@individualkex: reinforcement learning (for llms) explained

TheLegend27 :

I don't understand on what is it being reinforced, like, what is the "test" the "judge" is getting? how can you tell if something is more "unhinged" for the judge to be reinforced to mimic?

Will 🧡 :

Need this for myself

Dariton :

cyrilzgheib :

I recently made a cnn program that identifies different garments and accessories the library I installed was perfect about 93% but when I want insert an image it confuses bag with shoes and vice versa

AI kyarisiimaishmael :

amazing 👏

Charlie :

Niceeeee