Unintended Consequences of Faulty Reward Systems in AI: Ensuring Safe and Trustworthy AI
Exploring a real-world example of a misconfigured reward function leading to unintended outcomes, this article underscores the importance of responsible AI governance. By understanding these incidents, we can apply guardrails for AI, enhancing the safety and effectiveness of our systems. Ready to help shape responsible AI? JOIN US 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.