normative

Human oversight as a self-improvement safeguard

A practical safeguard against runaway self-improvement is to keep a human in charge of the algorithmic research loop—the system explores the space and produces results, but a person decides whether to incorporate a given learning algorithm or change into the core code base—plus exposing capabilities only through APIs or interfaces that allow monitoring and boundaries, so you get the benefits of self-improvement without letting the system go fully autonomous.

normativepending

Speaker

Jeff Dean

Evidence Quote

“there's still a human in charge of that... we're going to make a decision, like, are we going to incorporate this particular, you know, learning algorithm or change to the system into kind of the core code base?”

Source

Jeff Dean & Noam Shazeer — 25 years at Google: from PageRank to AGI— Dwarkesh Patel Podcast
Created: 6/13/2026, 3:30:41 AM

Your notes

Loading notes...