‹ BackHN Continuity

Thread

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

637 points · 217 comments · jasondavies

  1. pcthrowaway · · focus · HN ↗
    > First, it has a vision encoder so it’s able to take in images and classify visual content.

    Wait, does this mean this is the first (non-generative) model to be able to do <a href="https:&#x2F;&#x2F;xkcd.com&#x2F;1425&#x2F;" rel="nofollow">https:&#x2F;&#x2F;xkcd.com&#x2F;1425&#x2F; !?

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.