causal

Reward functions explain compact genome encoding

If a major part of intelligence is the reward/loss functions that aid sample-efficient learning, then the small information content of the genome (~3GB, only a fraction coding the brain) is explained: a reward function is just a line of Python, so a thousand such lines plus a compact learning algorithm and reusable architecture can specify an intelligence without storing a pretrained network.

causalpending

Speaker

Dwarkesh Patel

Evidence Quote

“if a big part of the story is that increased sample efficiency aids learning... and if evolution found those loss functions that aid learning—then it actually makes sense how you can build an intelligence with so little information.”

Source

Adam Marblestone – AI is missing something fundamental about the brain— Dwarkesh Patel Podcast
Created: 6/13/2026, 3:32:22 AM

Your notes

Loading notes...