NMSLIB author: new preprint cites us to back an unsubstantiated claim
srchvrs · x · 2026-11-05
srchvrs continues his thread on NMSLIB being sidelined in a new vector-search preprint: he privately flagged NMSLIB's early graph-based sparse/mixed retrieval work to the authors in January and got acknowledgment plus benchmarking tips, yet the preprint never names NMSLIB as a library and cites their paper to support an unsubstantiated claim that multi-representation support "reduces performance on each." Author Silvio Martinico responds that the sentence's subject was hnswlib, and their dense/sparse/multivector scope only warrants citing nmslib in the intro.
Related event: NMSLIB Author Protests New Vector Search Paper Downplaying His Work(4 posts)→
More from coding & agent
- Max out Claude thinking and ultracode on every prompt, says dev — curious_vii · 2026-11-05
- After 100+ team interviews, Swytchcode argues MCP is for building agents, not running them — curiousblack99 · 2026-11-05
- Yuchen declares 'Codex won the agent war' — Yuchenj_UW · 2026-11-05
- Interactive home-emergency trainer built with Opus 5.5, Blender and Three.js — techartist_ · 2026-11-05
- Developer proposes a 12-level AI coding autonomy scale based on who does the work — nimareq · 2026-11-05
- Claude Cookbook shows how to build a nightly "dreaming" memory service for agents — brada · 2026-11-05