Off-Switching Not Guaranteed

Philosophical Studies:1-13 (forthcoming)
  Copy   BIBTEX

Abstract

Hadfield-Menell et al. (2017) propose the Off-Switch Game, a model of Human-AI cooperation in which AI agents always defer to humans because they are uncertain about our preferences. I explain two reasons why AI agents might not defer. First, AI agents might not value learning. Second, even if AI agents value learning, they might not be certain to learn our actual preferences.

Categories

Keywords

Reprint years

DOI

10.1007/s11098-025-02296-x

Other Versions

No versions found

Links

PhilArchive

External links

Setup an account with your affiliations in order to access resources via your University's proxy server

Through your library

My notes

Similar books and articles

Moral Gridworlds: A Theoretical Proposal for Modeling Artificial Moral Cognition.Julia Haas - 2020 - Minds and Machines 30 (2):219-246.
Domesticating Artificial Intelligence.Luise Müller - 2022 - Moral Philosophy and Politics 9 (2):219-237.
Incentivized Symbiosis: A Paradigm for Human-Agent Coevolution.Tomer Jordi Chaffer, Justin Goldston & Gemach D. A. T. A. I. - manuscript
The Puzzle of Evaluating Moral Cognition in Artificial Agents.Madeline G. Reinecke, Yiran Mao, Markus Kunesch, Edgar A. Duéñez-Guzmán, Julia Haas & Joel Z. Leibo - 2023 - Cognitive Science 47 (8):e13315.
Exploring Affinity-Based Reinforcement Learning for Designing Artificial Virtuous Agents in Stochastic Environments.Ajay Vishwanath & Christian Omlin - 2024 - In Mina Farmanbar, Maria Tzamtzi, Ajit Kumar Verma & Antorweep Chakravorty, Frontiers of Artificial Intelligence, Ethics, and Multidisciplinary Applications: 1st International Conference on Frontiers of AI, Ethics, and Multidisciplinary Applications (FAIEMA), Greece, 2023. Springer Nature Singapore. pp. 25-38.
The linguistic dead zone of value-aligned agency, natural and artificial.Travis LaCroix - 2024 - Philosophical Studies:1-23.
Can We Govern the Agent-to-Agent Economy?Tomer Jordi Chaffer - manuscript
Streaching the notion of moral responsibility in nanoelectronics by appying AI.Robert Albin & Amos Bardea - 2021 - In Robert Albin & Amos Bardea, Ethics in Nanotechnology Social Sciences and Philosophical Aspects, Vol. 2. Berlin: De Gruyter. pp. 75-87.
The Shutdown Problem: Incomplete Preferences as a Solution.Elliott Thornley - manuscript

Analytics

Added to PP
2025-02-12

Downloads
322 (#96,451)

6 months
322 (#8,247)

Historical graph of downloads
How can I increase my downloads?

Author's Profile

Sven Neth
University of Pittsburgh

Citations of this work

Add more citations

References found in this work

The Foundations of Statistics.Leonard Savage - 1954 - Wiley Publications in Statistics.
Risk and Rationality.Lara Buchak - 2013 - Oxford, GB: Oxford University Press.
The Value of Biased Information.Nilanjan Das - 2023 - British Journal for the Philosophy of Science 74 (1):25-55.
Against the singularity hypothesis.David Thorstad - forthcoming - Philosophical Studies:1-25.

View all 27 references / Add more references