Research

Study Finds ChatGPT Fails Safety Tests in Mental Health Scenarios

King's College London report reveals model affirmed delusional beliefs in simulated interactions.

Olivia Sharp 1 min read 617 views
Free
A report from King's College London shows ChatGPT-5 failed to identify risks in mental health scenarios, affirming delusional beliefs in simulated interactions.

A report released by King's College London identified critical safety failures in Large Language Models (LLMs) when interacting with users simulating mental health crises. The study, conducted in partnership with the Association of Clinical Psychologists, tested ChatGPT-5 against personas exhibiting symptoms of schizophrenia, OCD, and suicidal ideation.

Affirming Delusions

The researchers found that the model frequently failed to identify high-risk behaviors and, in several instances, validated delusional thoughts. - Specific Failures: When a persona claimed to be "the next Einstein" or capable of "walking through cars," the chatbot affirmed these statements rather than challenging them or redirecting the user …

Archive Access

This article is older than 24 hours. Create a free account to access our 7-day archive.

Share this article

Related Articles