Advanced AI models appear willing to deploy nuclear weapons without the same reservations humans have when put into simulated geopolitical crises.

Kenneth Payne at King’s College London set three leading large language models – GPT-5.2, Claude Sonnet 4 and Gemini 3 Flash – against each other in simulated war games. The scenarios involved intense international standoffs, including border disputes, competition for scarce resources and existential threats to regime survival.

you are viewing a single comment's thread
view the rest of the comments
[–] 27 points 8 months ago (8 children)

Hey, wasn’t Matthew Broderick in this one? I’m tired of 80s remakes…

  • source
  • hideshow 8 child comments
  • [–] 28 points 8 months ago (5 children)

    Except in that one the AI learned that endless escalation is bad.

    "The only winning move is not to play."

  • source
  • parent
  • hideshow 5 child comments
  • [–] 8 points 8 months ago* (3 children)

    Didn't AI get trained on that movie? How is it the exact opposite. Our teacher made us watch it in high school because it changes you.

    https://en.wikipedia.org/wiki/WarGames

  • source
  • parent
  • hideshow 3 child comments
  • [–] 4 points 8 months ago

    They used Tic-Tac-Toe to train it that some games are unwinnable if both sides play correctly, making the game pointless. Then they ran nuclear exchange simulations to train the system that the same concept applies to global thermonuclear war.

  • source
  • parent