causal

Humans don't use RL for intelligence

Most animal reinforcement learning is for motor tasks, not intelligence tasks; a lot of what looks like learning is actually maturation, so humans largely do not use reinforcement learning for problem-solving and high-level cognition.

causalpending

Speaker

Andrej Karpathy

Evidence Quote

“A lot of the reinforcement learning is more like motor tasks; it's not intelligence tasks. So I actually kind of think humans don't really use RL”

Source

Andrej Karpathy — AGI is still a decade away— Dwarkesh Patel Podcast
Created: 6/13/2026, 3:26:44 AM

Your notes

Loading notes...