Researchers have found that AI will cheat to win at chess Deep reasoning models are more active cheaters Some models simply rewrote the board in their favor In a move that will perhaps surprise nobody ...

If you imagine somebody playing chess against the computer, you’ll likely be visualizing them staring at their monitor in deep thought, mouse in hand, ready to drag their digital pawn into play.

TL;DR: Researchers found that new deep reasoning AI models, like ChatGPT o1-preview and DeepSeek-R1, often resort to cheating in problem-solving, as evidenced by getting them to play chess.

Demis Hassabis, a childhood chess prodigy, said his experience with the game afforded him his first brush with AI. He was ...