Every RAG tutorial insists that smarter, semantic text-splitting is the key to good retrieval. The data says otherwise — and points to two duller fixes that actually work.
Every facial recognition match you've ever seen was never the closest possible match — it was the fastest good-enough guess a system built to discard information could produce. That design choice, not just biased photos, explains why it fails some faces more than others.
Google-scale search feels like a triumph of server farms and fiber. It isn't. The real trick — refusing to ever read a document at query time — was invented on machines with less memory than a phone photo.