Thread

1. alex7o · 1790367128 · focus · HN ↗

   Guys I have a real q, what is the difference between an instruct based re-ranker and laya/jev I just don't see it.

   Edit: One is that jev/laya are tuned to have better probabilities, but a reranker can be fine tuned to do that as well. And jev/laya use RLCD?

   1. kakugawa · 1790373212 · focus · HN ↗

      Jev's value becomes more apparent when the task is a moving target. eg an auto-mode classifier.

      1. c10o · 1790399804 · focus · HN ↗

         Exactly. Just think about a discord or twitch moderation bot that screens messages in real-time. When the streamer starts playing a game, the whole context switch in an instant and comments like «kill them» will suddenly have a whole different meaning.

         1. alex7o · 1790407093 · focus · HN ↗

            Yea but a re-ranker can do that too if instruct trainrd. You update the instruction on which it is ranking the the values, a.k.a it is classifying them.

Unofficial Hacker News client; not affiliated with Y Combinator.