factual

Twenty-year horizon makes longevity a hard RL problem

Selecting for longevity is like a long-horizon reinforcement learning problem with a ~20-year horizon and a sparse scalar reward (number of surviving offspring), which is surprising it works at all given how difficult RL is for models even on intermediate hour-long goals.

factualpending

Speaker

Dwarkesh Patel

Evidence Quote

“it's surprising that any signal propagates across a 20-year horizon.”

Source

Evolution designed us to die fast; we can change that — Jacob Kimmel— Dwarkesh Patel Podcast
Created: 6/13/2026, 3:28:32 AM

Your notes

Loading notes...