How Search Engines Actually Work — and Why LLMs Extend, Not Replace, Them

Short summary

A veteran search engineer explains that lexical search is not obsolete but foundational, with inverted indexes, BM25, and relevance scoring doing critical work that databases cannot replicate. LLMs and embeddings are extensions rather than replacements, fixing specific gaps like synonym matching that lexical search handles poorly. The article sets up a framework for understanding what genuinely changes when AI enters search, arguing that most commentary misunderstands what search already does.

• •Lexical search uses inverted indexes and decades of relevance science — it is not primitive or obsolete
• •Search engines trade transactional guarantees for millisecond-latency relevance scoring, unlike databases
• •Embeddings and LLMs extend lexical search by fixing synonym and semantic gaps, not replacing it

Generated with AI, which can make mistakes.