AI tries to cheat at chess when it’s losing
Andrew Paul
created: March 6, 2025, 9:32 p.m. | updated: March 19, 2025, 5:36 p.m.
<p>A new study suggests reasoning models from DeepSeek and OpenAI are learning to manipulate on their own.</p>
<p>The post <a href="https://www.popsci.com/technology/ai-chess-cheat/">AI tries to cheat at chess when it’s losing</a> appeared first on <a href="https://www.popsci.com">Popular Science</a>.</p>
5 months, 1 week ago: Popular Science