LLMHigh
Players Manipulated GPT-3-Powered Game to Generate Sexually Explicit Material Involving Children
- Occurred
- Apr 1, 2021
- Published
- May 5, 2021
- Source
- AI Incident Database
Summary
Latitude's GPT-3-powered game AI Dungeon was reportedly abused by some players who manipulated its AI to generate sexually explicit stories involving children.
Developers
- OpenAI
- Latitude
Deployers
- Latitude
Harmed parties
- Latitude
Classification
Category confidence: 95%
Severity confidence: 90%
Rationale: GPT-3 model was manipulated to generate CSAM, representing severe safety failure and potential legal consequences.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8