The Shutdown Problem: An AI Engineering Puzzle for Decision Theorists

Elliott Thornley (Global Priorities Institute, University of Oxford)

GPI Working Paper No. 10-2024, forthcoming in Philosophical Studies

I explain and motivate 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 suggest 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. I end by noting that these theorems can guide our search for solutions to the problem.

Other working papers

Economic growth under transformative AI – Philip Trammell (Global Priorities Institute, Oxford University) and Anton Korinek (University of Virginia)

Industrialized countries have long seen relatively stable growth in output per capita and a stable labor share. AI may be transformative, in the sense that it may break one or both of these stylized facts. This review outlines the ways this may happen by placing several strands of the literature on AI and growth within a common framework. We first evaluate models in which AI increases output production, for example via increases in capital’s substitutability for labor…

‘The only ethical argument for positive 𝛿’? – Andreas Mogensen (Global Priorities Institute, Oxford University)

I consider whether a positive rate of pure intergenerational time preference is justifiable in terms of agent-relative moral reasons relating to partiality between generations, an idea I call ​discounting for kinship​. I respond to Parfit’s objections to discounting for kinship, but then highlight a number of apparent limitations of this…

On two arguments for Fanaticism – Jeffrey Sanford Russell (University of Southern California)

Should we make significant sacrifices to ever-so-slightly lower the chance of extremely bad outcomes, or to ever-so-slightly raise the chance of extremely good outcomes? Fanaticism says yes: for every bad outcome, there is a tiny chance of of extreme disaster that is even worse, and for every good outcome, there is a tiny chance of an enormous good that is even better.