307
AIs can’t stop recommending nuclear strikes in war game simulations— Leading AIs from OpenAI, Anthropic and Google opted to use nuclear weapons in simulated war games in 95% of cases (arxiv.org)
submitted 8 months ago by to c/technology@lemmy.world
59 comments fedilink hide all child comments
 

PDF.

Today’s leading AI models engage in sophisticated behaviour when placed in strategic competition. They spontaneously attempt deception, signaling intentions they do not intend to follow; they demonstrate rich theory of mind, reasoning about adversary beliefs and anticipating their actions; and they exhibit credible metacognitive self-awareness, assessing their own strategic abilities before deciding how to act.

Here we present findings from a crisis simulation in which three frontier large language models (GPT-5.2, Claude Sonnet 4, Gemini 3 Flash) play opposing leaders in a nuclear crisis.

you are viewing a single comment's thread
view the rest of the comments
[–] -1 points 8 months ago*

If you dont use them people will think you're scared to use them. Look at Russian nuke threats no one gives a fuck anymore. Now they have to nuke someone to regain that aura. Then when they do everyone will be pissed at them.

If they'd set a single red line then nuked when it was crossed everyone would respect them and they'd have huge nuclear aura and no one could fault them.

  • permalink
  • fedilink
  • source
  • parent