Developer shows local embeddings enable free semantic emoji search without LLMs

Developer Max Leiter argues that LLM integrations like Linear's emoji picker are overkill, demonstrating zero-cost semantic emoji search using local embeddings such as bge-small, which is faster and cheaper than LLM-based approaches.

2026-09-27 ~ 2026-09-27 · 3 related posts

• You don't need an LLM for good emoji search: embeddings run faster and cost $0 — maxleiter · 2026-09-27
• Semantic emoji search with on-device bge-small beats LLM at $0 per search — maxleiter · 2026-09-27
• Emoji search without embeddings: pgvector latency questions for a lightweight API — paul_cal · 2026-09-27