Journal

Notes on research in progress, papers I am reading, and things I am learning. Written to think, not to conclude.

Alignment × Econ

Essays and experiments connecting classic ideas from economics — incentives, information, contracts, mechanism design, and strategic behavior — to the problem of building and evaluating AI systems.

Part 1: You Can't Reward What You Can't See

What a classic 1979 economics paper can teach us about monitoring and aligning modern AI systems.

Part 2: Coming soon

Notes