korrents

Our readingWhat is a korrent?

Human preference rankings for RLHF are partly subjective, because raters with limited time cannot always check which answer is correct.

Drawn from what Sebastian Raschka said

What these subjects mean

taste Whether good and bad exist in made things, and how a maker comes to tell them apart.

reinforcement learning Training by reward: environments, verifiable tasks, value functions, and whether it works or merely beats what came before.

What Sebastian Raschka actually said

  1. Sebastian Raschka AI research engineer working on large language models
    But you can imagine if you are having to rank answers, and you have to only so much time to rank them, you can't always double check which one is the correct answer. You're sometimes also just ranking them by, well, I like this explanation better, for example.

Added to korrents 9 Nov 2026 · How quotes work · Something wrong? Tell us

Do you hold this korrent?Do you also believe this?

I hold this too

Related korrents

Shared subject first, then similar wording. They may agree or disagree.

See this claim on the map