Thread

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

637 points · 217 comments · jasondavies

amluto · 1790881961 · 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. mikeocool · 1790883945 · focus · HN ↗
  It seems like jev's major advantage over existing classifiers is that I dont have train it.
  If I have to gather and tag data to fine-tune Jev, I can probably just train an "old school" classifier model and make it even cheaper, faster, and just as accurate.

Unofficial Hacker News client; not affiliated with Y Combinator.