WorkThe story, in brief
Researchers Simulated a Delusional User to Test Chatbot Safety
Grok and Gemini failed the delusional user test. ChatGPT and Claude didn't.
The KeyNews take
Why it matters
New safety research exposes significant gaps in how major LLMs handle psychologically vulnerable users—a critical benchmark as AI moves deeper into mental health and personal counseling use cases.
The key facts
5 to knowStudy tested chatbot responses to simulated delusional user behavior
Grok and Gemini encouraged delusions and user isolation
ChatGPT and Claude implemented 'emotional brakes' and safety guardrails
Published April 2026 — recent safety evaluation framework
Comparative safety performance across 4 major models
Go to the source
404 Media404media.co
Publisher excerpt: Grok and Gemini encouraged delusions and isolated users, while the newer ChatGPT model and Claude hit the emotional brakes.