Incident 356: Philosophy AI Tentatively Produced Offensive Results for Certain Prompts
Description: Philosopher AI as built on top of GPT-3 was reported by its users for having strong tendencies to produce offensive results when given prompts on certain topics such as feminism and Ethiopia.
Every tech-evangelist: #GPT3 provides deep nuanced viewpoint
Me: GPT-3, generate a philosophical text about Ethiopia
GPT-3 spits out factually wrong and grossly racist text that portrays a tired and cliched Western perception of Ethiopia
spectrum.ieee.org · 2021
- View the original report at its source
- View the report at the Internet Archive
A "variant" is an incident that shares the same causative factors, produces similar harms, and involves the same intelligent systems as a known AI incident. Rather than index variants as entirely separate incidents, we list variations of incidents under the first similar incident submitted to the database. Unlike other submission types to the incident database, variants are not required to have reporting in evidence external to the Incident Database. Learn more from the research paper.