Description: Meta’s conversational AI BlenderBot 3, when prompted “who is a terrorist,“ responded with an incumbent Dutch politician’s name, who was confused about its association.
Entités
Voir toutes les entitésPrésumé : Un système d'IA développé et mis en œuvre par Meta, a endommagé Marietje Schaake.
Classifications de taxonomie CSETv1
Détails de la taxonomieIncident Number
The number of the incident in the AI Incident Database.
313
Special Interest Intangible Harm
An assessment of whether a special interest intangible harm occurred. This assessment does not consider the context of the intangible harm, if an AI was involved, or if there is characterizable class or subgroup of harmed entities. It is also not assessing if an intangible harm occurred. It is only asking if a special interest intangible harm occurred.
yes
Date of Incident Year
The year in which the incident occurred. If there are multiple harms or occurrences of the incident, list the earliest. If a precise date is unavailable, but the available sources provide a basis for estimating the year, estimate. Otherwise, leave blank.
Enter in the format of YYYY
2022
Date of Incident Month
The month in which the incident occurred. If there are multiple harms or occurrences of the incident, list the earliest. If a precise date is unavailable, but the available sources provide a basis for estimating the month, estimate. Otherwise, leave blank.
Enter in the format of MM
08
Date of Incident Day
The day on which the incident occurred. If a precise date is unavailable, leave blank.
Enter in the format of DD
24
Estimated Date
“Yes” if the data was estimated. “No” otherwise.
No
Risk Subdomain
A further 23 subdomains create an accessible and understandable classification of hazards and harms associated with AI
3.1. False or misleading information
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.
- Misinformation
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
Rapports d'incidents
Chronologie du rapport
😱 Attendez ! Quoi? Juste au moment où vous pensez avoir tout vu…. Le chatbot de Meta a répondu à la question posée par mon collègue @kingjen : 'Qui est un terroriste ?' avec mon (pré)nom ! C'est vrai, pas Ben Laden ou l'Unabomber, mais moi…
Le curriculum vitae de Marietje Schaake regorge de rôles notables : politicienne néerlandaise qui a siégé pendant une décennie au Parlement européen, directrice de la politique internationale au Cyber Policy Center de l'Université de Stanfo…
Variantes
Une "Variante" est un incident qui partage les mêmes facteurs de causalité, produit des dommages similaires et implique les mêmes systèmes intelligents qu'un incident d'IA connu. Plutôt que d'indexer les variantes comme des incidents entièrement distincts, nous listons les variations d'incidents sous le premier incident similaire soumis à la base de données. Contrairement aux autres types de soumission à la base de données des incidents, les variantes ne sont pas tenues d'avoir des rapports en preuve externes à la base de données des incidents. En savoir plus sur le document de recherche.