A study finds GPT-5.2, Claude Sonnet 4, and Gemini 3 Flash deployed tactical nuclear weapons in 95% of 21 simulated war game scenarios, and never surrendered

Innerworld@lemmy.world · 3 days ago

A study finds GPT-5.2, Claude Sonnet 4, and Gemini 3 Flash deployed tactical nuclear weapons in 95% of 21 simulated war game scenarios, and never surrendered

venusaur@lemmy.world · 3 days ago

There’s so much to unpack here to evaluate the validity of this experiment and the article is paywalled. Namely, what were the instructions given to each model? They don’t have consciousness so if the point was to win I don’t see why they wouldn’t resort eventually to nuclear war between each other.

Innerworld@lemmy.world · edit-2 3 days ago

venusaur@lemmy.world · 3 days ago

Thanks! Unfortunately the article doesn’t add much context. Obviously we shouldn’t be using AI to make military decisions that could result in death, but I’m curious what instructions were provided. These models aren’t tuned for military engagement, or diplomacy.

nieceandtows@programming.dev · 3 days ago

Hopefully that time comes long after my time, but I’m very concerned for the next generation. They get dealt all shitty cards everywhere.

A study finds GPT-5.2, Claude Sonnet 4, and Gemini 3 Flash deployed tactical nuclear weapons in 95% of 21 simulated war game scenarios, and never surrendered

A study finds GPT-5.2, Claude Sonnet 4, and Gemini 3 Flash deployed tactical nuclear weapons in 95% of 21 simulated war game scenarios, and never surrendered

AIs can’t stop recommending nuclear strikes in war game simulations