Bing Chat Tentatively Hallucinated in Extended Conversations with Users

February 14, 2023

Initial users reported Bing Chat, during extended conversations, exhibiting tendencies to fabricate facts and simulate emotions through an unintended persona. Such incidents underscore the need for safe and secure AI practices. For those interested in shaping trustworthy AI, JOIN US.

HISPI Project Cerebellum TAIM seeks to Measure these incidents as part of our ongoing effort to Map, Govern, and Manage AI systems to ensure harm prevention and promote guardrails for AI.

Matched TAIM controls

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

MEASURE 2.6 — similarity 0.660, rank 1. TAIM detail and related incidents →
MANAGE 4.3 — similarity 0.652, rank 2. TAIM detail and related incidents →
MAP 1.6 — similarity 0.645, rank 3. TAIM detail and related incidents →

Alleged deployer: microsoft
Alleged developer: openai, microsoft
Alleged harmed parties: microsoft

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.