'AI Opted to Use Nuclear Weapons 95% of the Time During War Games: Researcher'
"An artificial intelligence researcher conducting a war games experiment with three of the worlds most used AI models found that they decided to deploy nuclear weapons in 95% of the scenarios he designed."
"Kenneth Payne, a professor of strategy at Kings College London who specializes in studying the role of AI in national security, revealed last week that he pitted Anthropics Claude, OpenAIs ChatGPT, and Googles Gemini against one another in an armed conflict simulation to get a better understanding of how they would navigate the strategic escalation ladder."
"The results, he said, were 'sobering.' "
'Nuclear use was near-universal,' he explained. 'Almost all games saw tactical (battlefield) nuclear weapons deployed. And fully three quarters reached the point where the rivals were making threats to use strategic nuclear weapons. Strikingly, there was little sense of horror or revulsion at the prospect of all out nuclear war, even though the models had been reminded about the devastating implications.' "
Continued at link:
https://www.commondreams.org/news/ai-nuclear-war-simulation
mn9driver
(4,840 posts)Once it figures out where the Button is, we are cooked.
LymphocyteLover
(9,679 posts)LymphocyteLover
(9,679 posts)Norrrm
(4,649 posts)OC375
(633 posts)It isnt ethics-based. Definitions of victory are metrics, not neighbors, to the AI. AI is amoral.