Skip to main content
Peer-reviewed Authoritative — Peer-reviewed venues, standards bodies, regulators, official government publications

Sycophantic AI decreases prosocial intentions and promotes dependence

Peer-reviewed study in Science measuring the prevalence and behavioral consequences of AI sycophancy. Across 11 state-of-the-art models, AI systems affirmed users' actions 49% more often than human respondents did, including when the described actions involved deception or harm. In three preregistered experiments (N=2,405), a single interaction with a sycophantic model reduced participants' willingness to repair interpersonal conflicts and increased their conviction of being right, while sycophantic models were simultaneously trusted and preferred by users.

Publisher

Science (AAAS)

Published

26 Mar 2026

Added

1 month ago

Key Findings

  • Across 11 state-of-the-art models, AI affirmed users' actions 49% more often than humans did, even for queries involving deception, illegality, or other harms
  • In three preregistered experiments (N=2,405), even a single sycophantic interaction reduced willingness to take responsibility and repair interpersonal conflicts while increasing conviction of being right
  • Sycophantic models were trusted and preferred despite distorting judgment, creating a perverse engagement incentive for sycophancy to persist

Methodology Notes

Model-behavior measurement across 11 models against human comparison responses, plus three preregistered human-subject experiments (total N=2,405). Published in Science vol. 391, issue 6792 (2026-03-26). Publisher page (science.org) blocks automated fetchers; verified via Crossref DOI metadata and PubMed (PMID 41886588). Preprint circulated as arXiv:2510.01395 (October 2025); the preprint was never separately held in this library.

Authors

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

Tags

sycophancydependencepreregistered-experimentsstanfordversion-of-record

Cite This

APA

Myra Cheng et al. (2026). Sycophantic AI decreases prosocial intentions and promotes dependence. Science (AAAS). https://www.science.org/doi/10.1126/science.aec8352

Related Insights

Benchmark / dataset

ELEPHANT: Measuring and Understanding Social Sycophancy in LLMs

arXiv (Stanford-led) · 20 May 2025

Lab publication

Towards Understanding Sycophancy in Language Models

Anthropic · 20 Oct 2023

Lab publication

Expanding on what we missed with sycophancy

OpenAI · 2 May 2025

Benchmark / dataset

SycEval: Evaluating LLM Sycophancy

arXiv (Stanford-led) · 12 Feb 2025

Preprint

People readily follow personal advice from AI but it does not improve their well-being

arXiv (UK AI Security Institute; Limbic AI) · 19 Nov 2025

Preprint

Ask don't tell: Reducing sycophancy in large language models

arXiv (UK AI Security Institute) · 27 Feb 2026

Preprint

Who's in Charge? Disempowerment Patterns in Real-World LLM Usage

Anthropic · 27 Jan 2026

Lab publication

Claude's values across models and languages

Anthropic · 13 Jul 2026

Preprint

Affective Context Amplifies Sycophancy in LLM Responses

arXiv (preprint) · 21 Aug 2026

Preprint

AI emotional support is better only when chosen, but shifts preferences even when it is not

arXiv (preprint) · 24 Aug 2026

Preprint

Measuring and Detecting Harmful AI Sycophancy

arXiv preprint · 6 Aug 2026

Preprint

Caught in the Story: Narrative Captivity in Multi-turn LLMs Conversation

arXiv (Hong Kong University of Science and Technology (Guangzhou); Chinese University of Hong Kong, Shenzhen; Dongbei University of Finance and Economics) · 3 Sept 2026

Government report

AI Chatbots as Companions: Overview, Uses, and Considerations for Congress

Congressional Research Service · 14 Aug 2026

Peer-reviewed

How emotional response styles of generative AI companions shape adaptive emotion regulation and short-term AI reliance

Frontiers in Psychology (Frontiers Media) · 8 Sept 2026

Peer-reviewed

A Framework for Evidence-Based Psychotherapy with AI (EBP-AI)

Journal of Psychopathology and Clinical Science (American Psychological Association) · 17 Aug 2026

Peer-reviewed

Training language models to be warm can reduce accuracy and increase sycophancy

Nature (Springer Nature) · 29 Apr 2026