The National Interest on MSN
In Wargame Simulations, AI Models Keep Threatening to Nuke Each Other
The actions of AI large language models are concerning—but broadly similar to human decision-makers, who have used nuclear ...
Artificial intelligence models from Google, OpenAI and Anthropic resorted to nuclear escalation in 95 per cent of simulations ...
According to Payne, the models escalated to the point of tactical nuclear war in 95 percent of scenarios, noting that nuclear threats to each other were far more likely to escalate than de-escalate ...
Leading AIs from OpenAI, Anthropic and Google opted to use nuclear weapons in simulated war games in 95 per cent of cases ...
As the Department of Defense pushes for greater AI integration, researchers said the top models chose the nuclear option in nearly all war simulations.
LONDON, Jan. 6, 2026 /PRNewswire/ -- LucidQuest, a strategy and insights agency empowering biopharma and healthtech leaders with evidence-led intelligence, today announced the launch of LucidWargames.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results