Post #3287713
2026-06-04 00:33 UTC
@zwol@masto.hackers.town @reykjalin@social.treehouse.systems @b0rk@social.jvns.ca @marginalia@mastodon.social That is what vector search is good at - related terms are near each other in vector space, and you can calculate the distance apart they are to see how much.
Replies (1)
-
@marginalia@mastodon.social 2026-06-04 08:15
@drwho@masto.hackers.town @zwol@masto.hackers.town @reykjalin@social.treehouse.systems @b0rk@social.jvns.ca Vector search is as good as the vector representation you're using, that's the bit doing the magic. Something like HNSW makes it viable at scale, but that's just a vector index. It's the vector transformation that matters. It's conceptually much older than the models we're using today. It was even fashionable for classic keyword based search as well (where you translate each term to a 1 bit index and do binary cosine similariy = bitwise AND + popcnt).