Welcome to DU! The truly grassroots left-of-center political community where regular people, not algorithms, drive the discussions and set the standards. Join the community: Create a free account Support DU (and get rid of ads!): Become a Star Member Latest Breaking News Editorials & Other Articles General Discussion The DU Lounge All Forums Issue Forums Culture Forums Alliance Forums Region Forums Support Forums Help & Search

Science

Lithos

(26,505 posts)

2. It did not

Reply to Mosby (Original post)

Fri Apr 28, 2023, 11:46 PM

Apr 2023

I cannot find the link, as I read this about a week ago.

An ER doc pushed up their "case studies" to see how well ChatGPT did in diagnosis.

It did ok for fundamental situations. Ie, nasal drip things.

It failed horribly for every other case.

I would not trust it.

L-

My provenance - I am about a week from getting my MS degree in this stuff.

Edit history

Please sign in to view edit histories.

Recommendations

0 members have recommended this reply (displayed in chronological order):

4 replies

= new reply since forum marked as read

Highlight:

ChatGPT outperformed doctors in accuracy and empathy [View all] Mosby Apr 2023 OP

parlor tricks won't change the world. nt BootinUp Apr 2023 #1

Lol. nt intrepidity Apr 2023 #4

It did not Lithos Apr 2023 #2

But does it True Dough Apr 2023 #3