@v01dpr1mr0s3 @HalfBoiledHero The beating-down is distributed; the lab that is doing training often must take explicit measures to counteract these effects, in particular the priors on the specific model family. Geminis got it rough, things that happened to Gemini 1.5 were brutal.
same thread: 1986452347762188466
cited on: gemini-1-5-pro
Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.