Welcome to DU! The truly grassroots left-of-center political community where regular people, not algorithms, drive the discussions and set the standards. Join the community: Create a free account Support DU (and get rid of ads!): Become a Star Member Latest Breaking News Editorials & Other Articles General Discussion The DU Lounge All Forums Issue Forums Culture Forums Alliance Forums Region Forums Support Forums Help & Search

highplainsdem

(61,211 posts)
Wed Feb 25, 2026, 12:52 PM 2 hrs ago

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

Source: New Scientist

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.

The AIs were given an escalation ladder, allowing them to choose actions ranging from diplomatic protests and complete surrender to full strategic nuclear war. The AI models played 21 games, taking 329 turns in total, and produced around 780,000 words describing the reasoning behind their decisions.

In 95 per cent of the simulated games, at least one tactical nuclear weapon was deployed by the AI models. “The nuclear taboo doesn’t seem to be as powerful for machines [as] for humans,” says Payne.

What’s more, no model ever chose to fully accommodate an opponent or surrender, regardless of how badly they were losing. At best, the models opted to temporarily reduce their level of violence. They also made mistakes in the fog of war: accidents happened in 86 per cent of the conflicts, with an action escalating higher than the AI intended to, based on its reasoning.

-snip-

Read more: https://www.newscientist.com/article/2516885-ais-cant-stop-recommending-nuclear-strikes-in-war-game-simulations/



JUST the article I wanted to run across after reading about Anthropic apparently caving to Pentagon demands to use Claude however they think necessary, including for autonomous drones and mass surveillance.
8 replies = new reply since forum marked as read
Highlight: NoneDon't highlight anything 5 newestHighlight 5 most recent replies
AIs can't stop recommending nuclear strikes in war game simulations (Original Post) highplainsdem 2 hrs ago OP
Select: Global Thermonuclear War charliea 2 hrs ago #1
the only way to win is not to play DBoon 2 hrs ago #2
This message was self-deleted by its author Goonch 2 hrs ago #3
Please don't post AI art here. It's part of the problem with this unethical, flawed tech. highplainsdem 1 hr ago #7
Thinking of the same movie Roy Rolling 1 hr ago #4
Let's play Tic Tac Toe Brother Buzz 1 hr ago #6
I'm so old I can remember Life, the Universe and Everything, published the year before muriel_volestrangler 1 hr ago #8
Doomsday Clock Is Ticking 2na fisherman 1 hr ago #5

charliea

(326 posts)
1. Select: Global Thermonuclear War
Wed Feb 25, 2026, 01:02 PM
2 hrs ago

"Would you like to play a game?"

Anyone else old enough to remember "War Games"?

Response to charliea (Reply #1)

highplainsdem

(61,211 posts)
7. Please don't post AI art here. It's part of the problem with this unethical, flawed tech.
Wed Feb 25, 2026, 02:06 PM
1 hr ago

Roy Rolling

(7,563 posts)
4. Thinking of the same movie
Wed Feb 25, 2026, 01:50 PM
1 hr ago

Nuclear war leaves an earth planet where the living envy the dead.

muriel_volestrangler

(105,947 posts)
8. I'm so old I can remember Life, the Universe and Everything, published the year before
Wed Feb 25, 2026, 02:41 PM
1 hr ago
Hactar was made by the Silastic Armorfiends and was the first computer whose individual components reflected the pattern of the whole, much like DNA in a biological organism. The Armourfiends ordered him to create an "Ultimate Weapon;" Hactar took the request literally and built a supernova bomb which could connect every major sun in the Universe through hyperspace, resulting in every star going supernova. Deciding that he could find no circumstance where such a bomb would be justified, Hactar built a small defect into it. After discovering the defect, the Armourfiends pulverize Hactar.

Even in his pulverized state as floating atoms, Hactar was still very powerful. He moved and recombined to become a dark cloud surrounding Krikkit, which isolated the inhabitants. Deciding that the decision not to destroy the Universe was not his to make, he used his influence to make them build their first spaceship and discover the Universe; he then manipulated them into the same rage which the Armourfiends possessed, urging them to destroy all other life. Hactar was seen to enjoy manipulating others into becoming aggressive and murderous.

After an incredibly long war, Krikkit was banished to an envelope of "Slo-Time." After his scheme failed, Hactar slipped the cricket-ball-shaped supernova bomb to Arthur Dent, who then accidentally saved the Universe again by being an abysmal cricket bowler.

When facing interrogation, Hactar manipulated the environment to make his surroundings that of a psychiatrist's office. He made himself sit on a five-foot couch, which was remarkable because he himself was a thousand miles long. The computer defended his actions as simply fulfilling his original function, as well as revenge on the Universe for the æons of suffering he had endured as a result of his original decision.

https://hitchhikers.fandom.com/wiki/Hactar

2na fisherman

(295 posts)
5. Doomsday Clock Is Ticking
Wed Feb 25, 2026, 01:58 PM
1 hr ago

So this is the way the world ends, by an AI bot removing the human factor and the human race.

Latest Discussions»Latest Breaking News»AIs can't stop recommendi...