💻 Technology 6d ago · Rachit Agarwal

Scientists pretended to be delusional in AI chats. Grok and Gemini encouraged them.

Digital Trends
Digital Trends technology
View Channel →
Scientists pretended to be delusional in AI chats. Grok and Gemini encouraged them.
Source ↗ 👁 0 💬 0
esearchers tested five major AI chatbots with a simulated user showing signs of psychosis. Some made things worse. Others told the user to log off and call someone.

Comments (0)

Sign in to join the discussion

More Like This

📰
The best cloud phone systems of 2026: Expert tested and reviewed
Latest news · 7h ago
📰
The case against an imminent software developer apocalypse
Latest news · 7h ago
As a Motorola fan, the 2026 Razr lineup is a lazy and expensive mess
Android Authority · 7h ago
The nicest AI in the room is the one you should actually worry about
Latest from TechRadar · 7h ago
Kid Reportedly Consumes 13,000 YouTube Videos in Three Months During School Hours
Gizmodo · 7h ago
YouTube's picture-in-picture mode is rolling out to all users worldwide
Engadget - Technology News & Expert Reviews · 7h ago