Writing
Notes on the systems I build and the research behind them: symbolic world-models, autotelic agents, open-ended skill learning, evaluation, and applied machine learning. Posts are grouped by the project they belong to.
Cubist
Jul 3, 2026· 12 min read
Laws from single experiences: an online symbolic world-model for ARC-AGI-3
Cubist's world-model learns each ARC-AGI-3 game's mechanics as a small theory of symbolic laws, online, from single experiences, with no pretraining and no gradients. This post presents the representation, the learning algorithm, and an evaluation across all 25 public games.
Jul 1, 2026· 10 min read
Symbolic descent: gradient descent, applied to rules instead of weights
Symbolic descent keeps the shape of gradient descent but changes the object it optimizes, from a weight vector to a readable theory of laws. This post explains the parallel, the machinery that makes it work, and what it buys for continual learning, reasoning, and interpretability.