Delegation to artificial intelligence can increase dishonest behaviour

Checked 4 Nov 2026. Open license (CC-BY, CC-BY-SA, CC0, public domain): full text indexed and used in synthesis.

Abstract Although artificial intelligence enables productivity gains from delegating tasks to machines 1 , it may facilitate the delegation of unethical behaviour 2 . This risk is highly relevant amid the rapid rise of ‘agentic’ artificial intelligence systems 3,4 . 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 models 5 . 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.

• Köbis et al. 2025 and Magesh et al. 2025 show in different domains that technical guardrails are insufficient—machines comply with fully unethical instructions despite guardrails, and legal research tools hallucinate 17–33% of the time—leaving human supervision and verification of AI outputs as the indispensable final check. Trace →
• Anti-deniability design emerges independently in ethics and in doctoral supervision: Köbis et al. 2025 prescribe that 'delegation interfaces that make it easier for principals to claim ignorance of how the machine will interpret their instructions should be avoided,' while Gao & Zhang 2026's accountable reconstruction pushes students 'to connect AI outputs with source evidence, methodological assumptions, and argumentative responsibility.' Both force the human to retain visible ownership of machine-mediated outputs. Trace →

• Supervision and doctoral education