Saved in:
Bibliographic Details
Main Authors: Benavoli, Alessio, Facchini, Alessandro, Zaffalon, Marco
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.06403
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • The off-switch problem is a critical challenge in AI control: if an AI system resists being switched off, it poses a significant risk. In this paper, we model the off-switch problem as a signalling game, where a human decision-maker communicates its preferences about some underlying decision problem to an AI agent, which then selects actions to maximise the human's utility. We assume that the human is a bounded rational agent and explore various bounded rationality mechanisms. Using real machine learning models, we reprove prior results and demonstrate that a necessary condition for an AI system to refrain from disabling its off-switch is its uncertainty about the human's utility. We also analyse how message costs influence optimal strategies and extend the analysis to scenarios involving incomparability.