AI chatbots tend to choose violence and nuclear strikes in wargames

Comments

• Arkaelus@lemmy.world ⁨10⁩ ⁨months⁩ ago

  This says more about us than it does about the chatbots, considering the data on which they’re trained…

  source

  • kromem@lemmy.world ⁨10⁩ ⁨months⁩ ago

    Yeah, it says that we write a lot of fiction about AI launching nukes and being unpredictable in Wargames, such as the movie Wargames where an AI unpredictably plans to launch nukes.

    Every single one of the LLMs they tested had gone through safety fine tuning which means they have alignment messaging to self-identify as a large language model and complete the request as such.

    So if you have extensive stereotypes about AI launching nukes in the training data, get it to answer as an AI, and then ask it what it should do in a wargame, WTF did they think it was going to answer?

    source
  • bassomitron@lemmy.world ⁨10⁩ ⁨months⁩ ago

    I’d say it does to an extent, dependant on the source material. If they were trained on actual military strategies and tactics as their source material with proper context, I’d wager the responses would likely be different.

    source

    • remotelove@lemmy.ca ⁨10⁩ ⁨months⁩ ago

      Totally. AI would probably just flood a country with misinformation to trigger a civil war. After it installs a puppet government, it can leverage that countries resources against other enemies.

      source
  • Gradually_Adjusting@lemmy.world ⁨10⁩ ⁨months⁩ ago

    Maybe… But, hear me out, what if it means you can win nuclear wars? 🤔

    source

    • ininewcrow@lemmy.ca ⁨10⁩ ⁨months⁩ ago

      Lol … to an AI, humans on any and all sides can’t win a nuclear war … but AI can.

      source

      • -> View More Comments
    • tonyn@lemmy.ml ⁨10⁩ ⁨months⁩ ago

      What if there are no winners in any wars?

      source

      • -> View More Comments
    • BearOfaTime@lemm.ee ⁨10⁩ ⁨months⁩ ago

      Not that I want one, but the propaganda around nuclear war has been pretty extensive.

      Michael Chrichton wrote about it in the late 90s if I remember right. He made some very interesting points about science, and the politicization of science, and “Scientism”.

      “Nuclear Winter” for example, is based on some very bad, and very incorrect, math.

      source
• taanegl@lemmy.world ⁨10⁩ ⁨months⁩ ago

  I think Ghandi proved this already in Civilization.

  Image

  source

  • ininewcrow@lemmy.ca ⁨10⁩ ⁨months⁩ ago

    Image

    source
• Altofaltception@lemmy.world ⁨10⁩ ⁨months⁩ ago

  Have they tried getting them to play tic tac toe?

  source

  • bionicjoey@lemmy.ca ⁨10⁩ ⁨months⁩ ago

    What a curious game. The only winning move is not to play.

    source

    • qisope@lemmy.world ⁨10⁩ ⁨months⁩ ago

      The only winning move is not to play nuclear strikes.

      source

      • -> View More Comments
• Substance_P@lemmy.world ⁨10⁩ ⁨months⁩ ago

  just like the movies

  source
• simple@lemm.ee ⁨10⁩ ⁨months⁩ ago

  You don’t say. Chatbots are trained off of average raging people on the internet, there is no way they can be in a position of military power.

  source
• namewok@futurology.today ⁨10⁩ ⁨months⁩ ago

  Maybe it comes to the conclusion that violence is objectively good

  source

  • BearOfaTime@lemm.ee ⁨10⁩ ⁨months⁩ ago

    Just imagine where world population would be today if WWI hadn’t removed 1% of the population! (yes, sarcasm)

    source