Under the big-world hypothesis, agents become useful on the job by encountering their particular, unanticipatable part of a world too huge to pre-load; the LLM dream of teaching the agent everything in advance fails because of all the idiosyncrasies of a particular life, so the agent must learn it along the way into its weights (not just a context window).
causalpending
Speaker
Richard SuttonEvidence Quote
“The world is so huge that you can't. The dream of large language models, as I see it, is you can teach the agent everything... That's just saying the world is really big, and you're going to have to learn it along the way.”
Created: 6/18/2026, 1:59:29 PM
Your notes
Loading notes...