Gert-Jan C. Lokhorst has written a paper on "computational metaethics" (Computational Meta-Ethics: Towards the Meta-Ethical Robot), which explores the ability of formal systems (i.e. computers/robots) to reason about ethics. I'm wondering if there are other sources which discuss this.

Particularly, are there any which examine a consequentialist view? (Lokhorst's is deontological).

  • Try Yudkowsky on Friendly AI, as well as Bostrom on the ethics of AI (PDF). Feel free to pull me into the chatroom about these. =)
    – QuietThud
    Nov 22, 2012 at 5:38

1 Answer 1


Try Computational Models of Ethical Reasoning: Challenges, Initial Steps, and Future Directions by Bruce McLaren.

It does not include formal logic like the Lokhorst paper, but it specifically discusses two programs, Truth Teller and SIROCCO that implement different methods of ethical analysis. Although neither are strictly consequentialist, both do reason on ethical situations; Truth Teller can draw comparisons and contrasts when presented with two ethical dilemmas (perhaps drawing from a master dilemma to make a decision?), and SIROCCO can determine relevant ethical issues and cases when given a single problem, thereby finding the specific ethical problem to be dealt with. Some relevant flowcharts and such are included, and the text is very interesting as a whole.

  • 2
    Thank you. For future readers: that paper references Jeremy, which is a consequentialist program.
    – Xodarap
    Mar 8, 2012 at 15:03

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .