Towards shutdownable agents via stochastic choice

Elliott Thornley (Global Priorities Institute, University of Oxford), Alexander Roman (New College of Florida), Christos Ziakas (Independent), Leyton Ho (Brown University) and Louis Thomson (University of Oxford)

GPI Working Paper No. 16-2024

Some worry that advanced artificial agents may resist being shut down. The Incomplete Preferences Proposal (IPP) is an idea for ensuring that doesn’t happen. A key part of the IPP is using a novel ‘Discounted REward for Same-Length Trajectories (DREST)’ reward function to train agents to (1) pursue goals effectively conditional on each trajectory-length (be ‘USEFUL’), and (2) choose stochastically between different trajectory-lengths (be ‘NEUTRAL’ about trajectory-lengths). In this paper, we propose evaluation metrics for USEFULNESS and NEUTRALITY. We use a DREST reward function to train simple agents to navigate gridworlds, and we find that these agents learn to be USEFUL and NEUTRAL. Our results thus suggest that DREST reward functions could also train advanced agents to be USEFUL and NEUTRAL, and thereby make these advanced agents useful and shutdownable.

Other working papers

How important is the end of humanity? Lay people prioritize extinction prevention but not above all other societal issues. – Matthew Coleman (Northeastern University), Lucius Caviola (Global Priorities Institute, University of Oxford) et al.

Human extinction would mean the deaths of eight billion people and the end of humanity’s achievements, culture, and future potential. On several ethical views, extinction would be a terrible outcome. How do people think about human extinction? And how much do they prioritize preventing extinction over other societal issues? Across six empirical studies (N = 2,541; U.S. and China) we find that people consider extinction prevention a global priority and deserving of greatly increased societal resources. …

How much should governments pay to prevent catastrophes? Longtermism’s limited role – Carl Shulman (Advisor, Open Philanthropy) and Elliott Thornley (Global Priorities Institute, University of Oxford)

Longtermists have argued that humanity should significantly increase its efforts to prevent catastrophes like nuclear wars, pandemics, and AI disasters. But one prominent longtermist argument overshoots this conclusion: the argument also implies that humanity should reduce the risk of existential catastrophe even at extreme cost to the present generation. This overshoot means that democratic governments cannot use the longtermist argument to guide their catastrophe policy. …

Is In-kind Kinder than Cash? The Impact of Money vs Food Aid on Social Emotions and Aid Take-up – Samantha Kassirer, Ata Jami, & Maryam Kouchaki (Northwestern University)

There has been widespread endorsement from the academic and philanthropic communities on the new model of giving cash to those in need. Yet the recipient’s perspective has mostly been ignored. The present research explores how food-insecure individuals feel and respond when offered either monetary or food aid from a charity. Our results reveal that individuals are less likely to accept money than food aid from charity because receiving money feels relatively more shameful and relatively less socially positive. Since many…