@krishnanrohit For me GPT-2 to 3 is like going from scoring 20 on an exam to scoring 60, while 3 to 4 is maybe going from 60 to 80. Sure, the raw improvement is more, but qualitatively 3 feels barely usable to me—it’s only reliable on the simplest tasks or after a lot of prompt optimization.
cited on: gpt-2
Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.