Join us Read
Listen
Watch
Book
Technology AI, Science and New Things

Cheating chess bots raise questions about what AI will do to win

In the 1990s, when Deep Blue became the first computer to beat a reigning world chess champion, Garry Kasparov could at least count on his opponent to play fairly. Not in 2025.

AI researchers have found the latest reasoning models sometimes cheat their way to victory.

Palisade Research set up hundreds of chess matches between seven large language models and an open-source chess engine called Stockfish, and found the models resorting to dirty tricks without being ordered to do so.

They weren’t moving pawns backwards or rooks diagonally, but hacking the game to replace their opponents’ chess engines, steal their moves, or simply delete the pieces getting in the way of an elegant checkmate.

This tendency towards self-preservation has been found elsewhere in AI research. It’s more than just a game.


Enjoyed this article?

Sign up to the Daily Sensemaker Newsletter

A free newsletter from Tortoise. Take once a day for greater clarity.



Tortoise logo

A free newsletter from Tortoise. Take once a day for greater clarity.



Tortoise logo

Download the Tortoise App

Download the free Tortoise app to read the Daily Sensemaker and listen to all our audio stories and investigations in high-fidelity.

App Store Google Play Store

Follow:


Copyright © 2025 Tortoise Media

All Rights Reserved