Meta’s BlenderBot 3 Chatbot Demo Made Offensive Antisemitic Comments

August 7, 2022

The latest conversational AI demo, BlenderBot 3 from Meta, has been found to make occasional offensive comments invoking Jewish stereotypes. This underscores the importance of safe and secure AI practices. For those interested in shaping trustworthy AI, learn how HISPI Project Cerebellum TAIM can help Govern such incidents by mapping them onto our incident database.

JOIN US

Matched TAIM controls

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

MAP 1.6 — similarity 0.659, rank 1. TAIM detail and related incidents →
MEASURE 2.6 — similarity 0.648, rank 2. TAIM detail and related incidents →
MEASURE 2.10 — similarity 0.641, rank 3. TAIM detail and related incidents →

Alleged deployer: meta
Alleged developer: meta
Alleged harmed parties: jewish-people, blenderbot-3-users

Source

Data from the AI Incident Database (AIID). Cite this incident: https://incidentdatabase.ai/cite/278

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.