factual

Evolution And LLMs Build Agents In Opposite Order

Evolution does meta-RL to make an RL agent that can selectively do imitation learning, whereas with LLMs we go the opposite way: first building a base model that does pure imitation learning, then doing RL on it to make it a coherent agent with goals and self-awareness.

factualpending

Speaker

Dwarkesh Patel

Evidence Quote

“With LLMs, we’re going the opposite way. We first made a base model that does pure imitation learning. Then we do RL on it to make it a coherent agent with goals and self-awareness.”

Source

Some thoughts on the Sutton interview— Dwarkesh Patel Podcast
Created: 6/13/2026, 3:28:01 AM

Your notes

Loading notes...