‹ BackHN Continuity

Thread

Clef: Open-weight decision models, and new RL fine-tuning platform

637 points · 217 comments · jasondavies

  1. amluto · · focus · HN ↗
    I’ll go out on a limb and suggest that I don’t think a Jev-like model is particularly useful unless you can fine tune it. The Jev API has zero ability to pass in a prior [0], and, if you can neither pass in a prior nor fine tune for your system, you will get an output that may be almost meaningless.

    I’d love to see someone build a model of this sort that can actually accept priors and do something intelligent with them.

    [0] You can feed Jev a prior as text. I’ve tried it. It works poorly.

    1. jdthedisciple · · focus · HN ↗
      I suppose a sort of prior-proxy can be encapsulated by a carefully written system prompt.
      1. amluto · · focus · HN ↗
        The straightforward approach of literally staying a numeric prior has some effect but not the correct effect.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.