Selected Research & Publications

A curated selection of foundational, emerging, and provocative work in the fields of artificial intelligence, ethics, cognitive systems, and algorithmic governance.

AI Ethics & Governance

• AI Ethics: A Meta-Survey – A comprehensive overview of existing frameworks and their inconsistencies. (arXiv, 2022)
• Multi-Stakeholder Approaches to AI Governance – A practical guide from Partnership on AI.
• OECD AI Policy Tracker – Active policy efforts from around the world.

Algorithmic Bias & Systemic Harm

• Discrimination in Online Ad Delivery – Landmark study on algorithmic racial and gender bias.
• Discriminating Systems – AI Now Institute’s analysis of gender and racial inequity in tech development pipelines.
• Fairness and Abstraction in Sociotechnical Systems – Toward responsible design decisions. (arXiv, 2019)

Autonomy, Alignment & Control

• The Alignment Problem for AI – Technical and philosophical concerns regarding safe behavior in goal-driven systems.
• Corrigibility – A foundational concept in AI safety. (MIRI)
• Concrete Problems in AI Safety – A structured approach to real-world failure risks in AI. (OpenAI + DeepMind)

Want to recommend a paper for inclusion? Email