Seems like diminishing returns on creating a specialized vs foundational model...

At the extreme performance end these tests end up boiling down to trivia/minutiae... I guess I can take pride in getting a top 10% score for a human way back in the day... not bad for a human lol.

> the upshot is this:
> - doctors alone scored 73.7% on diagnosing patients even when using google etc.
> - doctors using GPT scored 76.3%
> - but GPT alone scored 92%.

👀 ... When they say you will be replaced by someone that knows how to use AI haha

![](https://m.stacker.news/105304)

> The median diagnostic accuracy for the docs using Chat GPT Plus was 76.3%, while the results for the physicians using conventional approaches was 73.7%. The Chat GPT group members reached their diagnoses slightly more quickly overall - 519 seconds compared with 565 seconds.
>
> The researchers were surprised at how well Chat GPT Plus alone performed, with a median diagnostic accuracy of more than 92%.

@gmd 