Gsus4Jul 24, 2023

Over just a few months, ChatGPT went from accurately answering a simple math problem 98% of the time to just 2%, study finds

https://lemmy.one/post/1385551

Over just a few months, ChatGPT went from accurately answering a simple math problem 98% of the time to just 2%, study finds - Lemmy.one

Can we discuss how it’s possible that the paid model got worse and the free one got better? Is it because the free one is being trained on a larger pool of users or what?

Show threadblue_zephyrJul 24, 2023
It’s because the research in question is of really poor quality.
Show threadGsus4
True, checking whether a number is prime is very limited in scope for chargpt, but this is in line with other reports of progressive dumbing down.
Jul 24, 2023 at 8:40pmWeb