Enderchef·inGeneral·3 days agoWhy SFT? And why one distill?Why is every new distill SFT? SFT can't teach as much new knowledge Why not RL? And why does everyone dump old agentic datasets while training on new model ones(e.g. having a Opus…#question1000
Enderchef·inGeneral·13 days agoDataset of 240 Fable 5 sessionsSo, I've had a glitch in my Cursor giving me infinite Cursor usage with all their models. I've been making all my projects with Fable 5 Max, and I've used several billion tokens. M…#dataset#distill#fable5#claude#anthropic4000