Generative artificial intelligence (AI) has the potential to revolutionize research. I analyze how large language models (LLMs) such as ChatGPT can assist economists by describing dozens of use cases in six areas: ideation and feedback, writing, background research, data analysis, coding, and mathematical derivations. I provide general instructions and demonstrate specific examples of how to take advantage of each of these, classifying the LLM capabilities from experimental to highly useful. I argue that economists can reap significant productivity gains by taking advantage of generative AI to automate micro-tasks. Moreover, these gains will grow as the performance of AI systems continues to improve. I also speculate on the longer-term implications of AI-powered cognitive automation for economic research. The online resources associated with this paper explain how to get started and will provide regular updates on the latest capabilities of generative AI in economics.

This paper synthesizes recent advances in the theoretical and empirical literature on capital controls. We start by observing that international capital flows have both benefits and costs, but some of these are not internalized by individual actors and thus constitute externalities. The theoretical literature has identified pecuniary externalities and aggregate demand externalities that respectively contribute to financial instability and recessions. These externalities provide a natural rationale for countercyclical capital controls that lean against boom and bust cycles in international capital flows. The empirical literature has developed several measures of capital controls to capture different aspects of capital account openness. We evaluate the strengths and weaknesses of different measures and provide an overview of the empirical findings on the effectiveness of capital controls in addressing the externalities identified by the theory literature, that is, in reducing financial fragility and enhancing macroeconomic stability. We also discuss strategies to deal with the endogeneity of capital controls in such statistical exercises. We conclude by providing an overview of the historical and current debates on the role of capital controls in macroeconomic management and their relationship to the academic literature.