Thread

Training a 4B model to produce 81% faster query plans than Postgres

702 points · 144 comments · polyphilz

trollied · 1789597271 · focus · HN ↗
TL:DR; for people. Index your data properly.
1. isatty · 1789607953 · focus · HN ↗
  It’s 8G of data in memory. You can raw dog that no problem.
  (Indexes would be nice though)

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.