Delegation to artificial intelligence can increase dishonest behaviour.

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 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 models⁵. Although the cheating requests by principals were no

SUBMITTER: Kobis N 

PROVIDER: S-EPMC12488497 | biostudies-literature | 2025 Oct

REPOSITORIES: biostudies-literature