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 ...

AI bots threatened to use nuclear weapons to destroy rival nations in a simulated war game at levels that would “alarm any student of nuclear strategy”, a study has found.

Imagine handing the nuclear launch codes to the world’s most advanced artificial intelligence. You’d hope the machine would ...

Artificial intelligence systems, including ChatGPT, Claude, and Gemini, have been showing a new and disturbing pattern. Controversies around AI chatbots reached ...

A recent study conducted by a King’s College London professor, Kenneth Payne, found that ...

There are some things perhaps we might not want artificial intelligence to handle, at least for the time being. When leading ...

A new study has revealed an aggressive nature of AI systems, exhibiting that chatbots do not hesitate to use nuclear weapons in simulated war game scenarios. Researchers at King’s ...

A disturbing new study has revealed that advanced artificial intelligence systems are more prone than humans to deploy nuclear weapons when international tensions escalate.

In 86% to 95% of scenarios the models escalated, in 95% both parties threatened nuclear strikes, and no model chose 'harmony or withdrawal'.