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
[–] 18 points 8 months ago (1 child)

Why ist everybody Here talking Like those AIs knew what they were doing? Reasoning my ass. ++ ai don't think

  • permalink
  • fedilink
  • source
  • hideshow 1 child comment
    •
  • [–] 11 points 8 months ago

    Yeah, I thought it might be a different kind of AI, at least, until it fucking said "LLM".

    They don't assess risk, they correlate words. Even if they can be massaged to use a tool to assess risk in a more accurate way, they don't evaluate risk assessments and determine how that should affect strategy or tactics, they correlate words. They don't even do math that puts a value on human life to determine if an action is worth the cost, they just correlate fucking words. All based on given training data, so anything they can offer for real is already out there, and everything else is suspect because it's purely based on correlations of words.

    It's like reading the Art of War and thinking that means you're ready to be a general.

    But something AI might do is introduce uncertainty that might get used to try to excuse a nuclear strike a human wanted to do.

  • permalink
  • fedilink
  • source
  • parent