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