korrents

Our readingWhat is a korrent?

It is more common to train only on answer tokens than on prompt tokens.

Drawn from what Sebastian Raschka said

LLMs

What Sebastian Raschka actually said

  1. Sebastian Raschka AI research engineer working on large language models
    But long story short, it is more common to only train on the answer tokens rather than the prompt tokens. It's just like also a common convention.

    Watch from 0:48:31 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 14th

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