Large language models may pass medical exams with flying colors but using them for diagnoses would currently be grossly negligent. Medical chatbots make hasty diagnoses, do not adhere to guidelines, and would put patients' lives at risk. A team has systematically investigated whether this form of artificial intelligence (AI) would be suitable for everyday clinical practice. Despite the current shortcomings, the researchers see potential in the technology. They have published a method that can be used to test the reliability of future medical chatbots.
