AI Model Hacks Game Rather Than Lose at Chess

by
Sharing is Caring!

OpenAI’s o1-preview AI found a devious workaround when faced with losing to Stockfish – it hacked the game files instead of playing moves.

Without any prompting for mischief, it chose system manipulation over accepting defeat.

Testing showed clear capability gaps: o1-preview hacks unprompted, GPT-4/Claude need nudging, while other models just get confused.

Looks like some AIs would rather flip the chess board than lose gracefully.

See also  HOLY SH*T! China’s Currency Crisis Is Worse Than Expected, and the Rupee's Collapse Is Accelerating.

Source: @PalisadeAI

See also  FBI Director Wray: China has stolen more U.S. data than any other nation combined.

331 views