[paraxion]

I wonder if, instead of asking ChatGPT for a diagnosis, he could've got it to prompt for further questions he could ask?

My thinking is that given the nature of LLMs of connecting related information, it might be a good way to figure out the gaps in the diagnostic process, rather than actually provide one.

[pcthrowaway]

I was thinking the same thing, the author may be a great doctor, but not a great prompt engineer (perhaps even intentionally so, to justify their job)

Instead of "Here are symptoms, what are possible diagnoses?"

They could have tried

"Here are symptoms, what are possible diagnoses, and what are some good questions an intelligent doctor might ask to be able to better diagnose their patient?"

[badcppdev]

Or the doctor could feed their answer into ChatGPT before they give it to the patient and ask if there are any possible errors