korrents

Our readingWhat is a korrent?

When a KL loss term is not needed, it is just overhead, since it requires keeping an extra reference model in memory.

Drawn from what Sebastian Raschka said

What this subject means

software performance Speed as a mark of quality: bloat, boot times, and software that got slower on hardware that got faster.

What Sebastian Raschka actually said

  1. Sebastian Raschka AI research engineer working on large language models
    They also omitted this KL loss term because it's just making the training more expensive. You have an additional reference model. You have to keep in memory and compute scores for that. And if you don't need that, it's just additional overhead.

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