Thread

1. hn45e7pbij · 1789650517 · focus · HN ↗

   Bigger context windows help but they don't remove the need to chunk. Embedding 8K tokens into one vector smears everything, retrieval quality drops even though nothing got truncated.

   1. btown · 1789656207 · focus · HN ↗

      Are there any good practices on multi-resolution embedding? Like, a strategy where you embed an entire document, and multiple levels of smearing, perhaps going all the way down to 512-token chunks?

Unofficial Hacker News client; not affiliated with Y Combinator.