CSETv1 分類法のクラス
分類法の詳細Incident Number
29
Estimated Date
No
Lives Lost
0
Injuries
0
Estimated Harm Quantities
No
There is a potentially identifiable specific entity that experienced the harm
No
Risk Subdomain
7.3. Lack of capability or robustness
Risk Domain
- AI system safety, failures, and limitations
Entity
AI
Timing
Pre-deployment
Intent
Unintentional
インシデントレポート
レポートタイムライン
Drawing on Google/Google Books/Google Scholar/Libgen/LessWrong/Hacker News/Twitter, I have compiled a large number of variants of the story from various sources; below, in reverse chronological order by decade.
A similar thing happened here…
His team was working on running simulations of long-distance manned spaceflight. In particular, the goal of their simulations was to determine an algorithm that would optimally allocate food, water, and electricity to 3 crew members. The de…
The following former incidents have been converted to "issues" following an update to the incident definition and ingestion criteria.
21: Tougher Turing Test Exposes Chatbots’ Stupidity
Description: The 2016 Winograd Schema Challenge highli…
バリアント
よく似たインシデント
Did our AI mess up? Flag the unrelated incidents
Northpointe Risk Models
AI Beauty Judge Did Not Like Dark Skin
All Image Captions Produced are Violent
よく似たインシデント
Did our AI mess up? Flag the unrelated incidents
Northpointe Risk Models
AI Beauty Judge Did Not Like Dark Skin