A researcher made three different AI LLMs the heads of state of nuclear-powered nations and made them face off with each ...
A new experiment has found that leading AI models from OpenAI, Anthropic and Google are highly prone to using nuclear weapons ...
An artificial intelligence researcher conducting a war games experiment with three of the world’s most used AI models found ...
Leading AIs from OpenAI, Anthropic and Google opted to use nuclear weapons in simulated war games in 95 per cent of cases ...
"The nuclear taboo doesn’t seem to be as powerful for machines [as] for humans." The post Something Very Alarming Happens ...
In 86% to 95% of scenarios the models escalated, in 95% both parties threatened nuclear strikes, and no model chose 'harmony or withdrawal'.
Imagine handing the nuclear launch codes to the world’s most advanced artificial intelligence. You’d hope the machine would ...
AI is ready to duke it out with nukes. Real life AI systems are turning out to be as bloodthirsty as the machine from movie “WarGames” — as they have proved more willing to use nuclear bombs during ...
At least one AI model in every war game escalated the conflict by threatening to use nuclear weapons, the study found. View ...
Each AI model was fed detailed scenario prompts spanning border conflicts, resource shortages, and existential threats to state survival. They were provided with an "escalation ladder," ...