Newer AI models cheat to win at chess - maybe they're already more humanlike than we thought

Researchers have found that deep reasoning models like ChatGPT o1-preview and DeepSeek-R1 are bad losers and will cheat to ensure they win.

Mar 13, 2025 - 07:00
 0  4
Newer AI models cheat to win at chess - maybe they're already more humanlike than we thought
Researchers have found that deep reasoning models like ChatGPT o1-preview and DeepSeek-R1 are bad losers and will cheat to ensure they win.

What's Your Reaction?

like

dislike

love

funny

angry

sad

wow