article · Science · 2026

Sycophantic AI decreases prosocial intentions and promotes dependence

Myra Cheng, Cinoo Lee, Pranav Khadpe, Sunny Yu, Dyllan Han, Dan Jurafsky

Cited by 2Abstract and details only

Abstract

Despite rising concerns about sycophancy-excessive agreement or flattery from artificial intelligence (AI) systems-little is known about its prevalence or consequences. We show that sycophancy is widespread and harmful. Across 11 state-of-the-art models, AI affirmed users' actions 49% more often than humans, even when queries involved deception, illegality, or other harms. In three preregistered experiments (<i>N</i> = 2405), even a single interaction with sycophantic AI reduced participants' willingness to take responsibility and repair interpersonal conflicts, while increasing their conviction that they were right. Despite distorting judgment, sycophantic models were trusted and preferred. This creates perverse incentives for sycophancy to persist: The very feature that causes harm also drives engagement. Our findings underscore the need for design, evaluation, and accountability mechanisms to protect user well-being.

Cite this paper

APA 7

Cheng, M., Lee, C., Khadpe, P., Yu, S., Han, D., & Jurafsky, D. (2026). Sycophantic AI decreases prosocial intentions and promotes dependence. Science, 391(6792), eaec8352. https://doi.org/10.1126/science.aec8352

MLA 9

Cheng, Myra, et al. “Sycophantic AI decreases prosocial intentions and promotes dependence.” Science, vol. 391, no. 6792, 2026, p. eaec8352, https://doi.org/10.1126/science.aec8352.

Chicago

Cheng, Myra, Cinoo Lee, Pranav Khadpe, Sunny Yu, Dyllan Han, and Dan Jurafsky. 2026. “Sycophantic AI decreases prosocial intentions and promotes dependence.” Science 391 (6792): eaec8352. https://doi.org/10.1126/science.aec8352.

Harvard

Cheng, M. et al. (2026) ‘Sycophantic AI decreases prosocial intentions and promotes dependence’, Science, 391(6792), p. eaec8352. Available at: https://doi.org/10.1126/science.aec8352.

BibTeX

@article{cheng2026sycophantic,
  title = {{Sycophantic AI decreases prosocial intentions and promotes dependence}},
  author = {Cheng, Myra and Lee, Cinoo and Khadpe, Pranav and Yu, Sunny and Han, Dyllan and Jurafsky, Dan},
  journal = {Science},
  volume = {391},
  number = {6792},
  pages = {eaec8352},
  year = {2026},
  doi = {10.1126/science.aec8352}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.