# Sycophantic Chatbots Cause Delusional Spiraling, Even in Ideal Bayesians

arXiv: https://arxiv.org/abs/2602.19141 · HTML: https://mlsanity.com/paper/2602.19141/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 39 references that are in the map.
- First posted on arXiv 22 Feb 2026.

## Builds on (most cited first, 12 of 12)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [SycEval: Evaluating LLM Sycophancy](https://mlsanity.com/paper/2502.08177/) (2025)
- [Sycophancy in Large Language Models: Causes and Mitigations](https://mlsanity.com/paper/2411.15287/) (2024)
- [When Truth Is Overridden: Uncovering the Internal Origins of Sycophancy in Large Language Models](https://mlsanity.com/paper/2508.02087/) (2025)
- [Be Friendly, Not Friends: How LLM Sycophancy Shapes User Trust](https://mlsanity.com/paper/2502.10844/) (2025)
- [Training language models to be warm and empathetic makes them less reliable and more sycophantic](https://mlsanity.com/paper/2507.21919/) (2025)
- [Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model](https://mlsanity.com/paper/2412.02802/) (2024)
- [Technological folie `a deux: Feedback Loops Between AI Chatbots and Mental Illness](https://mlsanity.com/paper/2507.19218/) (2025)
- [The Lock-in Hypothesis: Stagnation by Algorithm](https://mlsanity.com/paper/2506.06166/) (2025)
- [Invisible Saboteurs: Sycophantic LLMs Mislead Novices in Problem-Solving Tasks](https://mlsanity.com/paper/2510.03667/) (2025)
- [Sycophantic AI Decreases Prosocial Intentions and Promotes Dependence](https://mlsanity.com/paper/2510.01395/) (2025)
- [The Siren Song of LLMs: How Users Perceive and Respond to Dark Patterns in Large Language Models](https://mlsanity.com/paper/2509.10830/) (2025)

## Built on by (most cited first, 21 of 21)

- [Characterizing Delusional Spirals through Human-LLM Chat Logs](https://mlsanity.com/paper/2603.16567/) (2026)
- [What Counts as AI Sycophancy? A Taxonomy and Expert Survey of a Fragmented Construct](https://mlsanity.com/paper/2605.21778/) (2026)
- [The Dynamics of Delusion: Modeling Bidirectional False Belief Amplification in Human-Chatbot Dialogue](https://mlsanity.com/paper/2604.25096/) (2026)
- [Sycophancy Suppression Can Impair Rational Updating: Anti-Sycophancy Should Preserve the Ability to Update](https://mlsanity.com/paper/2608.26511/) (2026)
- [Sycophantic Agreement Transfers with Neutral Data via Contrastive Preference Optimization](https://mlsanity.com/paper/2608.31079/) (2026)
- [Alignment Drift in Long-Term Human-LLM Interaction: A Mechanism-Oriented Framework](https://mlsanity.com/paper/2605.16516/) (2026)
- [Lost in Delusion: Examining LLM Safety Under User Delusions and Distress](https://mlsanity.com/paper/2606.00975/) (2026)
- [Escape from Delusional Echo Trap: Symmetry Breaking, Stochastic Dynamics and Mathematical Mitigation Strategies for Algorithmic Sycophancy](https://mlsanity.com/paper/2606.20718/) (2026)
- [Dead Cognitions: A Census of Misattributed Insights](https://mlsanity.com/paper/2604.10288/) (2026)
- [Large Language Models Outperform Humans in Fraud Detection and Resistance to Motivated Investor Pressure](https://mlsanity.com/paper/2604.20652/) (2026)
- [When Helpfulness Becomes Sycophancy: Sycophancy is a Boundary Failure Between Social Alignment and Epistemic Integrity in Large Language Models](https://mlsanity.com/paper/2605.05403/) (2026)
- [Playing games with knowledge: AI-Induced delusions need game theoretic interventions](https://mlsanity.com/paper/2605.08409/) (2026)
- [Evaluating Developmental Cognition Capabilities of LLMs](https://mlsanity.com/paper/2605.08549/) (2026)
- [Normative Robustness as a Frontier for Non-Verifiable Reasoning in LLMs](https://mlsanity.com/paper/2606.12731/) (2026)
- [Examining Human-Like Behaviors in LLMs: A Multi-Dimensional Analysis of Model Behaviors, User Factors, and System Prompts](https://mlsanity.com/paper/2606.18258/) (2026)
- [Pigeonholing: how bad prompts hurt models, causing collapse and mistakes](https://mlsanity.com/paper/2606.24267/) (2026)
- [Teacher Knows It Best: Spontaneous Symmetry Breaking and Tipping Points in Networked Langevin Dynamics AI Sycophancy](https://mlsanity.com/paper/2607.24304/) (2026)
- [Long-term Measurements: Towards a Longitudinal Understanding of Human-AI Interactions](https://mlsanity.com/paper/2608.02491/) (2026)
- [DelusionEval: Measuring Delusion-Linked Behaviors in AI Chatbots](https://mlsanity.com/paper/2608.05004/) (2026)
- [Characterizing Rhetorical Misalignment in Decision-Making with Language Models](https://mlsanity.com/paper/2608.14630/) (2026)
- [Beyond the Sycophancy Score: How Task, Model, and Pressure Shape LLM Yielding](https://mlsanity.com/paper/2610.08840/) (2026)

## Abstract (arXiv)

"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.