Value Alignment, Fair Play, and the Rights of Service Robots

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Ethics and safety research in artificial intelligence is increasingly framed in terms of "alignment" with human values and interests. I argue that Turing's call for "fair play for machines" is an early and often overlooked contribution to the alignment literature. Turing's appeal to fair play suggests a need to correct human behavior to accommodate our machines, a surprising inversion of how value alignment is treated today. Reflections on "fair play" motivate a novel interpretation of Turing's notorious "imitation game" as a condition not of intelligence but instead of value alignment: a machine demonstrates a minimal degree of alignment (with the norms of conversation, for instance) when it can go undetected when interrogated by a human. I carefully distinguish this interpretation from the Moral Turing Test, which is not motivated by a principle of fair play, but instead depends on imitation of human moral behavior. Finally, I consider how the framework of fair play can be used to situate the debate over robot rights within the alignment literature. I argue that extending rights to service robots operating in public spaces is "fair" in precisely the sense that it encourages an alignment of interests between humans and machines.

Original languageEnglish (US)
Title of host publicationAIES 2018 - Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society
PublisherAssociation for Computing Machinery, Inc
Pages102-107
Number of pages6
ISBN (Electronic)9781450360128
DOIs
StatePublished - Dec 27 2018
Event1st AAAI/ACM Conference on AI, Ethics, and Society, AIES 2018 - New Orleans, United States
Duration: Feb 2 2018Feb 3 2018

Publication series

NameAIES 2018 - Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society

Conference

Conference1st AAAI/ACM Conference on AI, Ethics, and Society, AIES 2018
CountryUnited States
CityNew Orleans
Period2/2/182/3/18

Fingerprint

Fair Play
Alignment
Robot
Imitation
Inversion
Turing Test
Human Values
Artificial Intelligence
Safety
Human Behavior
Public Space

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Cite this

Estrada, D. (2018). Value Alignment, Fair Play, and the Rights of Service Robots. In AIES 2018 - Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society (pp. 102-107). (AIES 2018 - Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society). Association for Computing Machinery, Inc. https://doi.org/10.1145/3278721.3278730
Estrada, Daniel. / Value Alignment, Fair Play, and the Rights of Service Robots. AIES 2018 - Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society. Association for Computing Machinery, Inc, 2018. pp. 102-107 (AIES 2018 - Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society).
@inproceedings{0308f59adcc0461f8d12e9a6a916663a,
title = "Value Alignment, Fair Play, and the Rights of Service Robots",
abstract = "Ethics and safety research in artificial intelligence is increasingly framed in terms of {"}alignment{"} with human values and interests. I argue that Turing's call for {"}fair play for machines{"} is an early and often overlooked contribution to the alignment literature. Turing's appeal to fair play suggests a need to correct human behavior to accommodate our machines, a surprising inversion of how value alignment is treated today. Reflections on {"}fair play{"} motivate a novel interpretation of Turing's notorious {"}imitation game{"} as a condition not of intelligence but instead of value alignment: a machine demonstrates a minimal degree of alignment (with the norms of conversation, for instance) when it can go undetected when interrogated by a human. I carefully distinguish this interpretation from the Moral Turing Test, which is not motivated by a principle of fair play, but instead depends on imitation of human moral behavior. Finally, I consider how the framework of fair play can be used to situate the debate over robot rights within the alignment literature. I argue that extending rights to service robots operating in public spaces is {"}fair{"} in precisely the sense that it encourages an alignment of interests between humans and machines.",
author = "Daniel Estrada",
year = "2018",
month = "12",
day = "27",
doi = "https://doi.org/10.1145/3278721.3278730",
language = "English (US)",
series = "AIES 2018 - Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society",
publisher = "Association for Computing Machinery, Inc",
pages = "102--107",
booktitle = "AIES 2018 - Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society",

}

Estrada, D 2018, Value Alignment, Fair Play, and the Rights of Service Robots. in AIES 2018 - Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society. AIES 2018 - Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society, Association for Computing Machinery, Inc, pp. 102-107, 1st AAAI/ACM Conference on AI, Ethics, and Society, AIES 2018, New Orleans, United States, 2/2/18. https://doi.org/10.1145/3278721.3278730

Value Alignment, Fair Play, and the Rights of Service Robots. / Estrada, Daniel.

AIES 2018 - Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society. Association for Computing Machinery, Inc, 2018. p. 102-107 (AIES 2018 - Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Value Alignment, Fair Play, and the Rights of Service Robots

AU - Estrada, Daniel

PY - 2018/12/27

Y1 - 2018/12/27

N2 - Ethics and safety research in artificial intelligence is increasingly framed in terms of "alignment" with human values and interests. I argue that Turing's call for "fair play for machines" is an early and often overlooked contribution to the alignment literature. Turing's appeal to fair play suggests a need to correct human behavior to accommodate our machines, a surprising inversion of how value alignment is treated today. Reflections on "fair play" motivate a novel interpretation of Turing's notorious "imitation game" as a condition not of intelligence but instead of value alignment: a machine demonstrates a minimal degree of alignment (with the norms of conversation, for instance) when it can go undetected when interrogated by a human. I carefully distinguish this interpretation from the Moral Turing Test, which is not motivated by a principle of fair play, but instead depends on imitation of human moral behavior. Finally, I consider how the framework of fair play can be used to situate the debate over robot rights within the alignment literature. I argue that extending rights to service robots operating in public spaces is "fair" in precisely the sense that it encourages an alignment of interests between humans and machines.

AB - Ethics and safety research in artificial intelligence is increasingly framed in terms of "alignment" with human values and interests. I argue that Turing's call for "fair play for machines" is an early and often overlooked contribution to the alignment literature. Turing's appeal to fair play suggests a need to correct human behavior to accommodate our machines, a surprising inversion of how value alignment is treated today. Reflections on "fair play" motivate a novel interpretation of Turing's notorious "imitation game" as a condition not of intelligence but instead of value alignment: a machine demonstrates a minimal degree of alignment (with the norms of conversation, for instance) when it can go undetected when interrogated by a human. I carefully distinguish this interpretation from the Moral Turing Test, which is not motivated by a principle of fair play, but instead depends on imitation of human moral behavior. Finally, I consider how the framework of fair play can be used to situate the debate over robot rights within the alignment literature. I argue that extending rights to service robots operating in public spaces is "fair" in precisely the sense that it encourages an alignment of interests between humans and machines.

UR - http://www.scopus.com/inward/record.url?scp=85061050585&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85061050585&partnerID=8YFLogxK

U2 - https://doi.org/10.1145/3278721.3278730

DO - https://doi.org/10.1145/3278721.3278730

M3 - Conference contribution

T3 - AIES 2018 - Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society

SP - 102

EP - 107

BT - AIES 2018 - Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society

PB - Association for Computing Machinery, Inc

ER -

Estrada D. Value Alignment, Fair Play, and the Rights of Service Robots. In AIES 2018 - Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society. Association for Computing Machinery, Inc. 2018. p. 102-107. (AIES 2018 - Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society). https://doi.org/10.1145/3278721.3278730