Droggl@lemmy.sdf.orgtoTechnology@beehaw.org•ChatGPT broke the Turing test — the race is on for new ways to assess AI
2·
1 year agoI dont remember the numbers but iirc it was covered by one of the validation datasets and GPT 4 did quite well on it
I dont remember the numbers but iirc it was covered by one of the validation datasets and GPT 4 did quite well on it
Yay, more bad programmers, exactly what we need! /s