Caleb Choe
0 followers · 1 following · 229 views
on the atlas — 5
- Discord | @otherlego1 savers
- Level 281 savers
- Thread by @karpathy on Thread Reader App – Thread Reader App1 savers
- STANFORD MASTER GOOGLE DOC - Google Docs1 savers
- Curius / Onboarding2621 savers
highlights — 1
TLDR: RL will lead to more gains because when done well, it is a lot more leveraged, bitter-lesson-pilled, and superior to SFT. It doesn't feel like the full story, especially as rollout lengths continue to expand. There are more S curves to find beyond, possibly specific to LLMs and without analogues in game/robotics-like environments, which is exciting.
Thread by @karpathy on Thread Reader App – Thread Reader App