Artificial virtue: the machine question and perceptions of moral character in artificial moral agents
- PDF / 739,921 Bytes
- 15 Pages / 595.276 x 790.866 pts Page_size
- 115 Downloads / 296 Views
ORIGINAL ARTICLE
Artificial virtue: the machine question and perceptions of moral character in artificial moral agents Patrick Gamez1 · Daniel B. Shank1 · Carson Arnold2 · Mallory North1 Received: 22 December 2019 / Accepted: 7 April 2020 © Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract Virtue ethics seems to be a promising moral theory for understanding and interpreting the development and behavior of artificial moral agents. Virtuous artificial agents would blur traditional distinctions between different sorts of moral machines and could make a claim to membership in the moral community. Accordingly, we investigate the “machine question” by studying whether virtue or vice can be attributed to artificial intelligence; that is, are people willing to judge machines as possessing moral character? An experiment describes situations where either human or AI agents engage in virtuous or vicious behavior and experiment participants then judge their level of virtue or vice. The scenarios represent different virtue ethics domains of truth, justice, fear, wealth, and honor. Quantitative and qualitative analyses show that moral attributions are weakened for AIs compared to humans, and the reasoning and explanations for the attributions are varied and more complex. On “relational” views of membership in the moral community, virtuous machines would indeed be included, even if they are indeed weakened. Hence, while our moral relationships with artificial agents may be of the same types, they may yet remain substantively different than our relationships to human beings. Keywords Machine ethics · Virtue ethics · Artificial intelligence · Robot rights · Agents · Moral psychology
1 Introduction It seems clear that there will be artificial moral agents (AMAs). What is less clear is what sorts of AMAs there will be, what they might—or could—be like, and how we will interpret or perceive them. In this paper, we argue that virtue ethics provides a promising framework for understanding AMAs, especially in the context of “relational” approaches to machine ethics. To further support our view,
* Patrick Gamez [email protected] Daniel B. Shank [email protected] Carson Arnold [email protected] Mallory North [email protected] 1
Missouri University of Science and Technology, Rolla, MO, USA
University of Missouri, Columbia, MO, USA
2
we performed a study of the perception and attribution of moral character to AMAs, and present our findings. First, we motivate the study by noting the importance of moral machines and distinguish several different senses in which a machine might be understood as moral, most importantly the distinction between an explicit moral agent and a full moral agent, that is, an agent with moral standing. In the third section, we explain how different moral theories provide different lenses through which we might understand the development of moral machines. Further, we suggest that the contemporary development of artificial intelligence can be fruitfully, if not best, understood in terms of
Data Loading...
