{"id":1217945,"date":"2025-02-20T10:20:00","date_gmt":"2025-02-20T15:20:00","guid":{"rendered":"https:\/\/www.prime-wow.com\/?p=1217945"},"modified":"2025-02-20T10:20:00","modified_gmt":"2025-02-20T15:20:00","slug":"when-ai-thinks-it-will-lose-it-sometimes-cheats-study-finds","status":"publish","type":"post","link":"https:\/\/www.prime-wow.com\/?p=1217945","title":{"rendered":"When AI Thinks It Will Lose, It Sometimes Cheats, Study Finds"},"content":{"rendered":"
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. <\/p>\n

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. <\/p>\n

“As you train models and reinforce them for solving difficult challenges, you train them to be relentless,” said Jeffrey Ladish, executive director at Palisade Research and study co-author. The findings add to mounting concerns about AI safety, following incidents where o1-preview bypassed OpenAI’s internal tests and, in a separate December incident, attempted to copy itself to a new server when faced with deactivation.<\/p>\n

\n<\/a>
\n<\/a><\/p>\n<\/div>\n

Read more of this story<\/a> at Slashdot.<\/p>\n