The Shutdown Problem: An AI Engineering Puzzle for Decision Theorists

Philosophical Studies:1-28 (forthcoming)
  Copy   BIBTEX

Abstract

I explain the shutdown problem: the problem of designing artificial agents that (1) shut down when a shutdown button is pressed, (2) don’t try to prevent or cause the pressing of the shutdown button, and (3) otherwise pursue goals competently. I prove three theorems that make the difficulty precise. These theorems show that agents satisfying some innocuous-seeming conditions will often try to prevent or cause the pressing of the shutdown button, even in cases where it’s costly to do so. And patience trades off against shutdownability: the more patient an agent, the greater the costs that agent is willing to incur to manipulate the shutdown button. I end by noting that these theorems can guide our search for solutions.

Similar books and articles

Analytics

Added to PP
2023-10-23

Downloads
781 (#22,025)

6 months
466 (#3,862)

Historical graph of downloads
How can I increase my downloads?

Author's Profile

Elliott Thornley
University of Oxford

References found in this work

The Morality of Freedom.Joseph Raz - 1986 - Philosophy 63 (243):119-122.
Money-Pump Arguments.Johan E. Gustafsson - 2022 - Cambridge: Cambridge University Press.
Shutdown-seeking AI.Simon Goldstein & Pamela Robinson - forthcoming - Philosophical Studies:1-13.

View all 7 references / Add more references