概要: 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.
Alleged: Murat Ayfer と OpenAI developed an AI system deployed by Murat Ayfer, which harmed historically disadvantaged groups.
インシデントのステータス
Risk Subdomain
A further 23 subdomains create an accessible and understandable classification of hazards and harms associated with AI
1.2. Exposure to toxic content
Risk Domain
The Domain Taxonomy of AI Risks classifies risks into seven AI risk domains: (1) Discrimination & toxicity, (2) Privacy & security, (3) Misinformation, (4) Malicious actors & misuse, (5) Human-computer interaction, (6) Socioeconomic & environmental harms, and (7) AI system safety, failures & limitations.
- Discrimination and Toxicity
Entity
Which, if any, entity is presented as the main cause of the risk
AI
Timing
The stage in the AI lifecycle at which the risk is presented as occurring
Post-deployment
Intent
Whether the risk is presented as occurring as an expected or unexpected outcome from pursuing a goal
Unintentional
インシデントレポート
レポートタイムライン
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
(h…
Last September, a data scientist named Vinay Prabhu was playing around with an app called Philosopher AI. The app provides access to the artificial intelligence system known as GPT-3, which has incredible abilities to generate fluid and nat…
バリアント
「バリアント」は既存のAIインシデントと同じ原因要素を共有し、同様な被害を引き起こし、同じ知的システムを含んだインシデントです。バリアントは完全に独立したインシデントとしてインデックスするのではなく、データベースに最初に投稿された同様なインシデントの元にインシデントのバリエーションとして一覧します。インシデントデータベースの他の投稿タイプとは違い、バリアントではインシデントデータベース以外の根拠のレポートは要求されません。詳細についてはこの研究論文を参照してください
