GPT-3 Powered Game Abused: Generating Sexually Explicit Content - Harm Prevention Needed
April 1, 2021
Recent reports indicate that Latitude's AI Dungeon, powered by GPT-3, was manipulated by certain players to generate sexually explicit content involving children. This incident underscores the need for safe and secure AI and highlights the importance of guardrails in responsible AI. Join us in preventing such incidents by contributing to Project Cerebellum's AI incident database - help shape trustworthy AI for a safer digital future.JOIN US. This AI incident maps to the Govern function in HISPI Project Cerebellum Trusted AI Model (TAIM).
- Alleged deployer
- latitude
- Alleged developer
- openai, latitude
- Alleged harmed parties
- latitude
Source
Data from the AI Incident Database (AIID). Cite this incident: https://incidentdatabase.ai/cite/402
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.