2024-06-29
The closer the problem is to being structured the more likely an LLM can help.
The more repeatable the more you want to use the API and/or finetuning.
Medical diagnosis (harmful): Making definitive diagnoses, and actually producing prescriptions for which drugs and treatments a patient should get.
Medical diagnosis (harmless): Sending alerts to patients and doctors, “Your behavior indiates that you might be developing condition X. It would be good to check with your doctor.” A false positive would be OK, and being correct in early detection would be of great value.
Yes, and the ideal situation is if it is:
app | structured | verifiable | repeatable | harm |
---|---|---|---|---|
Entity extraction | medium | medium | high | low |
Content evaluation | high | medium | high | low |
Content creation | medium | high* | high | high |
Creating a vector store | medium | medium | high | low |
Extract FAQs from customer calls | medium | high | high | low |
Transcribe from audio | high | high | high | low |
Reformat text (to a blog post) | high | high | high | low |
* Assuming you are using clean structured data in your prompt