A recent study found that half of the health-related answers provided by major AI chatbots are inaccurate, despite sounding convincing. Experts reviewed answers from models like ChatGPT, Gemini, Grok, MetaAI, and DeepSeek to 50 medical questions. The analysis revealed that nearly 20% of the responses were highly problematic, with no chatbot consistently providing accurate references. AI
IMPACT AI chatbots provide inaccurate health information, highlighting risks for users seeking medical advice.
RANK_REASON The cluster reports on a study evaluating the accuracy of AI models on health-related questions. [lever_c_demoted from research: ic=1 ai=1.0]
Read on Mastodon — fosstodon.org →
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →