‹ 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. malisper · · focus · HN ↗
      Funnily enough, you could replace "LLM query planner" with just "query planner" and this comment would still hold true
      1. Tanjreeve · · focus · HN ↗
        That bug is fixable and verifiable. The LLM you cross your fingers till the next time the same thing happens.
        1. malisper · · focus · HN ↗
          > That bug is fixable and verifiable

          A bad query plan is not your typical kind of bug. I would definitely not call it fixable. Query planners are inherently dealing with estimations and approximations. If the query planners estimation is off, you're screwed.

          Unless you come up with a way to cheaply determine exactly how many rows a query will return, bad query plans will still exist.

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.