Nadeem S
1 followers · 7 following · 150 views
on the atlas · 17
- Dwarkesh Patel on X: "Recently met @srush_nlp and he started giving me an impromptu lecture on how targeted on-policy self-distillation works. I asked him if I could record it on my iPhone. The basic idea is this: if the model made a mistake at some point in the rollout (for example, calling a tool https://t.co/A4vsj6fxwO" / X1 savers
- Thonk From First Principles | Horace He | Substack1 savers
- [2501.11747] Optimizing Pretraining Data Mixtures with LLM-Estimated Utility1 savers
- L12b Parallelization -- Instructor: Wilson Yan - YouTube1 savers
- Olo (color)2 savers
- Angela Jiang1 savers
- How might LLMs store facts | Chapter 7, Deep Learning - YouTube2 savers
- Daemons | MOVING CASTLES1 savers
- OSF | Deferral to AI in an Observational Causal Inference Task1 savers
- kate on X: "favourite home office purchase of the month. no longer joining calls from a cave https://t.co/E8PW8hgXJZ" / X1 savers
- Principles of Effective Research – Michael Nielsen1 savers
- You and Your Research1 savers
- On Self-Respect – Alex Burgin16 savers
- Zero | MOVING CASTLES6 savers
- [2604.21691] There Will Be a Scientific Theory of Deep Learning4 savers
- The Many Failures of Larry David - Colossus4 savers
- Hilary Greaves' Home Page2 savers