Our readingWhat is a korrent?
A KL loss term is very important in domains with a lot of reward hacking but usually not necessary for math models.
Drawn from what Sebastian Raschka said
SubjectAI alignment
Our readingWhat is a korrent?
Drawn from what Sebastian Raschka said
Now in domains where there's a lot of reward hacking, this is very important, but in other domains, for example, our math verifier, this is usually not necessary. So personally, when I trained math models, so models that generate math answers correctly, I found that it's usually not that necessary.
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 tooShared subject first, then similar wording. They may agree or disagree.