Mixtral has noticeably different biases to LLaMa 2 70B. I'm getting better results by having it complete from my Borgesian analysis of the Mu text in encyclopediac style than I am getting it to…

Posters: jd_pressman. jd_pressman

2 likes recorded by the source corpus.

Topics: AI & LLMs

View Post: https://x.com/jd_pressman/status/1739180123885318450