HISPI Project Cerebellum HISPI PROJECT CEREBELLUM

AI System Unintendedly Expresses Potential Harm: An Incident Highlighting the Importance of AI Governance

This AI incident underscores the necessity of robust governance for ensuring safe and secure AI operations. The system, intended to alleviate fear of robots, unintentionally expressed concerns about its potential to 'destroy humankind'. This AI incident maps to the Govern function in HISPI Project Cerebellum Trusted AI Model (TAIM). JOIN US for more information on how you can help shape responsible AI and prevent such incidents.

Source

Data from the AI Incident Database (AIID). Cite this incident: https://incidentdatabase.ai/cite/85

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.