factual
Alignment Fine-Tuning Doesn't Remove Knowledge
When a model is trained to be aligned, we don't actually know what happens inside it; current fine-tuning methods have the property that the underlying knowledge and dangerous abilities don't disappear — the model is merely taught not to output them — and it's unknown whether this is a fatal flaw or simply how things must be.
factualpending
Speaker
Dario Amodei (Anthropic CEO)Evidence Quote
“we don't really know what happens. 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.”
Source
Dario Amodei (Anthropic CEO) — The hidden pattern behind every AI breakthrough— Dwarkesh Patel PodcastCreated: 6/13/2026, 3:25:28 AM
Your notes
Loading notes...