GPI's research agenda
The central focus of GPI is what we call 'global priorities research': research into issues that arise in response to the question, 'What should we do with a given amount of limited resources if our aim is to do the most good?'. This question naturally draws upon central themes in the fields of economics, philosophy and psychology. Browse through GPI's research agenda to find out more.
Our papers
Evolutionary debunking and value alignment – Michael T. Dale (Hampden-Sydney College) and Bradford Saad (Global Priorities Institute, University of Oxford)
This paper examines the bearing of evolutionary debunking arguments—which use the evolutionary origins of values to challenge their epistemic credentials—on the alignment problem, i.e. the problem of ensuring that highly capable AI systems are properly aligned with values. Since evolutionary debunking arguments are among the best empirically-motivated arguments that recommend changes in values, it is unsurprising that they are relevant to the alignment problem. However, how evolutionary debunking arguments…
Read MoreThe 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…
Read MoreInput to UN Interim Report on Governing AI for Humanity
This document was written by Bradford Saad, with assistance from Andreas Mogensen and Jeff Sebo. Jakob Lohmar provided valuable research assistance. The document benefited from discussion with or feedback from Frankie Andersen-Wood, Adam Bales, Ondrej Bajgar, Thomas Houlden, Jojo Lee, Toby Ord, Teruji Thomas, Elliot Thornley and Eva Vivalt.
Read More
