Dev on retrieval: Index size hasn't been an issue since 2021
lateinteraction · x · 2026-08-25
A developer noted that since 2021, index size hasn't been the core issue, except for visual search like ColPali. ColBERTv2 and PLAID solved storage costs before text-davinci-002 existed. The real problem is that people simply don't use existing technologies, insisting on representing raw matrices and doing naive MaxSim over them, which makes no sense.
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
- Sim data can't cover the humanoid long tail: the sim2real debate, mapped — herbiebradley · 2026-10-16
- SJTU AutoLab releases Drive3R, a streaming geometric foundation model for long-horizon driving 3D reconstruction — AutoLab-SJTU · 2026-10-16