It Only Takes One: The Psychology of Unilateral Decisions

Joshua Lewis (New York University), Carter Allen (UC Berkeley), Christoph Winter (ITAM, Harvard University and Institute for Law & AI) and Lucius Caviola (Global Priorities Institute, Oxford University)

GPI Working Paper No. 14-2024

Sometimes, one decision can guarantee that a risky event will happen. For instance, it only took one team of researchers to synthesize and publish the horsepox genome, thus imposing its publication even though other researchers might have refrained for biosecurity reasons. We examine cases where everybody who can impose a given event has the same goal but different information about whether the event furthers that goal. Across 8 experiments (including scenario studies with elected policymakers, doctors, artificial-intelligence researchers, and lawyers and judges and economic games with laypeople, N = 1,518, and 3 supplemental studies, N = 847) people behave suboptimally, balancing two factors. First, people often impose events with expected utility only slightly better than the alternative based on the information available to them, even when others might know more. This approach is insufficiently cautious, leading people to impose too frequently, a situation termed the unilateralist’s curse. Second, counteracting the first factor, people avoid sole responsibility for unexpectedly bad outcomes, sometimes declining to impose seemingly desirable events. The former heuristic typically dominates and people unilaterally impose too often, succumbing to the unilateralist’s curse. But when only few people can impose, who know the stakes are high, responsibility aversion reduces over-imposing.

Other working papers

The Shutdown Problem: An AI Engineering Puzzle for Decision Theorists – Elliott Thornley (Global Priorities Institute, University of Oxford)

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…

Concepts of existential catastrophe – Hilary Greaves (University of Oxford)

The notion of existential catastrophe is increasingly appealed to in discussion of risk management around emerging technologies, but it is not completely clear what this notion amounts to. Here, I provide an opinionated survey of the space of plausibly useful definitions of existential catastrophe. Inter alia, I discuss: whether to define existential catastrophe in ex post or ex ante terms, whether an ex ante definition should be in terms of loss of expected value or loss of potential…

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…