ABSTRACT
Sophisticated AI's will make decisions about how to respond to complex situations, and we may wonder whether those decisions will align with the moral values of human beings. I argue that pessimistic worries about this value alignment problem are overstated. In order to achieve intelligence in its full generality and adaptiveness, cognition in AI's will need to be embodied in the sense of the Embodied Cognition research program. That embodiment will yield AI's that share our moral foundations, namely coordination, sociality, and acknowledgement of shared resources. Consequently, we can expect a broad moral alignment between human beings and AI's. AI's will likely show no more variation in their values than we find amongst human beings.
- Anderson, M. 2003. Embodied Cognition: A Field Guide. Artificial Intelligence, 149 (1):91--130. Google ScholarDigital Library
- Beer, R. 1990. Intelligence as Adaptive Behavior: An Experiment in Computational Neuroethology. San Diego: Academic Press. Google ScholarDigital Library
- Bostrom, N. 2012. The Superintelligent Will: Motivation and Instrumental Rationality in Advanced Artificial Agents. Minds and Machines 22(2), May:71--85. Google ScholarDigital Library
- Brooks, R. 1991. Intelligence without representation. Artificial Intelligence. 47(3):139--159. Google ScholarDigital Library
- Chemero, A. 2009. Radical Embodied Cognitive Science. Cambridge, MA: MIT Press.Google Scholar
- Cherniak, C. 1986. Minimal Rationality. Cambridge, MIT Press.Google Scholar
- Chiel, H., and Beer, R. 1997. The brain has a body: adaptive behavior emerges from interactions of nervous system, body and environment. Trends in Neuroscience 20(12):553--557.Google ScholarCross Ref
- Clark, A. 1997. Being There: Putting Brain Body and World Together Again. Cambridge, MA: MIT Press. Google ScholarDigital Library
- Clark, A. 2010. Supersizing the Mind: Embodiment, Action, and Cognitive Extension. Oxford UP.Google Scholar
- Descartes, R. 1641/2015. Meditations on First Philosophy with Selections from Objections and Replies. Cottingham, J., ed. Cambridge: Cambridge UP.Google Scholar
- Gallese, V., and Lakoff, G. 2005. The brain's concepts: The role of the sensorimotor system in conceptual knowledge. Cognitive Neuropsychology 21:455--479.Google ScholarCross Ref
- Greene, J., and Haidt, J. 2002. How (and where) does moral judgment work? Trends in Cognitive Sciences 6(12):517--523.Google ScholarCross Ref
- Haidt, J.; Koller, S.H.; and Dias, M.G. 1993. Affect, Culture, and Morality, or Is It Wrong to Eat Your Dog? Journal of Personality and Social Psychology 65(4):613--628.Google ScholarCross Ref
- Haidt, J.; Craig, J. 2004. Intuitive ethics: how innately prepared intuitions generate culturally variable virtues. Daedalus 133(4): 55--66.Google Scholar
- Haidt, J. 2012. The Righteous Mind: Why Good People are Divided by Politics and Religion. New York: Pantheon Books.Google Scholar
- Hare, B., and Tomasello, M. 2005. Human-like social skills in dogs? Trends in Cognitive Science 9:439--444.Google ScholarCross Ref
- Hume, D. 1736/1978. A Treatise of Human Nature. Selby-Bigge, L.A., ed. Oxford: Oxford UP.Google Scholar
- Hutchins, E. 1995. Cognition in the Wild. Cambridge, MA: MIT Press.Google Scholar
- Kirsh, D., and Maglio, P. 1994. On distinguishing epistemic from pragmatic action. Cognitive Science 18(4): 513--549.Google ScholarDigital Library
- Kristan, W. et al. 2000. Biomechanics of Hydroskeletons: Studies of Crawling in the Medicinal Leech. In Biomechanics and Neural Control of Movement, Winters, J. and Crago, P., eds. Springer-Verlag.Google Scholar
- Lakoff, G., and Johnson, M. 1999. Philosophy in the Flesh: The Embodied Mind And Its Challenge To Western Thought. New York, NY: Basic Books.Google Scholar
- Langton, C., ed. 1989. Artificial Life. Redwood City, CA: Addison-Wesley.Google Scholar
- Noë, A. 2004. Action in Perception. Cambridge, MA: MIT Press.Google Scholar
- Russell, S. 2014. Of Myths and Moonshine {Blog post}. Retrieved from https://www.edge.org/conversation/the-mythof-ai#26015.Google Scholar
- Simon, H. A. 1957. Models of Man, Social and Rational: Mathematical Essays on Rational Human Behavior in a Social Setting. New York: John Wiley and Sons.Google Scholar
- Strack, F.; Martin, LL.; and Stepper, S. 1988. Inhibiting and facilitating conditions of the human smile: a nonobtrusive test of the facial feedback hypothesis. Journal of Personality and Social Psychology 54(5): 768--77.Google ScholarCross Ref
- Thelen, E. 1995. Time-scale dynamics in the development of an embodied cognition. In Mind In Motion, Port, R. and van Gelder, T., eds. Cambridge, MA: MIT Press. Google ScholarDigital Library
- Thompson, E. 2010 Mind in Life. Cambridge, MA: Belknap Press of Harvard UP.Google Scholar
- Toner, J.; Montero, B.; and Moran, A. 2016 Reflective and Prereflective Bodily Awareness in Skilled Action. Psychology of Consciousness: Theory, Research, and Practice 1:1--13.Google Scholar
- Topál, J.; Kis, A.; Oláh, K. 2014. Dogs' sensitivity to human social cues: A unique adaptation. In The Social Dog: Behavior and Cognition, Kaminski, J. and Marshall-Pescini, S., eds. Sand Diego: Elsevier, pp. 319--346.Google Scholar
- Wagenmakers, E.-J.; Beek, T.; Dijkhoff, L., et al. 2016. Registered Replication Report, Strack, Martin, Stepper (1988). Perspectives on Psychological Science 11: 917--928.Google ScholarCross Ref
- Wolfram, S. 1994. Cellular Automata and Complexity. Redwood City, CA: Addison-Wesley.Google Scholar
- Varela, F.; Thompson, E.; and Rosch, E. 1991. The Embodied Mind. Cambridge, MA: MIT Press.Google Scholar
Index Terms
- Shared Moral Foundations of Embodied Artificial Intelligence
Recommendations
Artificial Intelligence and Indigenous Perspectives: Protecting and Empowering Intelligent Human Beings
AIES '20: Proceedings of the AAAI/ACM Conference on AI, Ethics, and SocietyAs 'control' is increasingly ceded to AI systems, potentially Artificial General Intelligence (AGI) humanity may be facing an identity crisis sooner rather than later, whereby the notion of 'intelligence' no longer remains solely our own. This paper ...
Artificial Intelligence, Values, and Alignment
AbstractThis 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 ...
Moral Philosophy of Artificial General Intelligence: Agency and Responsibility
Artificial General IntelligenceAbstractThe European Parliament recently proposed to grant the personhood of autonomous AI, which raises fundamental questions concerning the ethical nature of AI. Can they be moral agents? Can they be morally responsible for actions and their ...
Comments