normative

Dreaming Versus Compaction as Continual Learning

Hitting compact on a coding agent spends a small amount of compute to write a summary and gives a simulacrum of continual learning, whereas a /dream command would spend huge compute to build and train against a simulated version of what the model witnesses.

normativepending

Speaker

Dwarkesh Patel

Evidence Quote

“which gives you a simulacrum of continual learning, you hit /dream, which incinerates huge amounts of compute”

Source

Dwarkesh Patel Podcast - The next big breakthrough will be AIs learning on the job— Dwarkesh Patel Podcast
Created: 11/17/2026, 6:25:50 AM

Your notes

Loading notes...