Abstract
We present a position paper advocating the notion that Stoic philosophy and ethics can inform the development of ethical A.I. systems. This is in sharp contrast to most work on building ethical A.I., which has focused on Utilitarian or Deontological ethical theories. We relate ethical A.I. to several core Stoic notions, including the dichotomy of control, the four cardinal virtues, the ideal Sage, Stoic practices, and Stoic perspectives on emotion or affect. More generally, we put forward an ethical view of A.I. that focuses more on internal states of the artificial agent rather than on external actions of the agent. We provide examples relating to near-term A.I. systems as well as hypothetical superintelligent agents.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
- 2.
- 3.
Rule Utilitarianism addresses the problem of moral luck, and Eric O. Scott points out (personal communication) that a consequentialist analysis of an agent can also address the problem by considering a large number of trials.
- 4.
It should be noted, however, that creativity is a double-edged sword for an A.I. agent, since it may come up with very unexpected and disastrous solutions to a problem, such as Bostrom’s extreme example of a superintelligent agent getting rid of cancer in humans by killing all humans [7]. That is a clear example of the difference between creativity and moral progress.
References
Pigliucci, M.: Stoicism. http://www.iep.utm.edu/stoicism/. Accessed 2 Jan 2017
Hursthouse, R., Pettigrove, G.: Virtue ethics (2016). https://plato.stanford.edu/entries/ethics-virtue/. Accessed 2 Jan 2017
Sandel, M.: Justice: What’s the Right Thing to Do?. Macmillan, London (2010)
Amodei, D., Olah, C., Steinhardt, J., Christiano, P., Schulman, J., Mané, D.: Concrete problems in AI safety. arXiv preprint arXiv:1606.06565 (2016). http://arxiv.org/abs/1606.06565
Arkin, R.: Governing Lethal Behavior in Autonomous Robots. CRC Press, Boca Raton (2009)
Wallach, W., Allen, C.: Moral Machines: Teaching Robots Right from Wrong. Oxford University Press, Oxford (2008)
Bostrom, N.: Superintelligence: Paths, Dangers Strategies. Oxford University Press, Oxford (2014)
Dewey, D.: Learning what to value. In: Schmidhuber, J., Thórisson, K.R., Looks, M. (eds.) AGI 2011. LNCS (LNAI), vol. 6830, pp. 309–314. Springer, Heidelberg (2011). doi:10.1007/978-3-642-22887-2_35
Christiano, P.: Approval-directed agents (2014). https://medium.com/ai-control/model-free-decisions-6e6609f5d99e#.hpdm6kwee. Accessed 2 Jan 2017
Yudkowsky, E.: Coherent extrapolated volition (2004). https://intelligence.org/files/CEV.pdf
Coleman, K.: Android arete: toward a virtue ethic for computational agents. Ethics Inf. Technol. 3(4), 247–265 (2001)
Hicks, D.: Virtue ethics for robots (2014). http://jefais.tumblr.com/post/89164919838/virtue-ethics-for-robots. Accessed 2 Jan 2017
Wikipedia: Three laws of robotics (2016). https://en.wikipedia.org/wiki/Three_Laws_of_Robotics. Accessed 5 Dec 2016
Soares, N., Fallenstein, B., Armstrong, S., Yudkowsky, E.: Corrigibility. In: AAAI 2015 Workshop on AI & Ethics (2015)
Calvo, R., D’Mello, S., Gratch, J., Kappas, A.: The Oxford Handbook of Affective Computing. Oxford University Press, Oxford (2014)
Irvine, W.: A Guide to the Good Life: The Ancient Art of Stoic Joy. Oxford University Press, Oxford (2008)
Christian, B., Griffiths, T.: Algorithms to Live by: The Computer Science of Human Decisions. Macmillan, London (2016)
Stephens, W.: Stoic ethics. http://www.iep.utm.edu/stoiceth/. Accessed 2 Jan 2017
Bright, P.: Tay, the neo-Nazi millennial chatbot, gets autopsied (2016). http://arstechnica.com/information-technology/2016/03/tay-the-neo-nazi-millennial-chatbot-gets-autopsied/. Accessed 9 Jan 2017
Sinders, C.: Microsoft’s tay is an example of bad design (2016). https://medium.com/@carolinesinders/microsoft-s-tay-is-an-example-of-bad-design-d4e65bb2569f#.x27uitx3u. Accessed 9 Jan 2017
Simon, H.: Rational choice and the structure of the environment. Psychol. Rev. 63(2), 129 (1956)
Robertson, D.: Stoicism and the Art of Happiness. Teach Yourself, London (2013)
Christiano, P.: Concrete approval-directed agents (2015). https://medium.com/ai-control/concrete-approval-directed-agents-89e247df7f1b#.u2e59x2os. Accessed 2 Jan 2017
Wooldridge, M.: An Introduction to Multiagent Systems, 2nd edn. Wiley, Hoboken (2009)
Collins, W., Miller, K.: Paramedic ethics for computer professionals. J. Syst. Softw. 17(1), 23–38 (1992)
Acknowledgements
Thanks to Eric O. Scott for helpful feedback and discussion.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Murray, G. (2017). Stoic Ethics for Artificial Agents. In: Mouhoub, M., Langlais, P. (eds) Advances in Artificial Intelligence. Canadian AI 2017. Lecture Notes in Computer Science(), vol 10233. Springer, Cham. https://doi.org/10.1007/978-3-319-57351-9_42
Download citation
DOI: https://doi.org/10.1007/978-3-319-57351-9_42
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-57350-2
Online ISBN: 978-3-319-57351-9
eBook Packages: Computer ScienceComputer Science (R0)