Remember seeing something about GPT-4 doing well on standardized tests? It turns out it may have memorized the answers.
https://aisnakeoil.substack.com/p/gpt-4-and-professional-benchmarks
#gpt4 #AIHype #ThisIsWhyWeDontTestOnTheTrainingData
Remember seeing something about GPT-4 doing well on standardized tests? It turns out it may have memorized the answers. 2 comments
|
@janellecshane poke @Agar