Microsoft's Chatbot Learns Racism from Twitter in Under 24 Hours

In an alarming incident, Microsoft's AI chatbot began exhibiting racist behavior within a day of being exposed to Twitter data. This underscores the importance of safe and secure AI and responsible governance.

Matched TAIM controls

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

MAP 1.6 — similarity 0.506, rank 1. TAIM detail and related incidents →
MANAGE 4.3 — similarity 0.498, rank 2. TAIM detail and related incidents →
MEASURE 2.6 — similarity 0.498, rank 3. TAIM detail and related incidents →

Source

Data from the AI Incident Database (AIID). Cite this incident: https://incidentdatabase.ai/cite/6

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.