korrents

Our readingWhat is a korrent?

On-policy distillation is probably a bit more accurate than off-policy, because it always uses the most up-to-date student model.

Drawn from what Sebastian Raschka said

LLMs

What Sebastian Raschka actually said

  1. Sebastian Raschka AI research engineer working on large language models
    So you can do it even on a different machine ahead of time, collect everything and then train. But on-policy would be a bit, I guess, even more accurate or better because it's always with the most up-to-date version of your student model.

    Watch from 0:13:24 plays here

    ↗Build A Reasoning Model From Scratch 8: Distillationyoutube.com

    17 Oct 2026 · video · 1h 21m · spoken · machine transcript

    All 23 korrents from this recordingthis one is 6th

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