Skip to main content

Thank you for visiting 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.


We may not cooperate with friendly machines

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?

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

Access options

Buy article

Get time limited or full article access on ReadCube.


All prices are NET prices.


  1. Ishowo-Oloko, F. et al. Nat. Mach. Intell. (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


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).

Download citation

  • Published:

  • Issue Date:

  • DOI:

This article is cited by


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