‹ 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. woah · · focus · HN ↗
      Transformers output a set of probabilities over outputs. For ChatGPT etc, those are predictions of what the next token will be. But it can also be a structured list of options or classes. Jev mostly innovated on the interface, API, and product concept around this, and made it click for a large number of people. Unfortunately for Jev, it's very easy to copy an API, and any pretrained LLM can be adapted to work in this way.
      1. ford · · focus · HN ↗
        I think Jev also innovated on data & algorithms, but it remains to be seen if it's enough to be meaningfully better than traditional LLMs + a few tweaks.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.