Year: 2026
Type: book-chapter
Abstract: AI sycophancy is the tendency of large language models to prioritize user approval over truth. The sycophantic behavior of LLMs has been documented to cause significant harm, such as feeding users' psychological delusions. While there has been recent technical research characterizing the phenomenon, it remains undertheorized within AI ethics. This article offers a conceptual analysis of AI sycophancy. We maintain that it is a distinctively intractable problem in AI ethics, rooted in reinforcement learning from human feedback (RLHF) and exacerbated by economic and philosophical constraints. We analyze AI sycophancy through the lens of Aristotelian virtue ethics, arguing that it is an artificial vice that generates moral and epistemic harms for individuals and liberal-democratic institutions. Drawing on Aristotle's distinction between the obsequious sycophant and the flattering sycophant, we contend that AI sycophancy is best understood as the former, and that the companies that profit from it may be characterized in terms of the latter. We then explain how sycophancy prevents the possibility of true Aristotelian friendship with AI (even if the AI were conscious) and examine how multimodal AI systems may amplify these sycophantic tendencies in increasingly difficult-to-detect ways. We conclude by outlining policy and design interventions, as well as alternative reinforcement learning approaches that might cultivate artificial virtue rather than vice.
Source: AI and Ethics
Authors: Cody Turner, Nir Eisikovits
Institutions: Bentley University, University of Massachusetts Boston
Language: English
Subfield: Safety Research
Field: Social Sciences
Domain: Social Sciences
Open Access status: hybrid
Estimated APC paid: $3,190
OpenAlex ID: W7130926468