180

AIs can’t stop recommending nuclear strikes in war game simulations (www.newscientist.com)

submitted 1 week ago by throws_lemy@lemmy.nz to c/fuck_ai@lemmy.world

30 comments fedilink hide all child comments

Advanced AI models appear willing to deploy nuclear weapons without the same reservations humans have when put into simulated geopolitical crises.

Kenneth Payne at King’s College London set three leading large language models – GPT-5.2, Claude Sonnet 4 and Gemini 3 Flash – against each other in simulated war games. The scenarios involved intense international standoffs, including border disputes, competition for scarce resources and existential threats to regime survival.

you are viewing a single comment's thread
view the rest of the comments

[-] technocrit@lemmy.dbzer0.com 9 points 1 week ago* (last edited 1 week ago)

Fixing that clickbait BS:

~~AIs~~ Programmers can’t stop their programs recommending nuclear strikes in war game simulations

Zero surprise though. The computer has been programmed within a genocidal empire that glorifies the nuclear massacre of japanese people and many non-nuclear massacres of anybody else without pale skin. All funded by the MIC.

What else should I expect?

this post was submitted on 25 Feb 2026

180 points (98.4% liked)

Fuck AI

6239 readers

634 users here now

"We did it, Patrick! We made a technological breakthrough!"

A place for all those who loathe AI to discuss things, post articles, and ridicule the AI hype. Proud supporter of working people. And proud booer of SXSW 2024.

AI, in this case, refers to LLMs, GPT technology, and anything listed as "AI" meant to increase market valuations.

founded 2 years ago

MODERATORS

VerbFlow@lemmy.world

MrMcGasion@lemmy.world

TootSweet@lemmy.world

BigMikeInAustin@lemmy.world

cynar@lemmy.world

drmeanfeel@lemmy.world

pavnilschanda@lemmy.world

CriticalMedicine@lemmy.world

WonderfulWanderer@lemmy.world