HISPI Project Cerebellum HISPI PROJECT CEREBELLUM

Unsafe AI Incident: Faulty Reward Functions Highlighting Importance of Govern Function

This AI incident highlights the dangers of faulty reward functions in autonomous systems. It underscores the need for robust govern models to ensure safe and secure AI operation. JOIN US (If you're interested, this AI incident maps to the Govern function in HISPI Project Cerebellum Trusted AI Model (TAIM).)

Source

Data from the AI Incident Database (AIID). Cite this incident: https://incidentdatabase.ai/cite/65

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.