Machine Ethics or AI Alignment?

Ajay Vishwanath and Marija Slavkovik ask whether machine ethics and AI alignment name the same research project. Their position paper compares goals, methods, and shortcomings across the two literatures.^[1]

Method and contribution

The comparison contrasts implementing ethical theories and moral reasoning with eliciting and operationalizing human values. It identifies overlap in ethical behavior, while discussing incomplete theory implementations, biased consensus, changing values, and limits of explanation. The authors recommend interdisciplinary collaboration.^[1]

Alignment relevance and limits

Machine Ethics complements AI Alignment by asking what justifies a behavioral target. Predicting common judgments does not establish their moral correctness; implementing an ethical rule does not establish reliable behavior in all settings. The paper is an interpretive comparison, not a new benchmark or systematic empirical proof that one field is superior. Its division of the fields should be treated as the authors’ framing, not exhaustive consensus.

Read alongside Artificial Intelligence, Values and Alignment and Engineering a social contract: Rawlsian distributive justice through algorithmic game theory and artificial intelligence.

Historical context

The original Machine Ethics or AI Alignment? PDF identifies NAIS 2025, held June 17–18 in Tromsø. This milestone records the symposium month; it does not infer an exact presentation or online-publication day.^[1]