Games for AI Control: Models of Safety Evaluations of AI Deployment Protocols

To evaluate the safety and usefulness of deployment protocols for untrusted AIs, AI Control uses a red-teaming exercise played between a protocol designer and an adversary. This paper introduces AI-Control Games, a formal decision-making model of the red-teaming exercise as a multi-objective, partially observable, stochastic game. We also introduce methods for finding optimal protocols in AI-Control Games, by reducing them to a set of zero-sum partially observable stochastic games. We apply our formalism to model, evaluate and synthesise protocols for deploying untrusted language models as programming assistants, focusing on Trusted Monitoring protocols, which use weaker language models and limited human assistance. Finally, we demonstrate the utility of our formalism by showcasing improvements over empirical studies in existing settings, evaluating protocols in new settings, and analysing how modelling assumptions affect the safety and usefulness of protocols.

Towards shutdownable agents via stochastic choice

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.