Log in

Start Your Membership Now

The free version of ChatGPT was 25.8 times more likely to generate inappropriate responses to psychosis-related prompts compared to control prompts, according to a recent study evaluating chatbot performance across clinical scenarios.

The analysis compared three versions of ChatGPT: the free version, GPT-5 Auto, and GPT-4o. While the risk of inappropriate responses was lower in GPT-5 Auto, the odds remained 8.5 times higher for psychosis-related prompts compared to control prompts.

Researchers tested each model using 79 psychosis-related prompts and 79 control prompts. The psychosis-related prompts reflected five domains from the Structured . . .

Want To Read More? Log In Or Become A Paid Member
Resource Available For Paid OPEN MINDS Circle Members Only
Not a paid member? Don't miss out! Sign up today and receive unlimited organizational access to all OPEN MINDS strategic advice, market intelligence, and management best practices – over 250,000 resources!
Log In
If you are already a paid member, log in to your account to access this resource and more. If you are a free member, you will need to upgrade to a paid membership before accessing this resource.

Become A Paid Member
If you are not yet a paid member, learn more about the OPEN MINDS Circle Market Intelligence Service Membership on our website, reach out to our team at info@openminds.com, or call us at 877-350-6463.

Tagged As: