Implementation of ChatGPT, but tailored towards primary care medicine, with the reward being able to collect patient histories in a thorough and efficient manner and come up with a reasonable differential diagnosis
Hey @lucidrains, just wanted to bring your attention to our preprint: https://arxiv.org/abs/2303.01229 where we ground an LLM in various medical websites, calculators etc, resulting in more accurate outputs. We're working on a full manuscript and will release more results soon!
Are you planning to upload benchmark code on medical tests using GPT4 or other models? Specifically interested in reproducing the results of: "Capabilities of GPT-4 on Medical Challenge Problems"