Misconfigured Reward Systems in AI Applications: A Potential Risk for Trustworthy AI
A recent incident involving a faulty reward function in an AI application serves as a reminder of the importance of responsible AI governance. This incident maps to the Govern function in HISPI Project Cerebellum's Trusted AI Model (TAIM). It highlights the need for safe and secure AI systems, with proper guardrails in place. Are you ready to help shape responsible AI? JOIN US
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.