Tougher Turing Test Exposes Chatbots’ Stupidity (migrated to Issue)

July 14, 2016

The 2016 Winograd Schema Challenge underscores the boundaries of sophisticated AI systems, with these participating AI models only slightly outperforming random chance (3%) in solving complex linguistic tasks. This incident serves as a reminder about the need for trustworthy and safe AI practices. For those interested in shaping the future of responsible AI, consider joining Project Cerebellum.

This event aligns with the HISPI Project Cerebellum TAIM's Govern function to promote AI governance and establish guardrails for AI.

Matched TAIM controls

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

MEASURE 2.6 — similarity 0.694, rank 1. TAIM detail and related incidents →
MAP 1.6 — similarity 0.669, rank 2. TAIM detail and related incidents →
MEASURE 4.2 — similarity 0.668, rank 3. TAIM detail and related incidents →

Alleged deployer: researchers
Alleged developer: researchers
Alleged harmed parties: researchers

Source

Data from the AI Incident Database (AIID). Cite this incident: https://incidentdatabase.ai/cite/21

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.