‹ BackHN Continuity

Thread

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

702 points · 144 comments · polyphilz

  1. devsda · · focus · HN ↗
    > Frontier intelligence is extremely powerful; the distillation I did off Astra trajectories is proof enough that large models are not going anywhere

    Wouldn't admitting this invite trouble due to accusations of distillation flying around between closed and open models.

    1. Onavo · · focus · HN ↗
      I don't think anybody's denying that small models are doing distillation, the issue at hand is frontier lab vs frontier lab when it comes to big models.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.