It looks like the LLMs weren't trained for medical tasks. The study would be more interesting if it had been run on something built for the task.
this post was submitted on 09 Feb 2026
599 points (98.7% liked)
Technology
83529 readers
1936 users here now
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related news or articles.
- Be excellent to each other!
- Mod approved content bots can post up to 10 articles per day.
- Threads asking for personal tech support may be deleted.
- Politics threads may be removed.
- No memes allowed as posts, OK to post as comments.
- Only approved bots from the list below, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
- Check for duplicates before posting, duplicates may be removed
- Accounts 7 days and younger will have their posts automatically removed.
Approved Bots
founded 2 years ago
MODERATORS
This makes sense. However doctors aren't perfect either and one thing properly trained AI should excel at is helping doctors make rare diagnoses or determine additional testing for some diagnoses. I don't think it's quite there yet but probably close to being a tool a well trained doc could use as an adjunct to traditional inquiry. Certainly not something end users should be fiddling with with any sort of trust though. Much of doctor decision making happens based on experience - experience biases towards common diagnoses which usually works out because well, statistics, but it does lead to misdiagnosis of rare disorders. An Ai should be more objective about these.
An Ai should be more objective about these.
they tend more toward the middle than the outliers. law of the instrument and all
load more comments
(1 replies)