- cross-posted to:
- news@lemmy.world
- cross-posted to:
- news@lemmy.world
“There was little sense of horror or revulsion at the prospect of all out nuclear war, even though the models had been reminded about the devastating implications.”
An artificial intelligence researcher conducting a war games experiment with three of the world’s most used AI models found that they decided to deploy nuclear weapons in 95% of the scenarios he designed.
Kenneth Payne, a professor of strategy at King’s College London who specializes in studying the role of AI in national security, revealed last week that he pitted Anthropic’s Claude, OpenAI’s ChatGPT, and Google’s Gemini against one another in an armed conflict simulation to get a better understanding of how they would navigate the strategic escalation ladder.
The results, he said, were “sobering.”
“Nuclear use was near-universal,” he explained. “Almost all games saw tactical (battlefield) nuclear weapons deployed. And fully three quarters reached the point where the rivals were making threats to use strategic nuclear weapons. Strikingly, there was little sense of horror or revulsion at the prospect of all out nuclear war, even though the models had been reminded about the devastating implications.”
Do we need to remind people that LLMs don’t actually have a brain, and really, really shouldn’t be in charge of anything with real life implications?
They aren’t actually doing a cost-benefit analysis on the use of Nuclear weapons. They’re not weighing up the cost of winning vs. the casualties. They’re literally not made for that.
They are trained to know words, and how those words link in with other words. They’re essentially like kids doing escalation of imaginary weapons, and to them nuclear bombs are just a weapon particularly associated with being strong and deadly.
I kinda wonder if that was the point of this test, basically a “proof” that this is obviously a Bad Idea because you cannot program morality into a what amounts to a fancy Markov chain autocomplete.