Books, tools, experiments and working solutions for agents, context, memory, language, retrieval and AI applications.
The books work through difficult subjects from first principles. The goal is not to stop at explanation: each path should lead toward something that can be built, tested or used.
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 → 35A build-and-investigate book about typed, uncertain decisions as a programming abstraction: reconstructing the Jev idea from first principles, testing it against classifiers, embeddings, NLI and language-model alternatives, and building a decision stack that keeps uncertainty, evidence and provider choice explicit.
Read 35 chapters → 25Build browser-native AI from the capability boundary upward: local models, observability, WebMCP tools, agent security, and a user-owned browser policy engine.
Read 25 chapters → 36What 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 36 chapters → 21Build AI memory from storage and retrieval through provenance, temporal state, unfinished work, context selection, behavioural evaluation, trust, the boundary with learning, and the promotion boundary from memory to durable knowledge — adding only the mechanisms that measurement earns.
Read 21 chapters → 21Turn language-model behavior into an experimental variable, then learn when optimization is measurable, when improvement is trustworthy, and what DSPy contributes to the process.
Read 21 chapters → 30Build from a callable model to explicit context, durable state, controlled actions, independent verification, and a deterministic runtime that decides what happens next.
Read 30 chapters → 26Explore what it means for information to become geometry, when that geometry can be trusted, and how representation, similarity, retrieval, calibration, cross-space alignment, and compression combine into an embedding runtime that knows its own limits.
Read 26 chapters → 27Context as a compiled, observable artefact: see what a model actually receives, learn what capacity, content, representation, time, authority and scope each demand, then build a deterministic Context Compiler, deliver its output to a runtime, observe that it arrived, and test whether it helped.
Read 27 chapters → 19 Artificial life, complex systems and computational emergenceAn experimental search for life-like organization in computational systems — through emergence, causality, persistence, material turnover, hidden state and finite computation.
Read 19 chapters → 16Explore why language models hallucinate, how hallucination can be measured and evaluated, where individual detection methods fail, and how evidence, verification, policy, abstention, and memory gates can be combined to build reliable systems around stochastic models.
Read 16 chapters → 16Understand PyTorch from first principles — from tensor geometry and autograd to model structure, transforms, attention, debugging, performance, compilation, reproducibility, and a GPT-style model built from scratch.
Read 16 chapters → 13Learn to read modern AI models by decomposing them into smaller mechanisms, then rebuilding quality scorers, value and policy heads, recurrent reasoning systems, optimizers, and preference rankers in PyTorch.
Read 13 chapters → 11Build reliable AI agents by understanding the mechanisms underneath them: control loops, actions, validation, planning, state, tools, memory, search, and external verification.
Read 11 chapters → 59Build cellular automata from the smallest local rules, then follow them through measurement, computation, continuous artificial life, learned dynamics and reproducible engineering. A first-principles investigation of what simple local systems can do — and how to tell what the evidence actually supports.
Read 59 chapters → 47Go beyond basic agent loops into orchestration, evaluation, reliability, multi-step reasoning, memory, and production-grade agent systems.
Read 47 chapters → 60Progress from deterministic debugging to diagnosing models, evidence, trajectories, and AI-generated work.
Read 60 chapters → 32Think, create, research, write, and build with AI through open conversation, clear intent, structured reflection, iterative collaboration, and amplified creation.
Read 32 chapters → 16Explore how LLM agents grow from simple conversations into reflective, tool-using, memory-enabled and multi-agent systems—and how those systems can become collaborators, companions, interfaces, and extensions of human agency. Second edition: verified sources, frozen terminology, executed examples with negative controls, and evidence boxes that state exactly what each result supports.
Read 16 chapters →The practical destination of the work: projects, diagnostics and tools that turn the underlying ideas into something usable.
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 →Move beyond isolated prompts into reusable techniques, composed workflows and working sessions.
Explore solution →Evidence-first AI systems where claims, decisions, policy boundaries, failure states and replay remain explicit.
Explore solution →Embeddings are everywhere in modern AI. They power semantic search, retrieval-augmented generation, recommendations, clustering, duplicate detection, code search, memory systems, …
Read →For decades, the technological singularity has been presented as a future event. At some point, an artificial intelligence would become as intelligent as a human being, improve …
Read →What happens when a system stops asking an AI for the same directions repeatedly, and starts placing signs where decisions need to be made? ZeroModel in One Image Most AI systems …
Read →We Trained a Model on Editorial Choices to See Whether It Learned What Happened Next Most preference-learning systems use a choice to change the future. A model produces two …
Read →Evidence that the alternative a writer rejects can help predict the future stability of what they retain.
Read →An AI-assisted model of how GDP optics, housing pressure, debt rollover, and fiscal constraint can hide citizen insolvency. 1. A Country Is Its Citizens A country is not its GDP, …
Read →