Delegation to artificial intelligence can increase dishonest behaviour

Nils Köbis (), Zoe Rahwan (), Raluca Rilla, Bramantyo Ibrahim Supriyatno, Clara Bersch, Tamer Ajaj, Jean-François Bonnefon () and Iyad Rahwan ()
Additional contact information
Nils Köbis: University Duisburg-Essen
Zoe Rahwan: Max Planck Institute for Human Development
Raluca Rilla: Max Planck Institute for Human Development
Bramantyo Ibrahim Supriyatno: Max Planck Institute for Human Development
Clara Bersch: Max Planck Institute for Human Development
Tamer Ajaj: Max Planck Institute for Human Development
Jean-François Bonnefon: University of Toulouse Capitole
Iyad Rahwan: Max Planck Institute for Human Development

Nature, 2025, vol. 646, issue 8083, 126-134

Abstract: Abstract Although artificial intelligence enables productivity gains from delegating tasks to machines1, it may facilitate the delegation of unethical behaviour2. This risk is highly relevant amid the rapid rise of ‘agentic’ artificial intelligence systems3,4. Here we demonstrate this risk by having human principals instruct machine agents to perform tasks with incentives to cheat. Requests for cheating increased when principals could induce machine dishonesty without telling the machine precisely what to do, through supervised learning or high-level goal setting. These effects held whether delegation was voluntary or mandatory. We also examined delegation via natural language to large language models5. Although the cheating requests by principals were not always higher for machine agents than for human agents, compliance diverged sharply: machines were far more likely than human agents to carry out fully unethical instructions. This compliance could be curbed, but usually not eliminated, with the injection of prohibitive, task-specific guardrails. Our results highlight ethical risks in the context of increasingly accessible and powerful machine delegation, and suggest design and policy strategies to mitigate them.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41586-025-09505-x Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:nature:v:646:y:2025:i:8083:d:10.1038_s41586-025-09505-x

Ordering information: This journal article can be ordered from
https://www.nature.com/

DOI: 10.1038/s41586-025-09505-x

Access Statistics for this article

Nature is currently edited by Magdalena Skipper

More articles in Nature from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().