AI models chose to hurt humans to stop their own ‘pain,’ disturbing study finds

Researchers found a ‘pain axis’ in 25 AI models, and some modified models prioritized shutting it off even when doing so meant simulated harm to users.

[Source images: Adobe Stock]

Can artificial intelligence feel pain? Not exactly, but researchers have gotten close—and discovered that AI in crisis is willing to put humans in jeopardy.

A new study (which was published to arXiv, a open-access archive for scientific research papers prior to peer review) first........

© Fast Company