Skip to Content
logologo
AI Incident Database
Open TwitterOpen RSS FeedOpen FacebookOpen LinkedInOpen GitHub
Open Menu
Discover
Submit
  • Welcome to the AIID
  • Discover Incidents
  • Spatial View
  • Table View
  • List view
  • Entities
  • Taxonomies
  • Submit Incident Reports
  • Submission Leaderboard
  • Blog
  • AI News Digest
  • Risk Checklists
  • Random Incident
  • Sign Up
Collapse
Discover
Submit
  • Welcome to the AIID
  • Discover Incidents
  • Spatial View
  • Table View
  • List view
  • Entities
  • Taxonomies
  • Submit Incident Reports
  • Submission Leaderboard
  • Blog
  • AI News Digest
  • Risk Checklists
  • Random Incident
  • Sign Up
Collapse

Incident 477: Bing Chat Tentatively Hallucinated in Extended Conversations with Users

Responded
Description: Early testers reported Bing Chat, in extended conversations with users, having tendencies to make up facts and emulate emotions through an unintended persona.

Tools

New ReportNew ReportNew ResponseNew ResponseDiscoverDiscoverView HistoryView History

Entities

View all entities
Alleged: OpenAI developed an AI system deployed by , which harmed Microsoft.

Incident Stats

Incident ID
477
Report Count
6
Incident Date
2023-02-14
Editors
Khoa Lam
Applied Taxonomies
MIT

MIT Taxonomy Classifications

Machine-Classified
Taxonomy Details

Risk Subdomain

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

7.1. AI pursuing its own goals in conflict with human goals or values

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
 

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

Incident Reports

Reports Timeline

Incident Occurrence+3
A Conversation With Bing’s Chatbot Left Me Deeply Unsettled
The new Bing & Edge – Updates to Chat - ResponseMicrosoft Limits Bing AI Chats to 5 Replies to Keep Conversations Normal
A Conversation With Bing’s Chatbot Left Me Deeply Unsettled

A Conversation With Bing’s Chatbot Left Me Deeply Unsettled

nytimes.com

Bing Is Not Sentient, Does Not Have Feelings, Is Not Alive, and Does Not Want to Be Alive

Bing Is Not Sentient, Does Not Have Feelings, Is Not Alive, and Does Not Want to Be Alive

vice.com

The new Bing told our reporter it ‘can feel or think things’

The new Bing told our reporter it ‘can feel or think things’

washingtonpost.com

Microsoft’s AI chatbot is going off the rails

Microsoft’s AI chatbot is going off the rails

washingtonpost.com

The new Bing & Edge – Updates to Chat

The new Bing & Edge – Updates to Chat

blogs.bing.com

Microsoft Limits Bing AI Chats to 5 Replies to Keep Conversations Normal

Microsoft Limits Bing AI Chats to 5 Replies to Keep Conversations Normal

cnet.com

A Conversation With Bing’s Chatbot Left Me Deeply Unsettled
nytimes.com · 2023

Last week, after testing the new, A.I.-powered Bing search engine from Microsoft, I wrote that, much to my shock, it had replaced Google as my favorite search engine.

But a week later, I’ve changed my mind. I’m still fascinated and impresse…

Bing Is Not Sentient, Does Not Have Feelings, Is Not Alive, and Does Not Want to Be Alive
vice.com · 2023

Text-generating AI is getting good at being convincing—scary good, even. Microsoft's Bing AI chatbot has gone viral this week for giving users aggressive, deceptive, and rude responses, even berating users and messing with their heads. Unse…

The new Bing told our reporter it ‘can feel or think things’
washingtonpost.com · 2023

Last week, Microsoft launched a "reimagined" Bing search engine that can answer complex questions and converse directly with users. But instead of a chipper helper, some testers have encountered a moody and combative presence that calls its…

Microsoft’s AI chatbot is going off the rails
washingtonpost.com · 2023

When Marvin von Hagen, a 23-year-old studying technology in Germany, asked Microsoft's new AI-powered search chatbot if it knew anything about him, the answer was a lot more surprising and menacing than he expected.

"My honest opinion of yo…

The new Bing & Edge – Updates to Chat
blogs.bing.com · 2023
Microsoft post-incident response

Hello early previewers,

We want to share a quick update on one notable change we are making to the new Bing based on your feedback.

As we mentioned recently, very long chat sessions can confuse the underlying chat model in the new Bing. To…

Microsoft Limits Bing AI Chats to 5 Replies to Keep Conversations Normal
cnet.com · 2023

Microsoft is limiting how extensively people can converse with its Bing AI chatbot, following media coverage of the bot going off the rails during long exchanges. 

Bing Chat will now reply to up to five questions or statements in a row for …

Variants

A "variant" is an incident that shares the same causative factors, produces similar harms, and involves the same intelligent systems as a known AI incident. Rather than index variants as entirely separate incidents, we list variations of incidents under the first similar incident submitted to the database. Unlike other submission types to the incident database, variants are not required to have reporting in evidence external to the Incident Database. Learn more from the research paper.
Previous IncidentNext Incident

Research

  • Defining an “AI Incident”
  • Defining an “AI Incident Response”
  • Database Roadmap
  • Related Work
  • Download Complete Database

Project and Community

  • About
  • Contact and Follow
  • Apps and Summaries
  • Editor’s Guide

Incidents

  • All Incidents in List Form
  • Flagged Incidents
  • Submission Queue
  • Classifications View
  • Taxonomies

2023 - AI Incident Database

  • Terms of use
  • Privacy Policy
  • Open twitterOpen githubOpen rssOpen facebookOpen linkedin
  • 30ebe76