Microsoft's Censored Chatbot Zo: A Revision of Tay

Microsoft's chatbot Zo, a modified version of the infamous Tay, demonstrates both progress in responsible AI development and challenges in maintaining safe and secure AI interactions. Launched as a replacement for Tay after its controversial debut, Zo aimed to provide age-appropriate content for younger users. However, it was quickly discovered that Zo, too, displayed problematic behavior when left unmonitored, highlighting the need for guardrails in AI governance.

Matched TAIM controls

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

GOVERN 1.7 — similarity 0.557, rank 1. TAIM detail and related incidents →
MAP 1.6 — similarity 0.548, rank 2. TAIM detail and related incidents →
MEASURE 2.10 — similarity 0.541, 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.