Artificial Intelligence

Navigate the architectural discontinuity of the Foundation Model Era with this comprehensive guide designed for professionals sitting at the intersection of technology and leadership. Master the intersection of technical precision and strategic oversight through the RACE framework, robust ethical principles, and the operational realities of MLOps. From the legal mandates of the EU AI Act to the emerging risks of agentic AI, this guide empowers you to lead AI transformation with intention and accountability.

Master the definitive fusion of Swift 6 and Spatial AI to architect the future of visionOS. Leverage LiDAR, Core ML, and real-time hand tracking to build apps that truly understand reality. From persistent world-locking to RealityKit ECS, implement the blueprints of professional 3D engineering. Go beyond basic windows—design immersive, intelligent experiences ready for the visionOS App Store.

Stop building chatbots and start building agents that interact directly with the Android OS. Master Gemini Nano and AICore to architect autonomous systems that see, think, and take action. Implement production-ready Tool Calling, Screen Awareness, and the ReAct loop using Kotlin 2.x. Move beyond the API call—embrace the Agentic Era and build the future of mobile intelligence.

Master high-performance Edge AI by orchestrating NPUs, GPUs, and DSPs for real-time mobile intelligence. Run complex models at 60 FPS using advanced quantization, weight pruning, and NDK optimization. Leverage Kotlin 2.x and zero-copy pipelines to build battery-efficient and thermally stable AI features. The definitive engineering guide for shipping the "last mile" of AI deployment on modern Android SoCs.

AI can write code faster than any human can review it. That changes the economics of engineering, but not what engineering is for. The bottleneck has moved from building to judging —and judgment cannot be prompt-engineered into a system designed for cheap proposals.

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.

A practical handbook for building deterministic, auditable AI pipelines with safety gates, capability profiles, audit trails, telemetry and production deployment patterns.

The era of cloud-only AI is over. Transition from calling remote APIs to building on-device brains using Gemini Nano, local LLMs, and private RAG pipelines.Master the hardware orchestration and Kotlin architecture needed for privacy, zero latency, and production-grade mobile intelligence.Stop being just a developer—become an Android AI Engineer and lead the 2026 mobile revolution today!

Code is cheap. The real challenge now is managing AI agents.

Learn how to code AI agents safely and securely, with auto approved actions or permission controls, all without any special frameworks or dependencies.

Usar IA para programar é fácil. Usá-la sem perder o controle, nem tanto. Spec-Driven Development é o método para transformar sua ideia em uma spec que a IA executa com precisão — sem loops infinitos, sem código quebrado, sem começar do zero.

Claude Code users routinely spend more on tokens than they expect, and cannot see where the money goes. Chapter 8 catalogues 48 diagnostic symptoms — what each one looks like, what it costs you, and what to change — with a fix where a fix exists, and an honest "unresolved" where none does yet. Chapter 7 puts before-and-after numbers against the changes, measured on the author's own unattended runs, and Chapter 9 collects the settings templates.

This book presents an architecture-first approach to designing trustworthy GenAI applications. Using Digital Forensics and Incident Response (DFIR) as a continuous case study, you will progressively build an AI-assisted investigation system. If you want to move beyond building AI applications that simply work, and start architecting AI systems that professionals can trust, this book is for you.

跳过黑箱框架。用纯 Python 从零构建生产级 AI 编程智能体——云端或本地，用 pytest 测试，全部在一个文件中完成。