A study of nine AI chatbots found hallucination rates from 0% to 34%, with Grok 3 performing the worst and Perplexity Research being most reliable.
Medscape News UK
Source link : https://www.medscape.com/viewarticle/ai-chatbots-vary-widely-fake-medical-references-2026a1000bmr?src=rss
Author :
Publish date : 2026-04-14 16:48:00
Copyright for syndicated content belongs to the linked Source.