Users who direct medical questions to AI chatbots like OpenAI's ChatGPT or Google's Gemini may trust the AI tool's chatty responses more than a list of search results.
New findings show that AI programs like OpenAI's GPT-3.5 and MedAlpaca are more likely to provide incorrect responses to health care queries in Mandarin Chinese, Hindi, and Spanish compared to English.
Collection
[
|
...
]