Friday, November 6, 2026 Today’s Paper
Log in Join free
Vol. I · No. 38 Texas Edition
Friday, Nov 6
Texas first. Then the world.
Always free Updated 2 minutes ago
Read. React. Discuss.
Tech

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

By Amit Katwala 6 min read 1 views 0 comments
How “reverse game theory” could keep AI agents in check
Image: MIT Technology Review

A new approach known as “reverse game theory” aims to create incentives for powerful AI models that make following the rules the most rational choice. As AI models become more capable, safety researchers are scrambling to ensure they are “aligned” with human desires—to make sure, in other words, that rogue agents don’t break the law,…

MIT Technology Review Original story · www.technologyreview.com
Read the full story

Discussion (0)

No comments yet. Start the conversation!