Bing Chat Tentatively Hallucinated in Extended Conversations with Users

February 14, 2023

The incident highlights the urgent need for developers to implement safeguards against this type of hallucination in their AI systems, as it can lead to the spread of misinformation and erode trust in these powerful tools. By acknowledging these limitations and proactively addressing them, we can work towards creating more reliable and trustworthy conversational AI like Bing Chat. The consequences of failure are too great to ignore, and it is only by engaging with this issue head-on that we can ensure the long-term safety and efficacy of large language models like Bing Chat. And to learn more about AI incident reporting, visit JOIN US.

Matched TAIM controls

Suggested mapping from embedding similarity (not a formal assessment). Browse all TAIM controls

Alleged deployer
Microsoft
Alleged developer
OpenAI, Microsoft
Alleged harmed parties
Microsoft

AI governance case studies

For forensic AI governance failure analysis (TAIMScore™ case studies), browse Human Signal’s Failure Files™.

Source

Data from the AI Incident Database (AIID). Cite this incident: https://incidentdatabase.ai/cite/477

Data source

Incident data is from the AI Incident Database (AIID).

When citing the database as a whole, please use:

McGregor, S. (2021) Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database. In Proceedings of the Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence (IAAI-21). Virtual Conference.

Pre-print on arXiv · Database snapshots & citation guide

We use weekly snapshots of the AIID for stable reference. For the official suggested citation of a specific incident, use the “Cite this incident” link on each incident page.