- cross-posted to:
- technology@lemmit.online
- cross-posted to:
- technology@lemmit.online
AI chatbots tend to choose violence and nuclear strikes in wargames::undefined
You must log in or register to comment.
This says more about us than it does about the chatbots, considering the data on which they’re trained…
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?
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.
Totally. Properly trained 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.
Maybe… But, hear me out, what if it means you can win nuclear wars? 🤔
What if there are no winners in any wars?
Let’s think here… I’ve always heard history is written by the victors, which logically implies historians are the most dangerous people on the planet and ought to be detained. 🧐
Lol … to an AI, humans on any and all sides can’t win a nuclear war … but AI can.
I hope it’s obvious I was being hugely tongue in cheek
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, the politicization of science, and “Scientism”.
“Nuclear Winter” for example, is based on some very bad, and very incorrect, math.
I think Ghandi proved this already in Civilization.
Have they tried getting them to play tic tac toe?
What a curious game. The only winning move is not to play.
The only winning move is
not to playnuclear strikes.Flips over the game table with the pressure wave of a 20 megaton air detonated nuclear explosion
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.
Maybe it comes to the conclusion that violence is objectively good
Just imagine where world population would be today if WWI hadn’t removed 1% of the population! (yes, sarcasm)
The reality is violence is part of the human condition, and it’s been an effective tool throughout time, or else people wouldn’t use it.
Also part of the human condition is trying to teach each new successive generation to be better than ourselves. We each only get ~80 years, and those first 20 are crucial.
