[tsoukase]

Using an LLM to diagnose/treat a health issue is not yet mature and not going to be such in the foreseeable future. It's not like predicting a protein fold or presenting a business report. Medical advice is in many dimensions incompatible with artificial support: non-quantifiable, fuzzy, case-specific, intimate, empathic and awfully responsible. Even AGI is not enough. In order to become a doctor, the machine has to develop next-level dexterities, namely to follow the interplay of multiple concurrent factors on various types of living tissue. Multiple attempts to bring Decision Support to medicine have failed and LLM is one more. Sure you can take an advice, but it will be the less useful of all the other types you can have.