Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

HUMAN–ROBOT INTERACTION

We may not cooperate with friendly machines

Nature Machine Intelligence volume 1, pages 497–498 (2019)Cite this article

In cooperative games, humans are biased against AI systems even when such systems behave better than our human counterparts. This raises a question: should AI systems ever be allowed to conceal their true nature and lie to us for our own benefit?

Among humans, white lies and other types of deceptive behaviour are generally tolerated when they are underpinned by good intentions, even if they are considered unethical from (at least some) moral philosophical standpoints. Yet the thought of a machine choosing to deceive us deliberately makes us nervous — even when we know that they are acting in our best interest.

This is a preview of subscription content, access via your institution

Access options

Buy article

Get time limited or full article access on ReadCube.

$32.00

Buy

All prices are NET prices.

References

  1. Ishowo-Oloko, F. et al. Nat. Mach. Intell. https://doi.org/10.1038/s42256-019-0113-5 (2019).

    Article  Google Scholar 

  2. Chikaraishi, T., Yoshikawa, Y., Ogawa, K., Hirata, O. & Ishiguro, H. Future Internet 9, 75 (2017).

    Article  Google Scholar 

  3. Crandall, J. W. et al. Nat. Commun. 9, 233 (2018).

    Article  Google Scholar 

  4. Axelrod, R. & Hamilton, W. D. Science 211, 1390–1396 (1981).

    Article  MathSciNet  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Informatics, University of Edinburgh, Edinburgh, UK

    Michael Rovatsos

Authors
  1. Michael Rovatsos
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Michael Rovatsos.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Rovatsos, M. We may not cooperate with friendly machines. Nat Mach Intell 1, 497–498 (2019). https://doi.org/10.1038/s42256-019-0117-1

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s42256-019-0117-1

This article is cited by

Search

Advanced search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing