Most books about ChatGPT explain the magic. This one shows you the math. Inside Large Language Models, Volume I takes a curious beginner from "what is an LLM" to a complete, trained GPT, with nothing more than high-school algebra, a working laptop, and a willingness to read carefully. Every formula is walked through by hand. Every line of code comes with a plain-English explanation. By the end you will have built, trained, and run your own transformer from scratch, and you will know exactly what is happening inside. No PhD or Data Science required. No prior machine learning needed. Just curiosity and a calculator.
Using AI to code is easy. Using it without losing control — not so much.By week three, your project stops moving. The agent forgets decisions it made ten days ago. A change in auth breaks the dashboard. You spend more time re-explaining context than writing features. The code works, but only you know why — and you're not even sure you remember all of it.That's vibe coding hitting its ceiling.Spec-Driven Development is the method that replaces the chaos with a spec the AI actually executes. Not a ceremonial document. A working artifact: PRD, issues, tests, code — all traceable, all connected, all in the right order.This book shows you:How to grill your own idea before writing a single promptHow to write a PRD the AI won't misinterpretThe 7 phases that turn an idea into working softwareHow to use GitHub SpecKit and openSpec (and when not to)How to work this way in a team without slowing downThe 5 anti-patterns that destroy every spec22,000 words. 13 chapters. 5 appendices with ready-to-copy templates.No theory dumps. No filler. Just the method.
You've set up your agent and taught it your name. With this book you teach it your patterns, your triggers, and the version of yourself you're working towards. 24 chapters. All prompts, no code.
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.
Learn to discover, govern, secure, and operate enterprise AI assets with ServiceNow Super Intelligence Control Tower. A worked IT support scenario connects asset records, approvals, runtime controls, and production operations.
Every agent is a new client. Build the server side like it: OAuth 2.1 audience checks, tenant isolation, rate limits, idempotent tools and defences against tool poisoning, in Go.
Your agent runs at 3 a.m. with nobody watching. Build it like it knows: durable runs, idempotent tools, approvals, budgets, guardrails and evals, in Go.
Claude Code can read your repo, edit files, run tests, and open pull requests. Mastering Claude Code shows engineers and teams how to turn that power into dependable results, from first session to CI pipelines, with verified commands, real workflows, and the judgment to know what to delegate.
AI agents don’t fail because they forget everything. They fail because they remember badly. This book shows you how to engineer memory that stays accurate, efficient and useful over time. From SQLite and PostgreSQL to vector indexes and multi-agent systems, you’ll learn what it takes to build agents that can run for days without losing the plot.
The Python AI ecosystem has hundreds of excellent libraries that nobody writes about because LangChain dominates the conversation. This book covers 38 of them. Each chapter is a practical guide: what the library does, why it exists, how to install it, and working Python code you can run today. No fluff, no theory — just tools and code.
Build powerful AI agents that run entirely on your own hardware with Ollama. Learn practical patterns for RAG, multi-agent systems, security and deployment through clear explanations and production-ready code you can use right away. From first setup to reliable real-world applications, this book helps you build with confidence.
Build AI agents that can see screens, reason about tasks and control desktop applications and web browsers. Starting with a simple prototype, you'll learn how to create reliable production-ready systems that do real work on a computer.
Master Codex CLI from your first prompt to production-ready AI workflows. Learn how to automate coding, streamline development, and use OpenAI's terminal-native coding agent with confidence.
Mastering Qdrant for RAG Applications is your practical guide to building production-ready RAG systems with the leading open-source vector database. Learn how to design, optimize, and scale high-performance vector search using Qdrant through clear explanations, real-world examples, and hands-on code.
Tekoälyagentit ovat siirtyneet demoista tuotantoon. Agenttinen vallankumous näyttää teknisille päälliköille ja kehittäjille, miten agentit rakennetaan, suojataan ja viedään tuotantoon hallitusti, suomalaisesta ja eurooppalaisesta näkökulmasta.