‹ BackHN Continuity

Thread

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

702 points · 144 comments · polyphilz

  1. 2001zhaozhao · · focus · HN ↗
    Engineer: "HELP, our production DB is frozen on this query that worked fine before!"

    Infra: "Hmm, let's check... Well would you look at that, it seems like your LLM query planner usually works and produces fast queries, but this time when you changed a variable name to trigger query rebuild, it happened to hallucinate and miss an index, would you mind re-running the LLM a few times until you get a faster query?"

    1. ehe78qhe · · focus · HN ↗
      This exact situation has happened to me with Postgres' stock query planner when an automatic analyze got a bad sample of a large table.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.