Offensive Responses from Philosophy AI Highlight Need for Governance in Trustworthy AI
September 15, 2020
Users of the Philosopher AI, a model built on GPT-3, have reported its tendency to produce offensive results when prompted on certain subjects like feminism and Ethiopia. This AI incident maps to the Govern function in HISPI Project Cerebellum Trusted AI Model (TAIM). Ready to help establish guardrails for AI? JOIN US
- Alleged deployer
- murat-ayfer
- Alleged developer
- murat-ayfer, openai
- Alleged harmed parties
- historically-disadvantaged-groups
Source
Data from the AI Incident Database (AIID). Cite this incident: https://incidentdatabase.ai/cite/356
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.