它们在讨论专业话题时也展现出惊人的深度， 最终研究者们发现，但仍是错误的，研究者们发现它的诊断正确率仅为17%， 参考资料： 1.ChatGPT and Generating a Differential Diagnosis Early in an Emergency Department Presentation https://www.annemergmed.com/article/S0196-0644(23)00642-X/fulltext 2.Diagnostic Accuracy of a Large Language Model in Pediatric Case Studies https://jamanetwork.com/journals/jamapediatrics/article-abstract/2813283 3.Toddler whose symptoms puzzled 17 doctors for three YEARS is finally diagnosed with rare condition... by ChatGPT https://www.dailymail.co.uk/health/article-12509111/ChatGPT-diagnosis-rare-condition.html 4.WHO calls for safe and ethical AI for health https://www.who.int/news/item/16-05-2023-who-calls-for-safe-and-ethical-ai-for-health （原标题：美国医学会儿科杂志：ChatGPT在诊断儿科病例时准确率较低）