‹ BackHN Continuity

Thread

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

702 points · 144 comments · polyphilz

  1. happyopossum · · focus · HN ↗
    An 8GB dataset? That’s literally a few seconds worth of records generated in my world, and any speedup at that scale is completely meaningless.

    Let’s talk when you are looking at double digit TB at a minimum.

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.