yes! while I didn't have time to go all the way and turn this into a model-graded eval, my hand grading showed a strong correlation across open source models, with more cooked models showing poorer…
Posters: maxsloef. maxsloef
3 likes recorded by the source corpus.
Topics: AI & LLMs
View Post: https://x.com/maxsloef/status/1953880125482647742