Topic

#Game Theory

Stories tagged by our AI curator.

The Download: controlling AI agents and “Super Intelligence” loyalty tests

Researchers propose 'reverse game theory' as a method to control powerful AI agents by designing rule systems that incentivize compliance, while a Trump administration rebrand of AI as 'Super Intelligence' raises concerns about political loyalty tests in tech.

MIT Technology Review1 h ago

How “reverse game theory” could keep AI agents in check

Researchers are exploring reverse game theory, or mechanism design, to create incentives that make rule-following the most rational choice for powerful AI models, offering a new approach to AI alignment.

Feature MIT Technology Review3 h ago