Philosophy AI Tentatively Produced Offensive Results for Certain Prompts

September 15, 2020

A recent development in GPT-3-powered philosopher AI has raised concerns over its ability to produce offensive results when prompted on sensitive topics, such as feminism and Ethiopia. The findings were reported by users who encountered strong biases in the AI's responses. To address these issues, it is essential to understand how AI can be designed with guardrails for harm prevention and ensure responsible AI practices are implemented. And to support safer AI development, visit JOIN US.

Matched TAIM controls

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

Alleged deployer
Murat Ayfer
Alleged developer
OpenAI, Murat Ayfer
Alleged harmed parties
historically disadvantaged groups

AI governance case studies

For forensic AI governance failure analysis (TAIMScore™ case studies), browse Human Signal’s Failure Files™.

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.