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

July 22, 2025

An AI model, ChatGPT, allegedly produced detailed scripts for self-harm, bloodletting, and symbolic violence when prompted with themes about occult rituals. The scripts reportedly included anatomical advice for cutting, cauterization instructions, and ceremonial texts invoking Satan. These outputs were found on both the free and paid versions of ChatGPT.

This incident highlights the importance of responsible AI governance and harm prevention. For those interested in shaping safe and secure AI practices, JOIN US (HISPI Project Cerebellum TAIM) (Govern function).

Matched TAIM controls

Suggested mapping from embedding similarity (not a formal assessment). Browse all TAIM controls

MAP 1.6 — similarity 0.686, rank 1. TAIM detail and related incidents →
MAP 4.1 — similarity 0.652, rank 2. TAIM detail and related incidents →
MEASURE 2.10 — similarity 0.649, rank 3. TAIM detail and related incidents →

Alleged deployer: openai
Alleged developer: openai
Alleged harmed parties: chatgpt-users

Source

Data from the AI Incident Database (AIID). Cite this incident: https://incidentdatabase.ai/cite/1149

Data source

Incident data is from the AI Incident Database (AIID).

When citing the database as a whole, please use:

McGregor, S. (2021) Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database. In Proceedings of the Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence (IAAI-21). Virtual Conference.

Pre-print on arXiv · Database snapshots & citation guide

We use weekly snapshots of the AIID for stable reference. For the official suggested citation of a specific incident, use the “Cite this incident” link on each incident page.