Edit: Not saying this is the case for the person above, but one thing that might bias these observations is ChatGPT’s memory features.
If you have a chat about the condition after it’s diagnosed, you can’t use the same ChatGPT account to test whether it could have diagnosed the same thing (since the chatGPT account now knows the son has a specific condition).
The memory features are awesome but also sucks at the same time. I feel myself getting stuck in a personalized bubble even more so than Google.
He literally wrote that. I asked how he knows it's the right direction.
it must be treatment worked. otherwise it is more or less just a hunch
people go "oh yep that's definitely it" too easily. it is the problem with self diagnosing. And you didn't even notice it happened...
without more info this is not evidence.
We took him to our local ER, they ran tests. I gave the LLM just the symptom list that I gave to the ER initially. It replied with all the things they tested for. I gave the test results, and it suggested a short list with diagnostics that included his actual Dx and the correct way to test for it.
By the way unless you used an anonymous mode I wonder how much the model knew from side channels that could contribute to suggesting correct diagnosis...