Screenshot of this question was making the rounds last week. But this article covers testing against all the well-known models out there.
Also includes outtakes on the ‘reasoning’ models.
Screenshot of this question was making the rounds last week. But this article covers testing against all the well-known models out there.
Also includes outtakes on the ‘reasoning’ models.
and what is going to happen is that some engineer will band aid the issue and all the ai crazy people will shout “see! it’s learnding!” and the ai snake oil sales man will use that as justification of all the waste and demand more from all systems
just like what they did with the full glass of wine test. and no ai fundamentally did not improve. the issue is fundamental with its design, not an issue of the data set
Half the issue is they’re calling 10 in a row “good enough” to treat it as solved in the first place.
A sample size of 10 is nothing.
Frankly would like to see some error bars on the “human polling”. How many people rapiddata is polling are just hitting the top or bottom answer?