The broad foundation
Categories for AGI
A detailed introduction to the application of category theory to formulate a research program in artificial general intelligence.
A categorical research program for AI
Four books. One evolving argument.
From functorial models and learning sketches, through infinitesimal creativity, to the discovery of compositional worlds and doctrines.
The sequence
Begin broadly. Then go deeper.
The focused framework
Machine Learning from Enforcing Compositionality
A novel formulation of machine learning, based not on minimizing loss functions, but driven by failures of compositionality.
The theory-extension challenge
Infinitesimal Creativity
A novel framework for modeling creativity as a dual involution over assimilation of experience into an existing theory, and an accommodation process that instead seeks to augment the theory.
The discovery problem
Discovering Compositional Worlds from Interaction
A categorical theory of how lifelong learners discover compositional worlds, their generating presentations, and the doctrines that govern what can be learned.
Read across the series
Follow a question, not necessarily the shelf order.
Categorical foundationsCompositional learningCausality and interventionScientific discoveryVisual generation and repairDoctrines and world discoveryOnline decisions and agentic safety
See all 7 reading paths Browse the cross-book concept map
Look up the shared vocabulary
Release discipline
An ongoing investigation into the future of Artificial General Intelligence
Every public edition receives a dated filename, page count, and checksum. Demonstrated results, formal proposals, conjectures, and open problems remain visibly distinct.
See the theorem and evidence ledger
Open the edition registry
Report a tagged correction