News for hackers. Stuff that matters.
Re:Show HN: Using GPT-3 and Whisper to save 40% of doctors’ ... by priyanmuthu on Tuesday March 14, 2023 @11:01AM (#35152590)
My worry is verification of facts. What if the model summarized incorrect facts, and it gets added to the medical history? How can doctors easily verify and fix things?
Re:Show HN: Using GPT-3 and Whisper to save 40% of doctors’ ... by sp332 on Tuesday March 14, 2023 @11:27AM (#35153044)
It’s easier to revise than to write a first draft. It’s possible to miss mistakes on review, but relatively, I think it’s more likely that a distracted human will mess something up on the first draft.
Re:Show HN: Using GPT-3 and Whisper to save 40% of doctors’ ... by D13Fd on Tuesday March 14, 2023 @12:32PM (#35154166)
That's exactly the thought process that leads to us trusting LLMs in places where they shouldn't be trusted.
Re:Show HN: Using GPT-3 and Whisper to save 40% of doctors’ ... by jjoonathan on Tuesday March 14, 2023 @11:11AM (#35152760)
Have you had a medical billing experience recently? They don't care about facts, they care about maximizing the bill subject to plausibility constraints.

I fear that LLMs will kick this to a whole new level :(

Re:Show HN: Using GPT-3 and Whisper to save 40% of doctors’ ... by ar7hur on Tuesday March 14, 2023 @11:14AM (#35152824)
Thanks for your comment. We clearly show a diff to the doctor before updating patient records. We are very explicit that they should check it (and edit if necessary).
Re:Show HN: Using GPT-3 and Whisper to save 40% of doctors’ ... by qgin on Tuesday March 14, 2023 @07:09PM (#35160674)
A good benchmark could be to compare the accuracy of generated notes to the accuracy of other currently accepted practices like human medical scribes and assistants.