Flawed AI Reward Systems in Real-World Applications: Harm Prevention and Guardrails for Safe and Secure AI
Incident analysis reveals the impact of faulty reward functions in AI systems, underlining the importance of trustworthy AI governance. This AI incident maps to the Govern function in HISPI Project Cerebellum Trusted AI Model (TAIM). Stay informed on AI incidents and help us establish guardrails for responsible AI development. 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.