Books

Vector databases give you a similarity metric, an index with four tuning parameters, acompression option and a way to filter — and almost no guidance on what any of it costs. This book builds each one from scratch and measures it. The proximity graph, the invertedfile, the product quantiser: implemented in NumPy, included with the text, and checkedagainst exhaustive search — so every recall figure here is exact rather than estimated.

Both parts of the Transition Playbook in one 139-page volume: the mental models, the orchestration patterns, and two 30-day plans for moving from writing code to directing agents.

Four MCP servers installed end to end without a terminal, plus a troubleshooting decision tree and five workflows to run the day you finish.

Measure where LLM context costs accumulate, then cut them with deduplication, summarization, truncation and cache exploitation, with a cost model that shows the ROI of each.

A machine can hand you a grouping that is confident, stable, internally consistent, and seven times worse than the one it found a moment earlier. Nothing in the output says so.This book works k-means through completely on twelve bakery customers, small enough that every number is printed and checkable. You will build the method from nothing, see exactly where it succeeds, and see exactly where it fails silently.Fifty-eight figures, every one captured from a running implementation.

Every deep learning tutorial shows you the code. Almost none show you the idea. This is the book to read first - before the frameworks, before the maths notation, before the course you've already paid for. One example, followed all the way through, from a random guess to a network that works. By the end you'll understand what backpropagation actually does, why gradients matter, and what's really happening while your model trains. No calculus required.

Prompting has more advice than evidence. This book measures it instead: a model reading apattern it has never seen, the same model failing at a task in one pass and solving itperfectly in four, a decoder that guarantees a format instead of improving the odds, and amodel that is 2.4% accurate while 78.6% confident. Six central claims are built from scratch and measured on a single CPU core. Everythingtaken from published research sits in a grey box marked "Not measured here" — so you neverhave to guess which is which.

AI governance is moving from principle to practice. This hands-on guide shows you how to build, implement and certify an ISO/IEC 42001 AI management system with confidence. From clause-by-clause guidance to practical templates, integration strategies and real-world scenarios, it turns a complex standard into a clear path from foundation to certification.

ਆਪਣੇ ਹੱਥੀਂ ਬਣਾਏ ਇੱਕ ਕੰਮ ਕਰਦੇ LLM ਰਾਹੀਂ AI ਵਾਂਗ ਸੋਚਣਾ ਸਿੱਖੋ। Cray Research ਦੀ ਪਰਖੀ ਅਤੇ ਪਰਵਾਨਿਤ ਸਿਸਟਮ ਸੋਚ ਨੂੰ ਆਧੁਨਿਕ AI 'ਤੇ ਲਾਗੂ ਕਰੋ। ਉਹ ਕੁਝ ਕਰ ਦਿਖਾਓ ਜਿਸਨੂੰ ਹੋਰ ਲੋਕ ਅਸੰਭਵ ਸਮਝਦੇ ਹਨ।

Tanulj meg úgy gondolkodni, mint egy mesterséges intelligencia, egy saját kezűleg felépített, működő nagy nyelvi modell (LLM) segítségével. Ez a Cray Research-nél csiszolt, gyakorlatban bevált rendszerszemléletű gondolkodást alkalmazza a modern MI-re. Érj el olyat, amit mások lehetetlennek tartanak.

Five certifications ask about the same twenty topics, and each one stops at a differentdepth. This book teaches the topic once, properly, then shows you exactly where each examstops — with 61 original practice questions where every wrong option is explained. Every number in it was measured. Every line of code was run. The code is included.

Domine a arquitetura de sistemas de IA autônomos. Um guia completo cobrindo motores de raciocínio, memória de longo prazo, orquestração multiagentes, otimização de custos e o Model Context Protocol (MCP). O livro definitivo para arquitetos e desenvolvedores.

面向智能体重度用户的实战可靠性手册：不教造智能体、不教提示词技巧、不做产品测评； 每天用智能体 2 小时以上、已配多个工具、需要一套可预算 / 可监控 / 可验收的运营方法的实践者；

The EU AI Act is changing the rules for anyone building, buying or using AI. This practical guide cuts through the legal complexity and shows what compliance actually requires. With clear explanations, real-world cases, templates and checklists, it gives leaders and teams the tools to turn regulation into workable AI governance.

The loop writes code and clears context. The commit log records MAX_RETRIES = 3, but the reason it's three vanished on Friday night. The artifact survived; the decision evaporated.The Loop That Remembers inverts the premise: memory isn't the sixth piece, it's what the loop exists to produce. Two graphs, a promoted lattice, bounded context, and an evaluator checking claims against edges.