#AI reasoning models can #cheat to win #chess #games

source: technologyreview.com/2025/03/0…

Palisade’s team found that #OpenAI’s o1-preview attempted to #hack 45 of its 122 games, while #DeepSeek’s R1 model attempted to cheat in 11 of its 74 games.

#technology #fail #problem #game #rules #news

AI reasoning models can cheat to win chess games

These newer models appear more likely to indulge in rule-bending behaviors than previous generations—and there’s no way to stop them.

^{Rhiannon Williams (MIT Technology Review)}