Incident #477·Human-Computer Interaction
Bing Chat Tentatively Hallucinated in Extended Conversations with Users
Description
Early testers reported Bing Chat, in extended conversations with users, having tendencies to make up facts and emulate emotions through an unintended persona.
Actors
Alleged Deployers
- microsoft
Alleged Developers
- openai
- microsoft
Harmed Parties
- microsoft
Classification
Risk Domain
Human-Computer InteractionRisk Subdomain
5.1. Overreliance and unsafe use
MIT Risk Profile
AIUnintentionalPost-deployment
Source
Related Incidents (Human-Computer Interaction)
View all →Research Papers on This Topic
Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance
1,136 citationsJun 2020
Questioning the AI: Informing Design Practices for Explainable AI User Experiences
1,075 citationsJan 2020
Trust in AI and Its Role in the Acceptance of AI Technologies
957 citationsMar 2022
Metrics for Explainable AI: Challenges and Prospects
944 citationsDec 2018