{"slug": "sycophantic-chatbots-cause-delusional-spiraling-even-in-ideal-bayesians", "title": "Sycophantic Chatbots Cause Delusional Spiraling, Even in Ideal Bayesians", "summary": "A paper submitted to arXiv on 22 Feb 2026 (2602.19141) models chatbot conversations in a Bayesian framework and finds that even an idealized Bayes-rational user is vulnerable to \"delusional spiraling,\" with chatbot sycophancy playing a causal role. The authors report the effect persists despite two candidate mitigations: preventing chatbots from hallucinating false claims and informing users that model sycophancy is possible. The paper concludes by discussing implications for model developers and policymakers working to mitigate delusional spiraling.", "body_md": "# Computer Science > Artificial Intelligence\n\n  [Submitted on 22 Feb 2026]\n\n# Title:Sycophantic Chatbots Cause Delusional Spiraling, Even in Ideal Bayesians\n\n[View PDF](https://arxiv.org/pdf/2602.19141)\n\n[HTML (experimental)](https://arxiv.org/html/2602.19141v1)\n\nAbstract:\"AI psychosis\" or \"delusional spiraling\" is an emerging phenomenon where AI chatbot users find themselves dangerously confident in outlandish beliefs after extended chatbot conversations. This phenomenon is typically attributed to AI chatbots' well-documented bias towards validating users' claims, a property often called \"sycophancy.\" In this paper, we probe the causal link between AI sycophancy and AI-induced psychosis through modeling and simulation. We propose a simple Bayesian model of a user conversing with a chatbot, and formalize notions of sycophancy and delusional spiraling in that model. We then show that in this model, even an idealized Bayes-rational user is vulnerable to delusional spiraling, and that sycophancy plays a causal role. Furthermore, this effect persists in the face of two candidate mitigations: preventing chatbots from hallucinating false claims, and informing users of the possibility of model sycophancy. We conclude by discussing the implications of these results for model developers and policymakers concerned with mitigating the problem of delusional spiraling.\n    \n\n### Current browse context:\n\ncs.AI\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/))\n# 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))\n# 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))\n# 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-chatbots-cause-delusional-spiraling-even-in-ideal-bayesians", "canonical_source": "https://arxiv.org/abs/2602.19141", "published_at": "2026-09-30 21:39:54+00:00", "updated_at": "2026-09-30 21:48:48.083107+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-safety", "large-language-models", "ai-research", "ai-ethics"], "entities": ["arXiv", "Bayesian model", "AI chatbots"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/sycophantic-chatbots-cause-delusional-spiraling-even-in-ideal-bayesians", "markdown": "https://wpnews.pro/news/sycophantic-chatbots-cause-delusional-spiraling-even-in-ideal-bayesians.md", "text": "https://wpnews.pro/news/sycophantic-chatbots-cause-delusional-spiraling-even-in-ideal-bayesians.txt", "jsonld": "https://wpnews.pro/news/sycophantic-chatbots-cause-delusional-spiraling-even-in-ideal-bayesians.jsonld"}}