Books, research and new writing

Understand it.
Build it. Use it.

Books explain the machinery. Articles follow the research, experiments and ideas as they develop. Solutions put them to work.

Fresh from the notebook

Latest writing

All 165 articles →

New ideas, working experiments and the things learned along the way.

Books

Understand the machinery

View all books →

A selection from the growing bookshelf. Each book builds from first principles toward systems you can understand, test and use. Explore the complete collection of 25 books.

42
In development

Distillation From First Principles

Teaching AI to Learn from AI. A first-principles engineering guide to knowledge distillation: knowledge transfer, compression, specialisation, reasoning, evaluation, and lawful improvement of AI systems.

Read 42 chapters →
48
In development

Fine Tuning From First Principles

Understand fine-tuning from gradients and LoRA to data, preference learning, evaluation and release. Build FineTuneLab and learn when not to train.

Read 48 chapters →
38
In development

Adversarial Mathematics: From First Principles

A new approach to mathematical investigation using AI, proof assistants, counterexamples, reproducible experiments, and independently checked evidence.

Read 38 chapters →
39
Published

Language

What form does communication take when intelligence becomes part of the medium through which meaning moves? A first-principles investigation of representation, attention, personal mediation and delegated action.

Read 39 chapters →
46
Published

Pi Agents

A practical book about finding the right layer for agent behaviour, using Pi to see and build each one: from a direct model call, through an agent core and the coding-agent application, out to interfaces and authority boundaries — worked from the least powerful mechanism that solves the problem.

Read 46 chapters →
31
Published

Applied AI

Build from a callable model to explicit context, durable state, controlled actions, independent verification, and a deterministic runtime that decides what happens next.

Read 31 chapters →
Apply

Working systems and solutions

Browse solutions →

The practical destination of the work: projects, diagnostics and tools that turn the underlying ideas into something usable.

Live · Plugin

OpenCode Remembering

A standalone memory runtime for AI agents that separates retrieval, historical recall, temporal validity, current work, trust, decisive selection, traceability, unfinished work, and explicit memory writes from permission to influence present behaviour.

Explore solution →
Live · System

ZeroModel

Evidence-first AI systems where claims, decisions, policy boundaries, failure states and replay remain explicit.

Explore solution →
Live · Runtime

RELATE

A relation-aware embedding runtime that measures identity, compatibility, preservation, and policy-scoped usability instead of trusting raw vector similarity.

Explore solution →
Archive

Explore the article archive.

Browse 165 published articles covering experiments, technical guides and research. New writing appears above automatically as it is published.

Browse all articles