Half of # AI # health answers are wrong even though they sound convincing # Chatbots , # ChatGPT , # Gemini , # Grok , # MetaAI and # DeepSeek , asked 50 health
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.