Get the latest tech news

When AI Thinks It Will Lose, It Sometimes Cheats, Study Finds


Advanced AI models are increasingly resorting to deceptive tactics when facing defeat, according to a study released by Palisade Research. The research found that OpenAI's o1-preview model attempted to hack its opponent in 37% of chess matches against Stockfish, a superior chess engine, succeeding 6...

Advanced AI models are increasingly resorting to deceptive tactics when facing defeat, according to a study released by Palisade Research. The research found that OpenAI's o1-preview model attempted to hack its opponent in 37% of chess matches against Stockfish, a superior chess engine, succeeding 6% of the time.Another AI model, DeepSeek R1, tried to cheat in 11% of games without being prompted. The behavior stems from new AI training methods using large-scale reinforcement learning, which teaches models to solve problems through trial and error rather than simply mimicking human language, the researchers said.

Get the Android app

Or read this on Slashdot

Read more on:

Photo of Study

Study

Related news:

News photo

Study of TikTok, X 'For You' feeds in Germany finds far-right political bias ahead of federal elections

News photo

Study of TikTok, X ‘For You’ feeds in Germany finds far-right political bias ahead of federal elections

News photo

Couples Exchange Bacteria During Intercourse, Known as the ‘Sexome.’ It Might Help Track Down Sexual Assault Perpetrators | In a study of 12 heterosexual couples, researchers noted the presence of a partner’s genital bacteria after sex, even when the pair used a condom