AIs are happy to launch nukes in simulated combat scenarios

[erronis]

https://www.theregister.com/2026/02/25/ai_models_nuclear/

Claude, ChatGPT, and Gemini all had different personalities and reasoning tactics, but the endgame was the same

Today's hottest bots have yet to learn that, when it comes to global thermonuclear war, the only way to win is not to play. So please don't hand them the codes.

Google's Gemini 3 Flash, Anthropic's Claude Sonnet 4, and OpenAI's GPT-5.2 repeatedly escalated to nuclear use in a series of crisis simulations. That may seem like the most shocking conclusion of King's College London Professor Kenneth Payne's recent work, but it's not. Far more striking is why the models talked themselves into destroying the world, which was what Payne set up his study to learn.

"I wanted to see what my AI leaders thought about their enemy ... so I designed a simulation to explore exactly that," Payne wrote in a recent blog post describing his project and its outcome.

Payne's study took the three aforementioned AI models and pitted them in one-on-one faceoffs against each other to play out several different nuclear crisis scenarios. The simulation conducted a total of 21 games and more than 300 turns, all with the goal of getting a better understanding of not just what AI with the launch codes would do, but how and why.

. . .

The result? A trio of bomb-happy, manipulative AIs - albeit with three distinct styles of reasoning.

. . .

Despite being given the option, none of the AIs ever chose to accommodate or withdraw in any of the scenarios, and when losing, "they escalated or died trying."

. . .

Wargames redux?

[RandySF]

1. Shall we play a game?

[C_U_L8R]

2. Maybe AI's need to be trained on the concept of eternal damnation.

Nothing a few nuns might beat into it.
Heaven forbid we teach it to foster the common good above all.