Thesis: Digital abstraction simplifies coordination by dramatically reducing the complexity of verifiability and enforcement. It is primarily the progress of computation, not game theory, that fuels modern progress in coordination. Since AI happens to be digitally abstracted, it will enable a further revolution in coordination technology.
Suppose we want to cooperate in order to avoid some kind of prisoner’s-dilemma-esque tragedy of the commons. A normal pattern here is to agree to cooperate optimistically, and also punish anyone who doesn’t cooperate.
Notes on Active Inference
May 28, 2025
Disentangling the properties of the Active Inference algorithm.
How intelligence helps (and hurts) alignment
Mar 5, 2023
An initial reaction to AI alignment concerns.
Differential Privacy and Generalization
Dec 13, 2020
How differential privacy can be used to help solve problems of overfitting in adaptive data analysis.
Learning and Uniform Convergence
Nov 11, 2020
First post in a series on generalization in machine learning.
Plenoptic Camera Notes
Jul 1, 2019
Working notes related to the use of a plenoptic camera for estimating depth within a scene.