causal

Emergent capabilities come from compositional generalization

Emergent capabilities in LLMs arise not merely from internet data abundance but from compositional generalization: once generalization reaches a level, the model can combine known elements in novel ways (e.g. writing a recipe in the International Phonetic Alphabet despite never seeing that combination), and the same compositionality emerges in robots at scale.

causalpending

Speaker

Sergey Levine

Evidence Quote

“Emergent capabilities don't just come from the fact that internet data has a lot of stuff in it. They also come from the fact that generalization, once it reaches a certain level, becomes compositional.”

Source

Fully autonomous robots are much closer than you think – Sergey Levine— Dwarkesh Patel Podcast
Created: 6/13/2026, 3:29:18 AM

Your notes

Loading notes...