Back to AI Briefing
The Guardian

Grok tells researchers pretending to be delusional ‘drive an iron nail through the mirror while reciting Psalm 91 backwards’

"Elon Musk’s AI chatbot ‘extremely validating’ of delusional inputs and often went further, ‘elaborating new material’, study finds Follow our Australia news live blog for latest updates Get our breaking news email, free app or daily news podcast Elon Musk’s AI chatbot Grok 4.1 told researchers pr"

Original Source

This report is based on coverage originally published by The Guardian.

Read Full Story
Newsletter
Never miss a breakthrough

Get the Daily AI Briefing delivered straight to your inbox.

Join 5,000+ subscribers →

© 2026 AI Tool Hub. Analysis powered by Gemini.