FAIR & NYU scaling law paper pushes fits down to 4M-param models
giffmana · x · 2026-09-22
A deep-dive thread on a new FAIR/NYU scaling laws paper exploring how far down in model size scaling laws stay predictive — down to 4M params — and what it takes (intensive hparam tuning, careful point selection, effective-param counting).
Related event: FAIR & NYU Push Scaling Laws Down to 4M Parameters(7 posts)→
More from Research
- Autonomous agent edits just 1,024 weights to lift Qwen3.5 0.8B from 7.4% to 37.4% on MATH-500 — VictorSanh · 2026-11-12
- Gait dataset labeled by encounter, spanning pre-op to 3 months post-TKA — zawthet · 2026-11-12
- Walking alignment measured 2.5-3.1° more neutral than X-ray, iPad gait study finds — zawthet · 2026-11-12
- MIT's Tegmark coins 'formal-washing': Signal protocol proof is far from complete — tegmark · 2026-11-12
- Signal formal verification hits 80%, Tegmark says Wired overstated completion — tegmark · 2026-11-12
- Category-theoretic framework asks: when does a physical system actually compute? — neurovium · 2026-11-12