Minds and Machines 30 (3):411-437 (2020)
Abstract |
This paper looks at philosophical questions that arise in the context of AI alignment. It defends three propositions. First, normative and technical aspects of the AI alignment problem are interrelated, creating space for productive engagement between people working in both domains. Second, it is important to be clear about the goal of alignment. There are significant differences between AI that aligns with instructions, intentions, revealed preferences, ideal preferences, interests and values. A principle-based approach to AI alignment, which combines these elements in a systematic way, has considerable advantages in this context. Third, the central challenge for theorists is not to identify ‘true’ moral principles for AI; rather, it is to identify fair principles for alignment that receive reflective endorsement despite widespread variation in people’s moral beliefs. The final part of the paper explores three ways in which fair principles for AI alignment could potentially be identified.
|
Keywords | No keywords specified (fix it) |
Categories | (categorize this paper) |
ISBN(s) | |
DOI | 10.1007/s11023-020-09539-2 |
Options |
![]() ![]() ![]() ![]() |
Download options
References found in this work BETA
View all 74 references / Add more references
Citations of this work BETA
Decolonial AI: Decolonial Theory as Sociotechnical Foresight in Artificial Intelligence.Shakir Mohamed, Marie-Therese Png & William Isaac - 2020 - Philosophy and Technology 33 (4):659-684.
Ethics-based auditing of automated decision-making systems: nature, scope, and limitations.Jakob Mökander, Jessica Morley, Mariarosaria Taddeo & Luciano Floridi - 2021 - Science and Engineering Ethics 27 (4):1–30.
Human Goals Are Constitutive of Agency in Artificial Intelligence.Elena Popa - 2021 - Philosophy and Technology 34 (4):1731-1750.
Where Bioethics Meets Machine Ethics.Anna C. F. Lewis - 2020 - American Journal of Bioethics 20 (11):22-24.
Challenges of Aligning Artificial Intelligence with Human Values.Margit Sutrop - 2020 - Acta Baltica Historiae Et Philosophiae Scientiarum 8 (2):54-72.
View all 9 citations / Add more citations
Similar books and articles
The Value Alignment Problem: A Geometric Approach.Martin Peterson - 2019 - Ethics and Information Technology 21 (1):19-28.
Shared Moral Foundations of Embodied Artificial Intelligence.Joe Cruz - 2019 - In Vincent Conitzer, Gillian Hadfield & Shannon Vallor (eds.), AIES '19: Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society. pp. 139-146.
Robustness to Fundamental Uncertainty in AGI Alignment.G. G. Worley Iii - 2020 - Journal of Consciousness Studies 27 (1-2):225-241.
A Dashboard to Improve the Alignment of Healthcare Organization Decisionmaking to Core Values and Mission Statement.Timothy Lahey & William Nelson - 2020 - Cambridge Quarterly of Healthcare Ethics 29 (1):156-162.
Sharing Vocabularies: Towards Horizontal Alignment of Values-Driven Business Functions.Mollie Painter, Sareh Pouryousefi, Sally Hibbert & Jo-Anna Russon - 2019 - Journal of Business Ethics 155 (4):965-979.
Alignment and Commitment in Joint Action.Matthew Rachar - 2018 - Philosophical Psychology 31 (6):831-849.
Interactive Alignment: Priming or Memory Retrieval?Michael Kaschak & Arthur Glenberg - 2004 - Behavioral and Brain Sciences 27 (2):201-202.
Machines Learning Values.Steve Petersen - 2020 - In S. Matthew Liao (ed.), Ethics of Artificial Intelligence. New York, USA: Oxford University Press.
The Emergence of Active/Stative Alignment in Otomi.Enrique L. Palancar - 2008 - In Mark Donohue & Søren Wichmann (eds.), The Typology of Semantic Alignment. Oxford University Press.
Analytics
Added to PP index
2020-10-02
Total views
86 ( #133,600 of 2,497,999 )
Recent downloads (6 months)
22 ( #39,059 of 2,497,999 )
2020-10-02
Total views
86 ( #133,600 of 2,497,999 )
Recent downloads (6 months)
22 ( #39,059 of 2,497,999 )
How can I increase my downloads?
Downloads