MaxSim is soft alignment: 'live' matches 'inhabit' at 0.94, zero shared characters
tomaarsen · x · 2026-08-18
The key to understanding multi-vector retrieval is reading MaxSim as soft alignment: every query token points at the document token that best explains it, and the alignment isn't lexical — between "Where do penguins live?" and "Penguins inhabit Antarctica", live finds inhabit at 0.94 despite sharing no characters. A dense model compresses whole texts into one vector, averaging away token-level matching; a multi-vector model keeps a vector per token and sums each query token's best match in the document.
More from coding & agent
- Software engineer: devs are now just glorified agent managers — KevinNaughtonJr · 2026-10-17
- Dev complains coding agents force him to live in the terminal he hates — pixlpa · 2026-10-17
- Erwin Coumans revives 2010-era CUDA physics engine with Claude in one afternoon — erwincoumans · 2026-10-17
- Sol plays Asterix from screenshots, holding each move until its next reply arrives — wzenus · 2026-10-17
- GPT-6 Sol plays rhythm games in real time, picking keys and tap times from frames — wzenus · 2026-10-17
- Sol picks speed and lane targets frame-by-frame from onboard camera while racing — wzenus · 2026-10-17