On the computational complexity of ethics : moral tractability for minds and machines
(2024) In Artificial Intelligence Review 57(105).- Abstract
- Why should moral philosophers, moral psychologists, and machine ethicists care about computational complexity? Debates on whether artificial intelligence (AI) can or should be used to solve problems in ethical domains have mainly been driven by what AI can or cannot do in terms of human capacities. In this paper, we tackle the problem from the other end by exploring what kind of moral machines are possible based on what computational systems can or cannot do. To do so, we analyze normative ethics through the lens of computational complexity. First, we introduce computational complexity for the uninitiated reader and discuss how the complexity of ethical problems can be framed within Marr’s three levels of analysis. We then study a range of... (More)
- Why should moral philosophers, moral psychologists, and machine ethicists care about computational complexity? Debates on whether artificial intelligence (AI) can or should be used to solve problems in ethical domains have mainly been driven by what AI can or cannot do in terms of human capacities. In this paper, we tackle the problem from the other end by exploring what kind of moral machines are possible based on what computational systems can or cannot do. To do so, we analyze normative ethics through the lens of computational complexity. First, we introduce computational complexity for the uninitiated reader and discuss how the complexity of ethical problems can be framed within Marr’s three levels of analysis. We then study a range of ethical problems based on consequentialism, deontology, and virtue ethics, with the aim of elucidating the complexity associated with the problems themselves (e.g., due to combinatorics, uncertainty, strategic dynamics), the computational methods employed (e.g., probability, logic, learning), and the available resources (e.g., time, knowledge, learning). The results indicate that most problems the normative frameworks pose lead to tractability issues in every category analyzed. Our investigation also provides several insights about the computational nature of normative ethics, including the differences between rule- and outcome-based moral strategies, and the implementation-variance with regard to moral resources. We then discuss the consequences complexity results have for the prospect of moral machines in virtue of the trade-off between optimality and efficiency. Finally, we elucidate how computational complexity can be used to inform both philosophical and cognitive-psychological research on human morality by advancing the moral tractability thesis. (Less)
- Abstract (Swedish)
- Why should moral philosophers, moral psychologists, and machine ethicists care about computational complexity? Debates on whether artificial intelligence (AI) can or should be used to solve problems in ethical domains have mainly been driven by what AI can or cannot do in terms of human capacities. In this paper, we tackle the problem from the other end by exploring what kind of moral machines are possible based on what computational systems can or cannot do. To do so, we analyze normative ethics through the lens of computational complexity. First, we introduce computational complexity for the uninitiated reader and discuss how the complexity of ethical problems can be framed within Marr’s three levels of analysis. We then study a range of... (More)
- Why should moral philosophers, moral psychologists, and machine ethicists care about computational complexity? Debates on whether artificial intelligence (AI) can or should be used to solve problems in ethical domains have mainly been driven by what AI can or cannot do in terms of human capacities. In this paper, we tackle the problem from the other end by exploring what kind of moral machines are possible based on what computational systems can or cannot do. To do so, we analyze normative ethics through the lens of computational complexity. First, we introduce computational complexity for the uninitiated reader and discuss how the complexity of ethical problems can be framed within Marr’s three levels of analysis. We then study a range of ethical problems based on consequentialism, deontology, and virtue ethics, with the aim of elucidating the complexity associated with the problems themselves (e.g., due to combinatorics, uncertainty, strategic dynamics), the computational methods employed (e.g., probability, logic, learning), and the available resources (e.g., time, knowledge, learning). The results indicate that most problems the normative frameworks pose lead to tractability issues in every category analyzed. Our investigation also provides several insights about the computational nature of normative ethics, including the differences between rule- and outcome-based moral strategies, and the implementation-variance with regard to moral resources. We then discuss the consequences complexity results have for the prospect of moral machines in virtue of the trade-off between optimality and efficiency. Finally, we elucidate how computational complexity can be used to inform both philosophical and cognitive-psychological research on human morality by advancing the moral tractability thesis. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/75adfc4d-0a94-4a71-a098-e9bbcdfa4c87
- author
- Stenseke, Jakob LU
- organization
- publishing date
- 2024-03-31
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Computational complexity, Machine ethics, Artificial moral agents, Consequentialism, Deontology, Virtue ethics, Computational complexity, Machine ethics, Artificial moral agents, Consequentialism, Deontology, Virtue ethics
- in
- Artificial Intelligence Review
- volume
- 57
- issue
- 105
- article number
- 105
- pages
- 90 pages
- publisher
- Springer Nature
- external identifiers
-
- scopus:85189081842
- ISSN
- 1573-7462
- DOI
- 10.1007/s10462-024-10732-3
- project
- How to build nice robots: ethics from theory to machine implementations
- Ethics for autonomous systems/AI
- Instrumental and normative expectations in a social robot
- language
- English
- LU publication?
- yes
- id
- 75adfc4d-0a94-4a71-a098-e9bbcdfa4c87
- date added to LUP
- 2024-04-08 08:25:14
- date last changed
- 2024-04-12 14:43:22
@article{75adfc4d-0a94-4a71-a098-e9bbcdfa4c87,
abstract = {{Why should moral philosophers, moral psychologists, and machine ethicists care about computational complexity? Debates on whether artificial intelligence (AI) can or should be used to solve problems in ethical domains have mainly been driven by what AI can or cannot do in terms of human capacities. In this paper, we tackle the problem from the other end by exploring what kind of moral machines are possible based on what computational systems can or cannot do. To do so, we analyze normative ethics through the lens of computational complexity. First, we introduce computational complexity for the uninitiated reader and discuss how the complexity of ethical problems can be framed within Marr’s three levels of analysis. We then study a range of ethical problems based on consequentialism, deontology, and virtue ethics, with the aim of elucidating the complexity associated with the problems themselves (e.g., due to combinatorics, uncertainty, strategic dynamics), the computational methods employed (e.g., probability, logic, learning), and the available resources (e.g., time, knowledge, learning). The results indicate that most problems the normative frameworks pose lead to tractability issues in every category analyzed. Our investigation also provides several insights about the computational nature of normative ethics, including the differences between rule- and outcome-based moral strategies, and the implementation-variance with regard to moral resources. We then discuss the consequences complexity results have for the prospect of moral machines in virtue of the trade-off between optimality and efficiency. Finally, we elucidate how computational complexity can be used to inform both philosophical and cognitive-psychological research on human morality by advancing the moral tractability thesis.}},
author = {{Stenseke, Jakob}},
issn = {{1573-7462}},
keywords = {{Computational complexity; Machine ethics; Artificial moral agents; Consequentialism; Deontology; Virtue ethics; Computational complexity; Machine ethics; Artificial moral agents; Consequentialism; Deontology; Virtue ethics}},
language = {{eng}},
month = {{03}},
number = {{105}},
publisher = {{Springer Nature}},
series = {{Artificial Intelligence Review}},
title = {{On the computational complexity of ethics : moral tractability for minds and machines}},
url = {{http://dx.doi.org/10.1007/s10462-024-10732-3}},
doi = {{10.1007/s10462-024-10732-3}},
volume = {{57}},
year = {{2024}},
}