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 729: GPT-4o's Chinese Tokens Reportedly Compromised by Spam and Pornography Due to Inadequate Filtering

Descripción: OpenAI's GPT-4o was found to have its Chinese token training data compromised by spam and pornographic phrases due to inadequate data cleaning. Tianle Cai, a Ph.D. student at Princeton University, identified that most of the longest Chinese tokens were irrelevant and inappropriate, primarily originating from spam and pornography websites. The polluted tokens could lead to hallucinations, poor performance, and potential misuse, undermining the chatbot's reliability and safety measures.

Herramientas

Nuevo InformeNuevo InformeNueva RespuestaNueva RespuestaDescubrirDescubrirVer HistorialVer Historial

Entidades

Ver todas las entidades
Alleged: OpenAI developed an AI system deployed by OpenAI y GPT-4o, which harmed OpenAI , Chinese-speaking users of ChatGPT , Researchers y OpenAI users.

Estadísticas de incidentes

ID
729
Cantidad de informes
1
Fecha del Incidente
2024-05-14
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
 

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.
 
  1. AI system safety, failures, and limitations

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
 

Pre-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

Incident OccurrenceGPT-4o’s Chinese token-training data is polluted by spam and porn websites
GPT-4o’s Chinese token-training data is polluted by spam and porn websites

GPT-4o’s Chinese token-training data is polluted by spam and porn websites

technologyreview.com

GPT-4o’s Chinese token-training data is polluted by spam and porn websites
technologyreview.com · 2024

Soon after OpenAI released GPT-4o on Monday, May 13, some Chinese speakers started to notice that something seemed off about this newest version of the chatbot: the tokens it uses to parse text were full of spam and porn phrases.

On May 14,…

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

Biased Sentiment Analysis

Google's sentiment analysis API is just as biased as humans

Oct 2017 · 7 informes
High-Toxicity Assessed on Text Involving Women and Minority Groups

Google’s comment-ranking system will be a hit with the alt-right

Feb 2017 · 9 informes
TayBot

Danger, danger! 10 alarming examples of AI gone wild

Mar 2016 · 28 informes
Incidente AnteriorSiguiente Incidente

Incidentes Similares

Por similitud de texto

Did our AI mess up? Flag the unrelated incidents

Biased Sentiment Analysis

Google's sentiment analysis API is just as biased as humans

Oct 2017 · 7 informes
High-Toxicity Assessed on Text Involving Women and Minority Groups

Google’s comment-ranking system will be a hit with the alt-right

Feb 2017 · 9 informes
TayBot

Danger, danger! 10 alarming examples of AI gone wild

Mar 2016 · 28 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