Publications

Agentic Inequality

Beyond alignment: Why robotic foundation models need context-aware safety

Dynamics of sovereign debt: credit risk and sustainability analysis

AutoControl Arena: Synthesizing Executable Test Environments for Frontier AI Risk Evaluation

Token Taxes: Mitigating AGI’S Economic Risks

Old Habits Die Hard: How Conversational History Geometrically Traps LLMs

Early Internationalists: Bello, Calvo, and Álvarez and Beyond

Automated Interpretability-Driven Model Auditing and Control: A Research Agenda

A Blueprint for Multinational Advanced AI Development

Systemic impacts of disruptions at maritime chokepoints

Getting into the doughnut: A framework for assessing systemic resilience in the global food system

Chain-of-Thought Hijacking

Who Governs Climate Change? Business Interests and the American Clean Energy and Security Act

GCSCC AI Cybersecurity Conference Outcomes Report: Securing the Cyber Future, ‘Cyber Resilience in the Age of AI and Geopolitical Uncertainty’

Do Sparse Autoencoders Generalize? A Case Study of Answerability

Trust Me, I’m Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answer

United Nations Environment Assembly attendees underestimate public willingness to contribute to climate action

Integrating Nature into the IMF-World Bank’s Debt Sustainability Framework for Low Income Countries: A New Systematic Approach to Nature-Economy Risk Assessment

Survey ordering and the measurement of welfare

The value of qualitative approaches to impact evaluation in biodiversity conservation