‹ BackHN Continuity

Thread

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

637 points · 217 comments · jasondavies

  1. warkdarrior · · focus · HN ↗
    Can someone explain how so many folks managed to build decision models within days or weeks after Typesafe came out with Jev? Is this concept of decision models been in the works for a while? Is it easy to copy?
    1. kerenskiy · · focus · HN ↗
      The concept existed a year before Jev or so. See Laya
      1. XTXinverseXTY · · focus · HN ↗
        Laya came after Jev, the original post is clear about this much [0].

        Moreover the specific prior art claim is absurd (self-plug) [1]. GLiClass[2] is at least a coherent precedent.

        [0]: <a href="https:&#x2F;&#x2F;laya.convaiinnovations.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;laya.convaiinnovations.com&#x2F;

        [1]: <a href="https:&#x2F;&#x2F;xtxinversexty.com&#x2F;layas-prior-art-claim-is-absurd&#x2F;" rel="nofollow">https:&#x2F;&#x2F;xtxinversexty.com&#x2F;layas-prior-art-claim-is-absurd&#x2F;

        [2]: <a href="https:&#x2F;&#x2F;github.com&#x2F;knowledgator&#x2F;gliclass" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;knowledgator&#x2F;gliclass

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.