Hello! I am an applied researcher interested in AI safety, alignment, and scalable oversight. I am an Athena AI Research Fellow, where I work on a red-teaming project (ChatGPT, Claude, Gemini) and AI policy research in international contexts. I am also a data scientist at Condé Nast, contributing to LLMs and experimentation, and a consultant at The World Bank, where I study the use of AI in civil service environments.
Previously I:
- co-designed and -implemented a $2.5M experimental research portfolio on organizations, incentives, and governance with The World Bank, a top 10 economic research institution;
- contributed to a research initiative studying hierarchy and oversight in Paraguay with researchers from UC Berkeley and University of Wisconsin;
- managed large-scale fieldwork and data collection in Peru with Innovations for Poverty Action and researchers at UC Berkeley and Princeton; and
- designed, ran, and analyzed experiments on biases in recruitment and hiring with the Mind, Behavior, and Development Unit.
I studied Economics at the University of Wisconsin and Barcelona School of Economics.
I am on LinkedIn, GitHub, and Google Scholar. Feel free to get in touch at patriciarosepaskov at gmail dot com.