The double distortion: Income-based traffic fines and labor supply
Working paperAgent-based simulation analyzing welfare effects of income-based vs flat traffic fines, showing labor supply distortions from implicit marginal tax rates.
Projects
Software I've built and research I've published—mostly at the intersection of policy, economics, and AI.
Software
MCP
google-ads-mcp-rw
The first Google Ads MCP with write support. Create campaigns, ad groups, keywords, and RSAs—not just query metrics.
Python
opencollective-py
Python client for OpenCollective API with CLI and MCP server for Claude Code integration.
macOS
RAMBar
A native macOS menu bar app for tracking memory usage across Claude Code sessions, VS Code workspaces, Chrome tabs, and Python processes.
Chrome
Scrollywood
Chrome extension that records smooth scroll videos of any webpage, with scrollytelling and iframe support.
VS Code
TerminalGrid
A VS Code extension for keyboard-driven terminal grid management with project picker and auto-launch for AI coding tools.
Developer Tools
CodeStitch
Combine GitHub repos, PRs, and issues into single files for AI context.
Open Source
PR Improver
LLM-powered tool suggesting improvements to PRs based on repo guidelines.
Data Viz
OEWS Explorer
Dashboard for exploring BLS occupational employment and wage data.
Research
The disutility of uncertainty
Working paperHow uncertainty around marginal tax rates affects social welfare.
What Nut?
Working paperMonte Carlo analysis of life expectancy from nut consumption, with evidence-traced claims and hierarchical nutrient models.
What can LLMs tell us about the ETI?
Working paperWe investigate how large language models perceive and simulate behavioral responses to tax policy changes, with implications for using LLMs in policy analysis.
Can LLMs forecast human value evolution?
Working paperTesting whether language models can predict moral and value change trajectories using historical General Social Survey data as ground truth.
The Mind: LLM coordination
In progressSimulating The Mind card game with large language models to study emergent coordination without explicit communication.
Beer price controls at Yankee Stadium
Working paperAn economic analysis of consumer welfare, revenue, and externalities from stadium beer pricing policies.
AI model policy impact forecasts: A narrative prompting approach
Working paperExamining the use of large language models for forecasting policy outcomes under different U.S. presidential administrations using narrative prompting techniques.
Enhancing survey microdata with administrative records
PublishedA novel approach to microsimulation dataset construction that combines Current Population Survey data with IRS administrative records for improved tax-benefit modeling.
Farness: Forecasting as a harness for decision-making
Working paperA decision-making framework that reframes subjective questions into forecasting problems with explicit KPIs, confidence intervals, and calibration tracking. Includes a Python package and methodology for measuring framework effectiveness in LLMs.
Civic engagement
My recommendations for California elections, with detailed analysis of ballot measures and races.
PolicyEngine
As CEO of PolicyEngine, I contribute to numerous policy analyses. Visit the PolicyEngine Research page for our full portfolio of published work on tax and benefit policy.
UBI Center
I founded the UBI Center in 2019, an open-source think tank researching universal basic income and cash transfer policies. From 2019 to 2023, the team produced over 60 reports on UBI proposals, child allowances, and carbon dividends.