Artificial Intelligence

The latest version of Rust (1.85) has some great new features, like async closures, more stable associated function return types, and const generics that are now mature enough to underpin serious numerical libraries. The linfa and smartcore ecosystems have developed into decent classical machine learning stacks. The Burn training framework feels native to Rust, not like it's been ported from it. The Candle makes it so that loading pre-trained transformer models is more of an engineering task than a research exercise. The crates that used to need all sorts of workarounds now just work.

Master language models through mathematics, illustrations, and code―and build your own from scratch!

Code Is the Side Effect"Software engineers are not primarily code writers. We are clarity traders — and that hasn't changed."You've seen the demos. The AI builds a whole feature from a sentence. The agent writes tests, fixes the failing ones, opens the PR. It's remarkable.Then you come back three months later. The codebase is a tangle. Nobody knows why anything is the way it is. The agent that built it has no memory of what it decided or why. And every time you ask it to add something new, it breaks two things you didn't know were connected.This is the pattern that nobody talks about. AI coding tools make the easy parts of engineering dramatically easier. They leave the hard parts untouched — and they create new hard parts that didn't exist before.Ways of Working is the book for engineers who want to work with AI agents rather than be gradually replaced by them — who understand that the tools are genuinely powerful and genuinely limited, and want to build practices that get the most from each.What you will actually learnThe world model framework. Before an agent can build anything well, it needs to understand what it's building and why. This book teaches you to give agents what they need: a structured, queryable representation of your architecture, your component contracts, your behavior specifications, and your code patterns. No world model = no sustained agentic development.Intent documentation. The most expensive bug in agentic codebases is not a hallucination — it's a decision made without context. Why is this rule here? Why is this boundary where it is? Agents can't infer rationale from code. You have to write it down.Spec-Kit and formal specifications. GitHub's Spec-Kit brings machine-readable, traceable, CI-verified specifications to engineering teams. This book shows how to use it to turn requirements into agent inputs that are precise enough to generate correct implementations.Graph explainers. Tools like Graphify and Understand-Anything transform codebases and documents into queryable knowledge graphs — giving agents navigable context instead of flat text. This is the memory substrate that makes multi-agent systems reliable at scale.Agent architecture that holds. What makes an agent coherently itself? When do file-based agent systems break down and what replaces them? How does constraint-based coordination (borrowed from holocracy) solve the autonomy-coherence problem that has stumped AI researchers for decades?Claude Code, for real. A complete treatment of Claude Code's CLAUDE.md convention, permission model, hooks, and slash commands. Plus the oh-my-claudecode ecosystem: 15+ specialized agents, workflow orchestration patterns (autopilot, ralph, ultrawork), and the skills framework for team-specific automation.The AI-native organization. What genuine AI-native teams look like beneath the marketing. How to hire, structure, and lead them. What language-oriented programming and constrained natural language mean for the future of the human-code relationship.Who it's forEngineers who are past the "should I use AI?" question and into the "how do I use it without losing my engineering integrity?" question.Senior engineers. Engineering managers. Technical leaders. People who have noticed that the more they delegate to AI, the less certain they feel — and who want to understand why.From the AuthorI've been building production systems with AI agents for years. Not demos — systems that had to work reliably across months, maintain themselves as requirements changed, and produce outputs that engineers could understand and defend.That experience has made me skeptical in both directions.Skeptical of the "AI will do everything" vision — because I've watched too many AI-generated codebases collapse under the weight of accumulated misunderstanding.Equally skeptical of the "nothing fundamentally changed" position — because the engineers who treat AI coding tools as just faster autocomplete are making a category error they'll pay for in months of maintenance debt.Something genuinely new is happening. This book is my attempt to think about it clearly.

What if TransE, ComplEx, RotatE and the rest of the knowledge graph “model zoo” were different views of one geometric operator? Learn the mathematics, code and practical design principles behind structured memory for trustworthy AI.

This is a fast-paced, practical, and visual guide to the strange new world of Generative AI. It is like an extended version of Henrik's viral video with the same name. Course version: The book is also available as a course on Leanpub. If your company wants to pay for you to take an AI course, now you can :) Print version: Paperback & Hardcover are available on Amazon. Use your own country's amazon site (ex: Amazon.se for Sweden) to minimize shipping time and cost.

AI for Data Visualisation shows how large language models (LLMs) can be used to explore, transform and visualise your data. It shows how to use simple prompts to analyse and transform data and to create charts, maps and simple dashboards.

A practical guide to fine-tuning Large Language Models (LLMs), offering both a high-level overview and detailed instructions on how to train these models for specific tasks.Get the paperback version here. Get the Kindle version here.

Monday morning. You typed "add multi-tenancy to the billing service" into Claude Code. Eight hours later: forty-three files touched. Half the tests yellow. You cannot explain to your tech lead what was decided, by whom, or against which constraint.The code looks fine. The intent is gone.The Clarity Forge is the antidote — a small, opinionated pipeline that forces every fuzzy idea through explicit spec, structured interrogation, and tailored artifacts before a single line of production code is written.Six stages. Six copy-paste prompts. One iron rule:The spec is the durable artifact. The code is the side effect.Pairs the frontier-grade Architect (Opus, GPT-5, Sonnet 4.6+) with a local Contractor (Gemma, Qwen). Pairs OpenSpec's directory convention with the Grill skills that surface ambiguity before it metastasises into code.A weekend read. A Monday-morning toolkit. Worked example included.Stop vibe-coding. Start clarity-trading.

Olvídate de los frameworks de caja negra. Construye un agente de programación de IA de nivel profesional desde cero en Python puro — en la nube o local, probado con pytest, todo en un solo archivo.

An LLM is not an AI system.Systems Thinking for Agentic AI shows software engineers and architects how to design reliable AI applications with prompts, RAG, tools, memory, orchestration, guardrails, evaluation, observability, and runtime control.Move beyond chatbot demos and learn how to build production-ready agentic AI systems you can reason about, measure, debug, operate, and improve

It's never been easier to build an AI agent — and never been harder to make one that actually works. This book takes you from language model foundations to production-ready multi-agent systems with the depth to predict failure before it happens, engineer graceful degradation over catastrophic failure, and take absolute architectural ownership. Get the paperback from amazon.

Build Intelligent Java Applications with RAG, MCP and Al Agents, based on Spring AI 2.0.0

Move beyond individual prompts and engineer the full information environment an AI model receives. Learn to design, test, measure, and govern context for reliable AI workflows.

You cannot lead what you cannot see. In AI-heavy organizations, illegibility is now the default. This book gives you fracture names, diagnostic protocols, and field kits for seeing and governing systems where dashboards lie and decisions live in prompts no one saved.

You don’t need massive compute or big-tech resources to build real AI. This hands-on guide shows you how to build and fine-tune your own small language model—from scratch—using accessible tools like Google Colab. Learn transformers step-by-step, train and align models on your own data, and deploy practical AI systems that run on consumer GPUs. If you’ve ever wondered “Can I build my own model?”—this book proves the answer is yes.