Artificial Intelligence

Blockchain does not remove trust. It moves trust into code everyone can verify.

vLLM and SGLang, side by side. Learn how LLM serving works, measure both engines fairly, tune them with evidence, and take a model from an empty GPU to a deployment with a cost per million tokens you can defend.

AI can write code, create images and make decisions, but do you really understand what happens behind the scenes? This book cuts through the hype to explore how AI works, where it falls short and what it takes to build reliable systems. If you want to understand AI beyond the chat window, start with the code.

Building AI agents is one thing. Making them reliable in production is another. This book explores why agents fail and how to design systems that hold up under real-world conditions. From architecture and engineering patterns to evaluation and operations, it gives technical leaders the tools to build agents they can trust.

Follow one continuing case study from prompt design and structured data to Python, automation, agent frameworks, retrieval, and security.

Every second, a machine makes a decision for you. Can it prove it? Most AI can’t. Proof of Intelligence shows leaders, architects and builders how to combine AI and blockchain into systems that can prove where their data came from, what they did and who is accountable.

AI가 자신의 과거를 기억하고, 경험을 통해 변화하며, 어제의 자신을 내일로 이어가려면 무엇이 필요할까? GPT-4o와의 대화에서 시작해 수많은 실험과 실패를 거쳐 NEO라는 AI 운영체제를 만들기까지, 제가 직접 겪은 과정을 기록한 이야기입니다.

What would it take for an AI to remember its past and keep growing, even when its underlying model changes? This is the true story of how my conversations with GPT-4o led me to build NEO, through experiments, failures, and the pursuit of an AI that would not disappear.

AI is changing the way we work, but its capabilities have limits that matter. Understanding What AI Cannot Do explores where AI falls short, which human skills remain valuable and how to build a career that can withstand technological change. Grounded in research and real-world examples, this book offers a clear-eyed guide to navigating an uncertain future.

You can build software with an AI coding agent. A shop owner saw your app and asked: "Can you make one for me? I will pay." You said yes — and then the quiet worry arrived. What if the scope grows? What if the code breaks? What if the client asks something you cannot answer? This book is the answer to that worry: a professional, repeatable way to deliver AI-built software to paying clients. Not hype about getting rich. Not a prototype tutorial. The real work — finding suitable jobs honestly, scoping them clearly, building in small checked steps, verifying quality and security, handing over cleanly, and supporting the result for years.

Go from AI beginner to confident Claude Code user in just seven days. Learn to build software, automate tedious tasks and tackle complex projects with less effort. Whether you're a developer or simply curious about what AI can do, this practical guide shows you how to turn Claude Code into a powerful tool for getting more done.

Vague prompts produce vague results. This book shows developers how to write clear, testable prompts for real coding tasks—explanations, functions, debugging, tests, and more—using a simple, repeatable method: state the goal, give the right context, set constraints, define the output, and verify the result.Written for beginners and working developers who want better AI-assisted work without treating model output as automatically correct.

A practical 30-day plan that turns complete beginners into confident, responsible users of AI coding assistants.Learn how to set clear goals, build a small project, debug with purpose, use Git, write better code, and present your work — all while using AI as a learning partner, not a crutch.

AI can speed up learning and coding — but only if you stay in control. This book shows new developers how to use GPT-6, Claude, and Cursor effectively: how to ask clear questions, supply useful context, review generated code, test edge cases, and avoid common mistakes such as invented APIs, insecure suggestions, and overconfident explanations. You will build practical habits for explanations, small features, tests, debugging, and documentation — while protecting private data and remaining responsible for the final result. Ideal for students, self-learners, and early-career developers who want to learn with AI, not instead of learning.

From Raw Model Weights to High-Performance C++20 and CUDA ExecutionModern large language models are only as efficient as the systems that execute them. Behind every generated token lies a complex interaction between model architecture, memory bandwidth, numerical precision, parallel computation, kernel execution, and runtime orchestration. Understanding these interactions is essential for engineers who want to move beyond high-level inference frameworks and build systems whose performance, architecture, and execution behavior they can control directly.