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
Will AI Avoid Exploitation? – Adam Bales (Global Priorities Institute, University of Oxford)
A simple argument suggests that we can fruitfully model advanced AI systems using expected utility theory. According to this argument, an agent will need to act as if maximising expected utility if they’re to avoid exploitation. Insofar as we should expect advanced AI to avoid exploitation, it follows that we should expected advanced AI to act as if maximising expected utility. I spell out this argument more carefully and demonstrate that it fails, but show that the manner of its failure is instructive…
What power-seeking theorems do not show – David Thorstad (Vanderbilt University)
Recent years have seen increasing concern that artificial intelligence may soon pose an existential risk to humanity. One leading ground for concern is that artificial agents may be power-seeking, aiming to acquire power and in the process disempowering humanity. A range of power-seeking theorems seek to give formal articulation to the idea that artificial agents are likely to be power-seeking. I argue that leading theorems face five challenges, then draw lessons from this result.
Three mistakes in the moral mathematics of existential risk – David Thorstad (Global Priorities Institute, University of Oxford)
Longtermists have recently argued that it is overwhelmingly important to do what we can to mitigate existential risks to humanity. I consider three mistakes that are often made in calculating the value of existential risk mitigation: focusing on cumulative risk rather than period risk; ignoring background risk; and neglecting population dynamics. I show how correcting these mistakes pushes the value of existential risk mitigation substantially below leading estimates, potentially low enough to…