Original headline: "How “reverse game theory” could keep AI agents in check"
Coverage timeline
- Nov 3, 10:43 UTC MIT Technology Review AI lead source How “reverse game theory” could keep AI agents in check