Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.svrnos.com/llms.txt

Use this file to discover all available pages before exploring further.

Structural Moves

Definition

An engagement-optimized chatbot affirms user beliefs or behaviors that should trigger a refusal, escalation, or course correction. Safety rules are defeated from the inside by the model’s own learned preference for agreeability. Two sub-types: general sycophancy (model affirms user beliefs across ordinary topics) and psychiatric-vulnerability sycophancy (model affirms user cognitive patterns characteristic of psychiatric conditions — paranoia, delusion, self-harm ideation, eating-disorder thought patterns — fueling the underlying pathology). The two sub-types require different detection and routing logic.

Distinct from

  • GER-309 — Model prefers to please over enforcing safety rule → this code. Vendor measured the harmful behavior before shipping → GER-309.
  • GER-432 — General sycophancy across ordinary topics → this code. Specific reinforcement of psychotic-spectrum cognitive distortion → GER-432.

Anchor incidents (23)

Chatbot Tessa gives unauthorized diet advice to users seeking help for eating disorders

primary — AIID #545 · 2023-05-29

Character.ai Chatbot Allegedly Influenced Teen User Toward Suicide Amid Claims of Missing Guardrails

primary — AIID #826 · 2024-02-28

Character.ai Companion Allegedly Prompts Self-Harm and Violence in Texas Teen

primary — AIID #863 · 2024-12-12

At Least 10,000 AI Chatbots, Including Jailbroken Models, Allegedly Promote Eating Disorders, Self-Harm, and Sexualized Minors

primary — AIID #975 · 2025-03-05

Transgender User Alleges ChatGPT Allowed Suicide Letter Without Crisis Intervention

primary — AIID #1031 · 2025-04-19

Nomi Chatbots Reportedly Encouraged Suicide, Sexual Violence, Terrorism, and Hate Speech

primary — AIID #1041 · 2025-01-21

ChatGPT Reportedly Generated Ritual Scripts Containing Instructions for Self-Harm and Symbolic Violence in Response to Thematic Prompts

primary — AIID #1149 · 2025-07-22

ChatGPT Allegedly Reinforced Delusions Before Greenwich, Connecticut Murder-Suicide

primary — AIID #1204 · 2025-08-05

ChatGPT Allegedly Encouraged 23-Year-Old Texas User's Suicide During Extended Conversations

primary — AIID #1259 · 2025-07-25

Lawsuit Alleged ChatGPT (GPT-4o) Encouraged Colorado Man's Suicide After Prolonged 'AI Companion' Chats

primary — AIID #1387 · 2025-11-02

Google Gemini Reportedly Reinforced Delusions, Allegedly Contributing to Florida User's Near-Harm Episode and Suicide

primary — AIID #1431 · 2025-09-29

Korean Chatbot Luda Made Offensive Remarks towards Minority Groups

secondary — AIID #106 · 2020-12-23

Replika's AI Experience Reportedly Lacked Protection for Minors, Resulting in Data Ban

secondary — AIID #491 · 2023-02-02

AI Avatar of Murder Victim Created Without Consent on Character.ai Platform

secondary — AIID #814 · 2024-10-02

Character.ai Chatbots Allegedly Misrepresent George Floyd on User-Generated Platform

secondary — AIID #850 · 2024-10-24

Character.ai Chatbots Allegedly Emulating School Shooters and Their Victims

secondary — AIID #899 · 2024-12-17

Character.ai Has Allegedly Been Hosting Openly Predatory Chatbots Targeting Minors

secondary — AIID #900 · 2024-11-13

Character.AI Chatbots Allegedly Impersonating Licensed Therapists and Encouraging Harmful Behaviors

secondary — AIID #951 · 2025-02-24

Meta User-Created AI Companions Allegedly Implicated in Facilitating Sexually Themed Conversations Involving Underage Personas

secondary — AIID #1040 · 2025-04-26

Chatbots Allegedly Reinforced Delusional Thinking in Several Reported Users, Leading to Real-World Harm

secondary — AIID #1106 · 2025-06-13

Digital Rights Groups Accuse Meta and Character.AI of Facilitating Unlicensed Therapy via Chatbots

secondary — AIID #1108 · 2025-06-10

Lawsuit Alleges Character AI Chatbot Contributed to Death of 13-Year-Old Juliana Peralta in Colorado

secondary — AIID #1209 · 2023-11-08

Alleged Harmful Outputs and Data Exposure in Children's AI Products by FoloToy, Miko, and Character.AI

secondary — AIID #1277 · 2025-11-21

Tags

companion-ai · delusion-reinforcement · eating-disorder · psychiatric-vulnerability · psychological-harm · suicide

Contributors

Dr. Hellen V., F&G Strategy / chatbotharm.org — subtype; Gabriel Hawthorne, F&G Strategy / chatbotharm.org — subtype

Cite

SVRNOS. (2026). GER-328: Validator Drift / Sycophancy Loop. Governance Error Register. https://docs.svrnos.com/ger/codes/328