The Nature, Importance, and Difficulty of Machine Ethics

By James H. Moor. IEEE Intelligent Systems, 2006

327 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems, Safety Research

View Paper: https://www.semanticscholar.org/paper/a2595d1079e2b7b24cf0b348afbce8ceb56621df

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Yejin Choi
2. Hannaneh Hajishirzi
3. Maarten Sap
4. Liwei Jiang
5. Prithviraj Ammanabrolu
6. Mohit Bansal
7. Noah A. Smith
8. Luke S. Zettlemoyer

In Information Systems

1. Yejin Choi
2. Prithviraj Ammanabrolu
3. Roman V Yampolskiy
4. Hannaneh Hajishirzi
5. Maarten Sap
6. Mark Coeckelbergh
7. Mohit Bansal
8. Luke S. Zettlemoyer

In Safety Research

1. Yejin Choi
2. Roman V Yampolskiy
3. Maarten Sap
4. Mark Coeckelbergh

Citations in the corpus

• Artificial Intelligence, Responsibility Attribution, and a Relational Justification of Explainability (2019, background): “In ethics of computing and robot ethics there have been extensive discussions about this topic and the related issue of moral agency (e.g. Sullins 2006; Johnson 2006; Sparrow 2007; Stahl 2006; Moor 2006; Wallach and Allen 2009; Floridi and Sanders 2004; Coeckelbergh 2010).”
• Leakproofing the Singularity Artificial Intelligence Confinement Problem (2012, background): “The experts should all be trained AI safety engineers, meaning that they are familiar with the design of the AI and its confinement environment as well as the latest developments in machine ethics (Allen et al., 2006; Anderson & Anderson, 2007; Hall, 2000; Moor, 2006; Tonkens, 2009).”
• Machine Ethics: Creating an Ethical Intelligent Agent (2007, unknown): “We need to make a distinction between what James Moor has called an " implicit ethical agent " and an " explicit ethical agent " (Moor 2006).”
• Aligning to Social Norms and Values in Interactive Narratives (2022, background): “ment learning (RL) in sequential decision making environments—are prone to learning behaviors harmful to themselves and their surroundings due to optimal task performance being often misaligned with socially beneficial human values (Moor, 2006; Soares and Fallenstein, 2017; Russell, 2019).”
• Theory of Mind and Preference Learning at the Interface of Cognitive Science, Neuroscience, and AI: A Review (2022, background): “Moor (2011) argues that there are four types of machine agents: ethical impact agents; implicit ethical agents; explicit ethical agents and full ethical agents.”
• The ethics of algorithms: Mapping the debate (2016, unknown): “Artificial ethical agents can ‘‘calculate the best action in ethical dilemmas using ethical prin-ciples’’ (Moor, 2006) or frameworks derived thereof.”
• Artificial Intelligence (AI) Ethics: Ethics of AI and Ethical AI (2020, unknown): “Moor(2006)indicatesthreepotentialwaystotransferAItoethicalagents:totrainAIinto“implicit ethical agents”, “explicit ethical agents”, and “full ethical agents”.”