Algorithm efficiency shifts with doc length; token pooling gains edge in 1k token setting
tomaarsen · x · 2026-08-25
Addressing previous math on token pooling efficiency, the author notes that in a more realistic 1k token document setting, the calculation logic reverses. Approaches like token pooling become very attractive in long-context scenarios to offset computational costs.
More from Research
- Quotient Recurrent Reasoners hit 97.9% on Sudoku-Extreme with 78% fewer loops — burny_tech · 2026-10-16
- Mathematicians publish explainer for the Egyptian fraction proof in OpenAI's proofs collection — burny_tech · 2026-10-16
- Robin Hanson: a neural network is almost 'a fractal of explanations' — burny_tech · 2026-10-16
- 'Neural networks really are super simple': a takes on features, concepts and connectionism — burny_tech · 2026-10-16
- Composition gives more combinations, not more features: rebutting an anti-superposition essay — livgorton · 2026-10-16
- Composition and superposition aren't mutually exclusive — and each has worse interference regimes — livgorton · 2026-10-16