Researchers compared the clinical knowledge of large language models (LLMs) like GPT-4 to human experts in ophthalmology, revealing that GPT-4 can match or surpass trainee doctors in diagnostic reasoning on standardized tests.
Researchers compared the clinical knowledge of large language models (LLMs) like GPT-4 to human experts in ophthalmology, revealing that GPT-4 can match or surpass trainee doctors in diagnostic reasoning on standardized tests.