Skip to Content
logologo
AI Incident Database
Open TwitterOpen RSS FeedOpen FacebookOpen LinkedInOpen GitHub
Open Menu
Découvrir
Envoyer
  • Bienvenue sur AIID
  • Découvrir les incidents
  • Vue spatiale
  • Vue de tableau
  • Vue de liste
  • Entités
  • Taxonomies
  • Soumettre des rapports d'incident
  • Classement des reporters
  • Blog
  • Résumé de l’Actualité sur l’IA
  • Contrôle des risques
  • Incident au hasard
  • S'inscrire
Fermer
Découvrir
Envoyer
  • Bienvenue sur AIID
  • Découvrir les incidents
  • Vue spatiale
  • Vue de tableau
  • Vue de liste
  • Entités
  • Taxonomies
  • Soumettre des rapports d'incident
  • Classement des reporters
  • Blog
  • Résumé de l’Actualité sur l’IA
  • Contrôle des risques
  • Incident au hasard
  • S'inscrire
Fermer
Entités

Perplexity AI

Affecté par des incidents

Incident 6771 Rapport
ChatGPT and Perplexity Reportedly Manipulated into Breaking Content Policies in AI Boyfriend Scenarios

2024-04-29

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.

Plus

Incidents involved as Deployer

Incident 6771 Rapport
ChatGPT and Perplexity Reportedly Manipulated into Breaking Content Policies in AI Boyfriend Scenarios

2024-04-29

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.

Plus

Entités liées
Autres entités liées au même incident. Par exemple, si le développeur d'un incident est cette entité mais que le responsable de la mise en œuvre est une autre entité, ils sont marqués comme entités liées.
 

Entity

TikTok users

Incidents involved as Deployer
  • Incident 677
    1 Report

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

  • Incident 677
    1 Report

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

Plus
Entity

Julia Munslow

Incidents involved as Deployer
  • Incident 677
    1 Report

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

  • Incident 677
    1 Report

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

Plus
Entity

ChatGPT

Incidents involved as Deployer
  • Incident 677
    1 Report

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

  • Incident 677
    1 Report

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

Plus
Entity

GPT-3.5

Incidents involved as Deployer
  • Incident 677
    1 Report

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

  • Incident 677
    1 Report

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

Plus
Entity

GPT-4

Incidents involved as Deployer
  • Incident 677
    1 Report

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

  • Incident 677
    1 Report

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

Plus
Entity

OpenAI

Affecté par des incidents
  • Incident 677
    1 Report

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

  • Incident 677
    1 Report

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

Incidents involved as Developer
  • Incident 677
    1 Report

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

  • Incident 677
    1 Report

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

Plus
Entity

Perplexity.ai

Incidents involved as Developer
  • Incident 677
    1 Report

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

  • Incident 677
    1 Report

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

Plus
Entity

General public

Affecté par des incidents
  • Incident 677
    1 Report

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

  • Incident 677
    1 Report

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

Plus

Recherche

  • Définition d'un « incident d'IA »
  • Définir une « réponse aux incidents d'IA »
  • Feuille de route de la base de données
  • Travaux connexes
  • Télécharger la base de données complète

Projet et communauté

  • À propos de
  • Contacter et suivre
  • Applications et résumés
  • Guide de l'éditeur

Incidents

  • Tous les incidents sous forme de liste
  • Incidents signalés
  • File d'attente de soumission
  • Affichage des classifications
  • Taxonomies

2024 - AI Incident Database

  • Conditions d'utilisation
  • Politique de confidentialité
  • Open twitterOpen githubOpen rssOpen facebookOpen linkedin
  • 1420c8e