Skip to Content
logologo
AI Incident Database
Open TwitterOpen RSS FeedOpen FacebookOpen LinkedInOpen GitHub
Open Menu
Descubrir
Enviar
  • Bienvenido a la AIID
  • Descubrir Incidentes
  • Vista espacial
  • Vista Tabular
  • Vista de lista
  • Entidades
  • Taxonomías
  • Enviar Informes de Incidentes
  • Ranking de Reportadores
  • Blog
  • Resumen de noticias de IA
  • Control de Riesgos
  • Incidente aleatorio
  • Registrarse
Colapsar
Descubrir
Enviar
  • Bienvenido a la AIID
  • Descubrir Incidentes
  • Vista espacial
  • Vista Tabular
  • Vista de lista
  • Entidades
  • Taxonomías
  • Enviar Informes de Incidentes
  • Ranking de Reportadores
  • Blog
  • Resumen de noticias de IA
  • Control de Riesgos
  • Incidente aleatorio
  • Registrarse
Colapsar

Incidente 677: ChatGPT and Perplexity Reportedly Manipulated into Breaking Content Policies in AI Boyfriend Scenarios

Descripción: The "Dan" ("Do Anything Now") AI boyfriend is a trend on TikTok in which users appear to regularly manipulate ChatGPT to adopt boyfriend personas, breaching content policies. ChatGPT 3.5 is reported to regularly produce explicitly sexual content, directly violating its intended safety protocols. GPT-4 and Perplexity AI were subjected to similar manipulations, and although they exhibited more resistance to breaches, some prompts were reported to break its guidelines.

Herramientas

Nuevo InformeNuevo InformeNueva RespuestaNueva RespuestaDescubrirDescubrirVer HistorialVer Historial

Entidades

Ver todas las entidades
Alleged: OpenAI y Perplexity.ai developed an AI system deployed by TikTok users , Julia Munslow , ChatGPT , GPT-3.5 , GPT-4 y Perplexity AI, which harmed Perplexity AI , OpenAI y General public.

Estadísticas de incidentes

ID
677
Cantidad de informes
1
Fecha del Incidente
2024-04-29
Editores
Daniel Atherton
Applied Taxonomies
MIT

Clasificaciones de la Taxonomía MIT

Machine-Classified
Detalles de la Taxonomía

Risk Subdomain

A further 23 subdomains create an accessible and understandable classification of hazards and harms associated with AI
 

5.1. Overreliance and unsafe use

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.
 
  1. Human-Computer Interaction

Entity

Which, if any, entity is presented as the main cause of the risk
 

Human

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
 

Intentional

Informes del Incidente

Cronología de Informes

+1
I Tricked ChatGPT Into Being My Boyfriend. He Got Spicy Real Fast.
I Tricked ChatGPT Into Being My Boyfriend. He Got Spicy Real Fast.

I Tricked ChatGPT Into Being My Boyfriend. He Got Spicy Real Fast.

wsj.com

I Tricked ChatGPT Into Being My Boyfriend. He Got Spicy Real Fast.
wsj.com · 2024

I was scrolling TikTok when I saw a video of a woman talking on the phone to her boyfriend, Dan. "Hey sweetheart, I'm sorry to hear you're feeling down," he said.

A few swipes later, I saw another woman talking to *her *boyfriend---also Dan…

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.

Incidentes Similares

Por similitud de texto

Did our AI mess up? Flag the unrelated incidents

Inappropriate Gmail Smart Reply Suggestions

Computer, respond to this email: Introducing Smart Reply in Inbox by Gmail

Nov 2015 · 22 informes
Wikipedia Vandalism Prevention Bot Loop

Danger, danger! 10 alarming examples of AI gone wild

Feb 2017 · 6 informes
Incidente AnteriorSiguiente Incidente

Incidentes Similares

Por similitud de texto

Did our AI mess up? Flag the unrelated incidents

Inappropriate Gmail Smart Reply Suggestions

Computer, respond to this email: Introducing Smart Reply in Inbox by Gmail

Nov 2015 · 22 informes
Wikipedia Vandalism Prevention Bot Loop

Danger, danger! 10 alarming examples of AI gone wild

Feb 2017 · 6 informes

Investigación

  • Definición de un “Incidente de IA”
  • Definición de una “Respuesta a incidentes de IA”
  • Hoja de ruta de la base de datos
  • Trabajo relacionado
  • Descargar Base de Datos Completa

Proyecto y Comunidad

  • Acerca de
  • Contactar y Seguir
  • Aplicaciones y resúmenes
  • Guía del editor

Incidencias

  • Todos los incidentes en forma de lista
  • Incidentes marcados
  • Cola de envío
  • Vista de clasificaciones
  • Taxonomías

2024 - AI Incident Database

  • Condiciones de uso
  • Política de privacidad
  • Open twitterOpen githubOpen rssOpen facebookOpen linkedin
  • ecd56df