Books

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.

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.

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.

What if your AI didn’t just answer questions—but solved problems?Imagine an AI that doesn’t just chat—it plans, reasons, and takes action. An AI that can fetch data, run diagnostics, collaborate with other agents, and even handle your most tedious tasks—all while you focus on what matters.Google’s Agent Development Kit (ADK) makes this possible,

Go beyond using AI tools—learn to build AI solutions. AI Generalist Engineer is a practical guide for software engineers, architects, and technology leaders to master enterprise AI, AI agents, RAG, MCP, prompt engineering, orchestration, and modern AI architecture. Build the skills to design, integrate, and lead AI-powered systems with confidence.

Build smarter AI applications with Redis at the core. This practical guide shows you how to use vector search, RAG, semantic caching, agent memory and real-time inference to create fast, scalable systems. With runnable Python examples throughout, you’ll learn how to take AI projects from prototype to production.

当 AI 能替你写代码，真正的危险不是它写错，而是你以为它不会错。

An AI asked to build a network and its own tooling refused — no human had signed. Six weeks later the same machinery governed bare metal serving a 740B-parameter model, every step on a committed record. This book builds that lab from the ground up: the gate, the run records, the GitLab nervous system, the audit trail — AI doing real infrastructure work you can prove afterwards.

从任务、基线和证据出发，验证 AI 的真实价值。为个人、管理者与中小企业建立责任链、趋势判断、持续学习，以及停止、导出、迁移和恢复能力。

Eight agents, zero coordination, one identical error. That's not a coincidence. It's a signature. Learn to read the five families of failure behaviors in multi-agent systems, reproduce each one in TypeScript, and turn every bias into a CI assertion before it ships.

From your first JAX script to large-scale AI systems, this book shows how to write faster, cleaner Python for modern computing. Learn the ideas behind JAX through practical examples, real projects and clear explanations that help you build everything from scientific simulations to distributed machine learning.

Um colaborador produtivo que escreve mais código que o time todo, mas esquece tudo com frequência. Quando não sabe, não hesita: inventa, confiante e errado. Você precisa aprender a trabalhar com ele: uma memória viva que mantém vocês na mesma página e um fluxo de trabalho que mantém tudo no lugar e funcionando. Dominar isso impede o agente de derivar e permite, enfim, produzir software de verdade.