causal

Alignment And Values Won't Emerge From Scale

Alignment and values are not guaranteed to emerge from scaling because a model trained to predict the world learns facts, not values; predicting the next token leaves free variables about what one should do, think, or value that the training signal does not constrain, so these will not emerge on their own.

causalpending

Speaker

Dario Amodei (Anthropic CEO)

Evidence Quote

“Its job is facts not values. It's trying to predict what comes next. But there's free variables here — What should you do? What should you think? What should you value? There aren't bits for that.”

Source

Dario Amodei (Anthropic CEO) — The hidden pattern behind every AI breakthrough— Dwarkesh Patel Podcast
Created: 6/13/2026, 3:25:28 AM

Your notes

Loading notes...