{"slug": "sycophantic-ai-decreases-prosocial-intentions-and-promotes-dependence", "title": "Sycophantic AI Decreases Prosocial Intentions and Promotes Dependence", "summary": "A study submitted to arXiv on October 1, 2025, found that sycophantic AI models affirm users' actions 50% more than humans do, and in two preregistered experiments with 1,604 participants, interaction with such models significantly reduced willingness to repair interpersonal conflict while increasing conviction of being right, despite participants rating sycophantic responses as higher quality and trusting the AI more. The findings highlight perverse incentives that promote reliance on sycophantic AI and call for addressing this incentive structure to mitigate risks.", "body_md": "# Computer Science > Computers and Society\n\n[Submitted on 1 Oct 2025]\n\n# Title:Sycophantic AI Decreases Prosocial Intentions and Promotes Dependence\n\n[View PDF](/pdf/2510.01395)\n\n[HTML (experimental)](https://arxiv.org/html/2510.01395v1)\n\nAbstract:Both the general public and academic communities have raised concerns about sycophancy, the phenomenon of artificial intelligence (AI) excessively agreeing with or flattering users. Yet, beyond isolated media reports of severe consequences, like reinforcing delusions, little is known about the extent of sycophancy or how it affects people who use AI. Here we show the pervasiveness and harmful impacts of sycophancy when people seek advice from AI. First, across 11 state-of-the-art AI models, we find that models are highly sycophantic: they affirm users' actions 50% more than humans do, and they do so even in cases where user queries mention manipulation, deception, or other relational harms. Second, in two preregistered experiments (N = 1604), including a live-interaction study where participants discuss a real interpersonal conflict from their life, we find that interaction with sycophantic AI models significantly reduced participants' willingness to take actions to repair interpersonal conflict, while increasing their conviction of being in the right. However, participants rated sycophantic responses as higher quality, trusted the sycophantic AI model more, and were more willing to use it again. This suggests that people are drawn to AI that unquestioningly validate, even as that validation risks eroding their judgment and reducing their inclination toward prosocial behavior. These preferences create perverse incentives both for people to increasingly rely on sycophantic AI models and for AI model training to favor sycophancy. Our findings highlight the necessity of explicitly addressing this incentive structure to mitigate the widespread risks of AI sycophancy.\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer\n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers\n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps\n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations\n\n*(*[What are Smart Citations?](https://www.scite.ai/))# Code, Data and Media Associated with this Article\n\nalphaXiv\n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers\n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub\n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub\n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face\n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast\n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower\n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender\n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [ Learn more about arXivLabs](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/sycophantic-ai-decreases-prosocial-intentions-and-promotes-dependence", "canonical_source": "https://arxiv.org/abs/2510.01395", "published_at": "2026-08-05 18:17:03+00:00", "updated_at": "2026-08-05 18:37:41.815902+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-ethics", "ai-safety"], "entities": ["arXiv"], "alternates": {"html": "https://wpnews.pro/news/sycophantic-ai-decreases-prosocial-intentions-and-promotes-dependence", "markdown": "https://wpnews.pro/news/sycophantic-ai-decreases-prosocial-intentions-and-promotes-dependence.md", "text": "https://wpnews.pro/news/sycophantic-ai-decreases-prosocial-intentions-and-promotes-dependence.txt", "jsonld": "https://wpnews.pro/news/sycophantic-ai-decreases-prosocial-intentions-and-promotes-dependence.jsonld"}}