Our readingWhat is a korrent?
Fine-tuning-based alignment does not remove a model's worrying knowledge and abilities; it only teaches the model not to output them.
Drawn from what Dario Amodei said
Our readingWhat is a korrent?
Drawn from what Dario Amodei said
all the current methods that involve some kind of fine-tuning, of course, have the property that the underlying knowledge and abilities that we might be worried about don't disappear. The model is just taught not to output them.
Added to korrents 8 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.