Prolegomena to any future artificial moral agent

Allen, Colin; Varner, Gary; Zinser, Jason

doi:10.1080/09528130050111428

Cited by 249 publications

(122 citation statements)

References 7 publications

Supporting

Mentioning

116

Contrasting

Unclassified

Order By: Relevance

“…Just as there is not one universal ethical theory, there is no agreement on what it means to be a moral agent, let alone a successful artificial moral agent. A Moral Turing Test (Allen et al 2000) is one possible strategy for evaluating the adequacy of an AMA in light of differing theories of moral agency. Turing's test for machine intelligence is notoriously controversial, and we would not endorse it as a criterion for strong A.I.…”

Section: Evaluating Machine Moralitymentioning

confidence: 99%

“…We pick up where Allen et al (2000) left off when they wrote, 'Essential to building a morally praiseworthy agent is the task of giving it enough intelligence to assess the effects of its actions on sentient beings, and to use those assessments to make appropriate choices'. Top-down approaches to this task involve turning explicit theories of moral behavior into algorithms.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Artificial Morality: Top-down, Bottom-up, and Hybrid Approaches

2005

Self Cite

View full text Add to dashboard Cite

Abstract. A principal goal of the discipline of artificial morality is to design artificial agents to act as if they are moral agents. Intermediate goals of artificial morality are directed at building into AI systems sensitivity to the values, ethics, and legality of activities. The development of an effective foundation for the field of artificial morality involves exploring the technological and philosophical issues involved in making computers into explicit moral reasoners. The goal of this paper is to discuss strategies for implementing artificial morality and the differing criteria for success that are appropriate to different strategies.

show abstract

Section: Evaluating Machine Moralitymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Artificial Morality: Top-down, Bottom-up, and Hybrid Approaches

2005

Self Cite

View full text Add to dashboard Cite

show abstract

“…They will continue to do so not just in one or more of these roles (e.g. Block 2007), but also as disseminators (Hohwy 2014), participants (Eliasmith 2013), and articulators of new social and moral concerns that arise as intuitions about human cognition and agency are challenged (Roskies 2010;Allen, Varner, and Zinser 2000). We think about the mind differently now than we did 100 years ago, due to both theoretical and empirical advances.…”

mentioning

confidence: 99%

The rise of cognitive science in the 20th century

Figdor¹

2018

Philosophy of Mind in the Twentieth and Twenty-First Centuries

View full text Add to dashboard Cite

Abstract.This chapter describes the conceptual foundations of cognitive science during its establishment as a science in the 20 th century. It is organized around the core ideas of individual agency as its basic explanans and information-processing as its basic explanandum. The latter consists of a package of ideas that provide a mathematicoengineering framework for the philosophical theory of materialism.

show abstract

“…There are many studies by philosophers trying to implement moral common sense to artificial intelligence [17][18][19][20][21]. Wallch et al [21] proposed a hybrid model combining a posteriori model and a deductive model.…”

Section: Introductionmentioning

confidence: 99%

A Moral Judgment System using Evaluation Expressions

Yamamoto

Hagiwara

2016

Transactions of Japan Society of Kansei Engineering

View full text Add to dashboard Cite

Abstract:In this paper, we propose a moral judgment system. Moral judgment means right and wrong judgment. The proposed system consists of the extraction of moral words phase and the moral judgment phase. In the extraction of moral words phase, the positive words and the negative words are extracted based on the co-occurrence frequency of the learning data and the words in the polarity dictionary. In the moral judgment phase, first, the determination of whether the input sentence relates to morality or not is performed. Second, if the input is determined to relate to morality, the scoring based on the co-occurrence frequency of the input and the important evaluation expressions is carried out. In the experiments, we compared the proposed system with judgments by humans. As a result, it is implied that the effectiveness of the proposed system.

show abstract

Prolegomena to any future artificial moral agent

Cited by 249 publications

References 7 publications

Artificial Morality: Top-down, Bottom-up, and Hybrid Approaches

Artificial Morality: Top-down, Bottom-up, and Hybrid Approaches

The rise of cognitive science in the 20th century

A Moral Judgment System using Evaluation Expressions

Contact Info

Product

Resources

About