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
Longtermist political philosophy: An agenda for future research – Jacob Barrett (Global Priorities Institute, University of Oxford) and Andreas T. Schmidt (University of Groningen)
We set out longtermist political philosophy as a research field. First, we argue that the standard case for longtermism is more robust when applied to institutions than to individual action. This motivates “institutional longtermism”: when building or shaping institutions, positively affecting the value of the long-term future is a key moral priority. Second, we briefly distinguish approaches to pursuing longtermist institutional reform along two dimensions: such approaches may be more targeted or more broad, and more urgent or more patient.
Imperfect Recall and AI Delegation – Eric Olav Chen (Global Priorities Institute, University of Oxford), Alexis Ghersengorin (Global Priorities Institute, University of Oxford) and Sami Petersen (Department of Economics, University of Oxford)
A principal wants to deploy an artificial intelligence (AI) system to perform some task. But the AI may be misaligned and aim to pursue a conflicting objective. The principal cannot restrict its options or deliver punishments. Instead, the principal is endowed with the ability to impose imperfect recall on the agent. The principal can then simulate the task and obscure whether it is real or part of a test. This allows the principal to screen misaligned AIs during testing and discipline their behaviour in deployment. By increasing the…
The paralysis argument – William MacAskill, Andreas Mogensen (Global Priorities Institute, Oxford University)
Given plausible assumptions about the long-run impact of our everyday actions, we show that standard non-consequentialist constraints on doing harm entail that we should try to do as little as possible in our lives. We call this the Paralysis Argument. After laying out the argument, we consider and respond to…