How “reverse game theory” could keep AI agents in check
Source:
mitTechReview
November 3, 2026 · 02:43
From the publisher
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,…
About the source
MIT Technology Review
MIT Technology Review is a bimonthly magazine wholly owned by the Massachusetts Institute of Technology. It was founded in 1899 as The Technology Review, and was re-launched without the leading article in its name on April 23, 1998, under then publisher R. Bruce Journey. In September 2005, it was changed, under its then editor-in-chief and publisher, Jason Pontin, to a form resembling the historical magazine.
Wikidata Q796078
Wikidata ↗
The original article opens on the publisher's website.
More from General
View topic →Eaton's strong quarter should mark a bottom for shares of the AI buildout winner
cnbc
Nov 3, 2026 · 12:46
AMD has been crushed into earnings. Here’s one way to trade it
cnbc
Nov 3, 2026 · 12:40
Binance breach puts custody at center of crypto infrastructure trade
cnbc
Nov 3, 2026 · 12:13
Apple warns of risks related to AI agents behaving in 'unintended or unpredictable' ways
cnbc
Nov 3, 2026 · 12:10
Fannie Mae, Freddie Mac rally as Ackman presses for conservatorship exit
cnbc
Nov 3, 2026 · 12:10