Descripción: Pak 'n' Save's AI-based app, Savey Meal-bot, inadvertently suggested dangerous recipes, including one creating chlorine gas, when users entered non-food household items, raising safety and oversight concerns.
Entidades
Ver todas las entidadesPresunto: un sistema de IA desarrollado e implementado por Pak 'n' Save, perjudicó a Potential users of the Savey Meal-bot.
Clasificaciones de la Taxonomía CSETv1
Detalles de la TaxonomíaIncident Number
The number of the incident in the AI Incident Database.
594
AI Tangible Harm Level Notes
Notes about the AI tangible harm level assessment
People could misuse the AI to get harmful recipes--but they would have to intentionally put inedible ingredients into the AI to get these harmful recipes. This is an example of AI misuse.
Notes (special interest intangible harm)
Input any notes that may help explain your answers.
People could misuse the AI to get harmful content (ie recipes)
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
Risk Subdomain
A further 23 subdomains create an accessible and understandable classification of hazards and harms associated with AI
7.3. Lack of capability or robustness
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.
- AI system safety, failures, and limitations
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
Informes del Incidente
Cronología de Informes
Un supermercado Nueva Zelanda que está experimentando con el uso de inteligencia artificial para generar planes de comidas ha visto cómo su aplicación produce algunos platos inusuales, recomendando a los clientes recetas con cloro gaseoso m…
Variantes
Una "Variante" es un incidente que comparte los mismos factores causales, produce daños similares e involucra los mismos sistemas inteligentes que un incidente de IA conocido. En lugar de indexar las variantes como incidentes completamente separados, enumeramos las variaciones de los incidentes bajo el primer incidente similar enviado a la base de datos. A diferencia de otros tipos de envío a la base de datos de incidentes, no se requiere que las variantes tengan informes como evidencia externa a la base de datos de incidentes. Obtenga más información del trabajo de investigación.