Semantic emoji search with on-device bge-small beats LLM at $0 per search
maxleiter · x · 2026-09-27
Responding to the buzz around Linear adding an LLM ("Jev") to its emoji picker, Max Leiter argues developers are treating LLMs as a hammer for every classification task. Two years ago he built semantic emoji search with no LLM: bge-small-en-v1.5 (37MB) runs on-device in the browser, downloads once, and every search costs $0 — faster, cheaper, and occasionally better than the LLM route. His takeaway: use LLMs only when you actually need reasoning behind the decision; embeddings (plus pgvector for the API variant) suffice for tasks like emoji search. The post includes a live demo comparing on-device, Embeddings API, and Jev costs.
Related event: Developer Shows Embeddings Beat LLMs for Emoji Search at Near-Zero Cost(2 posts)→
More from coding & agent
- Dev turns Annecy into a playable 3D boat tour using Claude Opus 5.5 and Three.js — techartist_ · 2026-09-27
- One-shot with Opus: dev builds a jsfiddle-style sandbox for PHP 4.1.1 — generativist · 2026-09-27
- One-shot with Opus: a PHP 4.1.1 simulator with Zend Engine compiled to WebAssembly — generativist · 2026-09-27
- DHH on AI coding: thinking "architecture" is your fortress? Models are good at that too — tawnniee · 2026-09-27
- Reverse engineering with coding agents: set it up overnight, wake up to source — moyix · 2026-09-27
- ThePrimeagen joins DHH's Omarchy Core to lead agentic QA with Oligarchy harness — mark_k · 2026-09-27