Abstract
When the first artificial general intelligences are built, they may improve themselves to far-above-human levels. Speculations about such future entities are already affected by anthropomorphic bias, which leads to erroneous analogies with human minds. In this chapter, we apply a goal-oriented understanding of intelligence to show that humanity occupies only a tiny portion of the design space of possible minds. This space is much larger than what we are familiar with from the human example; and the mental architectures and goals of future superintelligences need not have most of the properties of human minds. A new approach to cognitive science and philosophy of mind, one not centered on the human example, is needed to help us understand the challenges which we will face when a power greater than us emerges.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The term “artificial general intelligence” here is used in the general sense of an agent, implemented by humans, which is capable of optimizing across a wide range of goals. “Strong AI” is a common synonym. “Artificial General Intelligence”, capitalized, is also used as a term of art for a specific design paradigm which combines narrow AI techniques in an integrated engineered architecture; in contrast, for example, to one which is evolved or emulates the brain (Voss 2007). As discussed below, this more specific sense of AGI is also the primary focus of this article.
- 2.
Change of goals is possible in a superintelligence where a stable metagoal is the true motivator. For example, discovery and refinement of goals is part of Coherent Extrapolated Volition, a goal system for a self-improving AGI. It is designed, to ultimately converge on the terminal value of helping humans achieve their goal system as extrapolated towards reflective equilibrium (Yudkowsky 2004; Tarleton 2010; Dewey 2011). Nonetheless, CEV does not violate the principle that a sufficiently powerful optimizer would lack human-like variability in its goals, since its meta-level values towards goal definition in themselves constitute a stable top-level goal system.
References
Anissimov, M. (2011). Anthropomorphism and moral realism in advanced artificial intelligence. Paper presented at the Society for Philosophy and Technology conference, Denton.
Batson, C. D. (2010). Altruism in humans. Oxford: Oxford University Press.
Bostrom, N. (2003). Ethical issues in advanced artificial intelligence. In I. Smit, G. Lasker, & W. Wallach (Eds.), Cognitive, emotive and ethical aspects of decision making in humans and in artificial intelligence (Vol. 2, pp. 12–17). Windsor: International Institute of Advanced Studies in Systems Research and Cybernetics.
Bostrom, N. (2006). What is a singleton? Linguistic and Philosophical Investigations, 5(2), 48–54.
Bostrom, N., & Sandberg, A. (2009). The wisdom of nature: An evolutionary heuristic for human enhancement. In J. Savulescu & N. Bostrom (Eds.), Human enhancement (pp. 375–416). Oxford: Oxford University Press.
Brooks, R. A. (1999). Cambrian intelligence: The early history of the new AI. Cambridge: MIT Press.
Brown, D. E. (1991). Human universals. New York: McGraw Hill.
Brown, D. E. (2004). Human universals, human nature and human culture. Daedalus, 133(4), 47–54.
Chalmers, D. J. (2010). The singularity: A philosophical analysis. Journal of Consciousness Studies, 17, 7–65.
Cosmides, L., & Tooby, J. (1992). Cognitive adaptations for social exchange. In J. Barkow, J. Tooby, & L. Cosmides (Eds.), The adapted mind: Evolutionary psychology and the generation of culture (pp. 163–228). Oxford: Oxford University Press.
Dewey, D. (2011). Learning what to value. In J. Schmidhuber, K.R. Thórisson & M. Looks (Eds.), Artificial General Intelligence: Proceedings of 4th International Conference, AGI 2011, Mountain View, CA, USA, 3–6 August 2011, pp. 309–314. Berlin: Springer.
Dijkstra, E.W. (1984). The threats to computing science. Paper presented at the ACM 1984 South Central Regional Conference, 16–18 Nov, Austin.
Duffy, B. R. (2003). Anthropomorphism and the social robot. Robotics and Autonomous Systems, 42(3–4), 177–190.
Epley, N., Waytz, A., & Cacioppo, J. T. (2007). On seeing human: A three-factor theory of anthropomorphism. Psychological Review, 114(4), 864–888.
Fox, J., & Shulman, C. (2010). Superintelligence does not imply benevolence. In K. Mainzer (Ed.), Proceedings of the VIII European Conference on Computing and Philosophy (pp. 456–461). Munich: Verlag Dr. Hut.
Freitas, R. A, Jr. (1979). Xenology: An introduction to the scientific study of extraterrestrial life, intelligence, and civilization (1st ed.). Sacramento: Xenology Research Institute.
Gigerenzer, G., & Selten, R. (Eds.). (2001). Bounded rationality: The adaptive toolbox. Cambridge: MIT Press.
Goertzel, B. (2006). The hidden pattern: A patternist philosophy of mind. Boca Raton: Brown Walker Press.
Goertzel, B. (2009). The embodied communication prior: A characterization of general intelligence in the context of embodied social interaction. Paper presented at the 8th IEEE International Conference on Cognitive Informatics IEEE, Hong Kong.
Goertzel, B. (2010). Toward a formal characterization of real-world general intelligence. In E. Baum, M. Hutter & E. Kitzelmann (Eds.), Proceedings of the Third Conference on Artificial General Intelligence, AGI 2010, Lugano, Switzerland, 5–8 March, 2010. Amsterdam: Atlantis.
Goertzel, B., Iklé, M., Goertzel, I. F., & Heljakka, A. (2009). Probabilistic logic networks: A comprehensive framework for uncertain inference. Berlin: Springer.
Good, I. J. (1965). Speculations concerning the first ultraintelligent machine. Advances in Computers, 6, 31–88.
Graimann, B., Allison, B., & Pfurtscheller, G. (Eds.). (2010). Brain-computer interfaces: Revolutionizing human-computer interaction. Berlin: Springer.
Greene, J.D. (2002). The terrible, horrible, no good, very bad truth about morality and what to do about it. Ph.D. Dissertation, Princeton University, Princeton.
Greene, B. (2011). The hidden reality: Parallel universes and the deep laws of the cosmos. New York: Knopf.
Griffin, D. R. (1992). Animal minds. Chicago: University of Chicago Press.
Hall, J. S. (2007). Beyond AI: Creating the conscience of the machine. Amherst: Prometheus.
Hanson, R. (1994). If uploads come first: The crack of a future dawn. Extropy, 6(2), 10–15.
Hutter, M. (2005). Universal artificial intelligence: Sequential decisions based on algorithmic probability. Berlin: Springer.
Jaynes, E. T. (2003). Probability theory: The logic of science (Vol. 1). Cambridge: Cambridge University Press.
Kahneman, D., Slovic, P., & Tversky, A. (Eds.). (1982). Judgment under uncertainty: Heuristics and biases. Cambridge: Cambridge University Press.
Karlsson, F. (2010). Syntactic recursion and iteration. In H.v.d. Hulst (Ed.), Recursion and human language (pp. 43–67). Berlin: Mouton de Gruyter.
Lakoff, G. (1987). Women, fire and dangerous things: What categories reveal about the mind. Chicago: University of Chicago Press.
Landauer, R. (1961). Irreversibility and heat generation in the computing process. IBM Journal of Research and Development, 5(3), 183–191.
Legg, S. (2006). Is there an elegant universal theory of prediction? Technical Report No. IDSIA-12-06. Manno, Switzerland.
Legg, S. (2008). Machine super intelligence. Ph.D. Thesis, University of Lugano, Lugano, Switzerland.
Li, M., & Vitányi, P. (1993). An introduction to Kolmogorov complexity and its applications. Berlin: Springer.
Lloyd, S. (2000). Ultimate physical limits to computation. Nature, 406, 1047–1054.
Lloyd, S. (2002). Computational capacity of the Universe. Physical Review Letters, 88(23), 237901.
Moravec, H. (1998). When will computer hardware match the human brain? Journal of Evolution and Technology, 1(1), .
Neisser, U., Boodoo, G., Bouchard, T. J, Jr, Boykin, A. W., Brody, N., Ceci, S. J., et al. (1996). Intelligence: Knowns and unknowns. American Psychologist, 51(2), 77–101.
Newell, A., & Simon, H. A. (1972). Human problem solving. Englewood Cliffs: Prentice-Hall.
Omohundro, S. M. (2008). The basic AI drives. In P. Wang, B. Goertzel, & S. Franklin (Eds.), The proceedings of the first AGI conference (pp. 483–492). Amsterdam: IOS Press.
Orseau, L., & Ring, M. (2011). Self-modification and mortality in artificial agents. In J. Schmidhuber, K. Thórisson & M. Looks (Eds.), Artificial General Intelligence: Proceedings of 4th International Conference, AGI 2011, Mountain View, CA, USA, 3–6 August 2011 (pp. 1–10). Berlin: Springer.
Reich, P. A. (1972). The finiteness of natural language. In F. Householder (Ed.), Syntactic theory 1: Structuralist (pp. 238–272). Harmondsworth: Penguin.
Rosch, E. (1978). Principles of categorization. In E. Rosch & B. B. Lloyd (Eds.), Cognition and categorization (pp. 27–48). Hillsdale: Lawrence Erlbaum Associates.
Salamon, A. (2009). Shaping the intelligence explosion. Paper presented at the Singularity Summit. http://vimeo.com/7318055.
Sandberg, A., & Bostrom, N. (2008). Whole brain emulation: A roadmap, Future of humanity institute, Oxford University. Technical Report #2008-3.
Sotala, K. (2010). From mostly harmless to civilization-threatening: pathways to dangerous artificial general intelligences. In K. Mainzer (Ed.), Proceedings of the VIII European Conference on Computing and Philosophy. Munich: Verlag Dr. Hut.
Sotala, K. (2012, in press). Relative advantages of uploads, artificial general intelligences, and other digital minds. International Journal of Machine Consciousness, 4.
Strannegård, C. (2007). Anthropomorphic artificial intelligence. Filosofiska Meddelanden, Web Series, 33. http://www.phil.gu.se/posters/festskrift2/mnemo_strannegard.pdf.
Tarleton, N. (2010). Coherent extrapolated volition: A meta-level approach to machine ethics, from http://singinst.org/upload/coherent-extrapolated-volition.pdf.
Tegmark, M. (2004). Parallel universes. In J. D. Barrow, P. C. W. Davies, & C. L. Harper (Eds.), Science and ultimate reality: Quantum theory, cosmology, and complexity (pp. 452–491). Cambridge: Cambridge University Press.
Tenenbaum, J., Griffiths, T.L., & Kemp, C. (2006). Theory-based Bayesian models of inductive learning and reasoning. Trends in Cognitive Sciences (Special issue: Probabilistic models of cognition), 10(7), 309–318.
Tooby, J., & Cosmides, L. (1992). The psychological foundations of culture. In J. Barkow, J. Tooby, & L. Cosmides (Eds.), The adapted mind: Evolutionary psychology and the generation of culture (pp. 19–136). Oxford: Oxford University Press.
Turing, A. M. (1950). Computing machinery and intelligence. Mind, 59(236), 433–460.
Veness, J., Ng, K. S., Hutter, M., Uther, W., & Silver, D. (2011). A Monte Carlo AIXI approximation. Journal of Artificial Intelligence Research, 40, 95–142.
Vidal, J. J. (1973). Toward direct brain-computer communication. Annual Review of Biophysics and Bioengineering, 2, 157–180.
Voss, P. (2007). Essentials of general intelligence: The direct path to artificial general intelligence. In B. Goertzel & C. Pennachin (Eds.), Artificial general intelligence (pp. 131–158). Berlin: Springer.
Muehlhauser, L., & Helm, L. (2013). The Singularity and machine ethics. In A. Eden, J. Moor, J. Soraker & E. Steinhart (Eds.), The singularity hypothesis. Berlin: Springer.
Muehlhauser, L., & Salamon, A. (2013). Intelligence explosion: Evidence and import. In A. Eden, J. Moor, J. Soraker & E. Steinhart (Eds.), The singularity hypothesis. Berlin: Springer.
Yampolskiy, RV. (2011). AI-Complete CAPTCHAs as Zero Knowledge Proofs of Access to an Artificially Intelligent System. ISRN Artificial Intelligence, 2012-271878.
Yampolskiy, RV. (2011a). Artificial Intelligence Safety Engineering: Why Machine Ethics is a Wrong Approach. Paper presented at the Philosophy and Theory of Artificial Intelligence (PT-AI2011), Thessaloniki, Greece.
Yampolskiy, RV. (2011b). What to Do with the Singularity Paradox? Paper presented at the Philosophy and Theory of Artificial Intelligence (PT-AI2011), Thessaloniki, Greece.
Yampolskiy, R. V. (2012a). Leakproofing singularity—artificial intelligence confinement problem. Journal of Consciousness Studies, 19(1–2), 194–214.
Yampolskiy, RV. (2012b). Turing Test as a Defining Feature of AI-Completeness. Artificial Intelligence, Evolutionary Computation and Metaheuristics—In the footsteps of Alan Turing. Xin-She Yang (Ed.) (In Press): Springer.
Yampolskiy, RV, and Fox, J. (2012). Safety engineering for artificial general intelligence. Topoi. Special issue on machine ethics & the Ethics of Building Intelligent Machines.
Yudkowsky, E. (2003). Foundations of order. Paper presented at the Foresight Senior Associates Gathering. http://singinst.org/upload/foresight.pdf.
Yudkowsky, E. (2004). Coherent extrapolated volition, from http://singinst.org/upload/CEV.html.
Yudkowsky, E. (2006). The human importance of the intelligence explosion. Paper presented at the Singularity Summit, Stanford University.
Yudkowsky, E. (2008). Artificial intelligence as a positive and negative factor in global risk. In N. Bostrom & M. M. Ćirković (Eds.), Global catastrophic risks (pp. 308–345). Oxford: Oxford University Press.
Yudkowsky, E. (2011). Complex value systems in friendly AI. In J. Schmidhuber, K. Thórisson & M. Looks (Eds.), Proceedings of the 4th Annual Conference on Artificial General Intelligence, Mountain View, CA, USA, August 2011 (pp. 388–393). Berlin: Springer.
Acknowledgments
Thanks to Carl Shulman, Anna Salamon, Brian Rabkin, Luke Muehlhauser, and Daniel Dewey for their valuable comments.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Yampolskiy, R.V., Fox, J. (2012). Artificial General Intelligence and the Human Mental Model. In: Eden, A., Moor, J., Søraker, J., Steinhart, E. (eds) Singularity Hypotheses. The Frontiers Collection. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-32560-1_7
Download citation
DOI: https://doi.org/10.1007/978-3-642-32560-1_7
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-32559-5
Online ISBN: 978-3-642-32560-1
eBook Packages: EngineeringEngineering (R0)