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?
References
Ishowo-Oloko, F. et al. Nat. Mach. Intell. https://doi.org/10.1038/s42256-019-0113-5 (2019).
Chikaraishi, T., Yoshikawa, Y., Ogawa, K., Hirata, O. & Ishiguro, H. Future Internet 9, 75 (2017).
Crandall, J. W. et al. Nat. Commun. 9, 233 (2018).
Axelrod, R. & Hamilton, W. D. Science 211, 1390–1396 (1981).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
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
Published:
Issue Date:
DOI: https://doi.org/10.1038/s42256-019-0117-1
- Springer Nature Limited
This article is cited by
-
The imperative of interpretable machines
Nature Machine Intelligence (2020)