Artificial Intelligence

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.

For PMs, presales, and managers who work with AI but don’t write code: how RAG, agents, fine-tuning, compliance, and security actually fit together.

Master Muse AI in 7 Days — the complete beginner-to-expert guide to Meta's personal AI agent. Learn every feature, prompt like a pro, and put Muse to work on your business, studies, and daily life.

Life and AI are made of different stuff, yet they face many of the same problems. This book sets their solutions side by side, from the first cells to today's language models, to understand both.

Your app is mostly other people's code. You chose a few packages, and those packages pulled in dozens more. Your AI coding agent installs whatever makes the demo work. Your secrets sit in files you will one day share. Your server has not been updated in months. None of this means you failed. It means you build alone, with no security team and no reviewer. This book gives you a realistic, low-cost routine to reduce supply chain risk in a small project, including the risks your AI coding agent introduces. In one weekend plus thirty minutes a month, you will learn to: - map what you actually ship, from direct packages to hidden transitive ones;- vet a new package in five minutes before you install it;- update safely, one small reversible step at a time;- read scanner reports without panic and without ignoring them;- keep secrets out of your code and rotate them when they leak;- protect your code host, registry, and cloud accounts;- run a minimal build pipeline and a boring, updated small server;- keep your AI coding agent leashed with permissions and rules files;- recover calmly from a compromised package, a leaked key, or a hijacked account. You will not become a security expert. You will become a solo builder with a written inventory, safer accounts, tested backups, and a monthly routine you can sustain for years. Most existing books on this topic target large companies, Kubernetes, and enterprise CI/CD. This one is for one person with limited time. It says what to do first, what to skip, and what is overkill. No setup is risk-free, and this book promises none. It promises fewer easy failures and faster recovery.

AI can analyze a thousand charts in seconds. So why can't it reliably make you rich? Discover the uncomfortable truth about AI trading, the mistakes most people overlook, and what these powerful tools can actually do for you.

Build three useful automations without code or a team. This practical guide gives solo operators a 90-minute build rhythm, a five-run safety check, and clear failure-detection steps for intake, delivery, and follow-up.

Learn Claude through practical exercises in chat, files, Projects, research and Artifacts, with an optional introduction to Claude Code.

HNSW powers almost every vector database, and few of the engineers who rely on it have seen inside it. Vector Search Inside Out builds it from first principles in 92 step-by-step figures, then tunes it on 1.18 million real vectors. You'll know exactly what M, efConstruction and ef do, and how to set them for your own data.

The code looks right. The agent sounds sure. Then it breaks. Learn the 50 most common ways AI-built apps fail, how to spot each one early, and how to fix it before your users find out.

Move from observing AI agents to operating them through runtime evidence, evaluation, economics, reliability, and governed action.This practitioner-focused book develops an architecture for production AI systems where traces, evaluations, safety signals, cost, business outcomes, and operational authority become part of one evidence model.

A short, hands-on guide to reverse engineering with AI agents and REA 6.4.0: drive Ghidra from Claude Code, Codex or Cursor, check every claim against evidence, and work through native, Electron, Android, .NET and web targets you are allowed to analyse. Every output shown is a real lab run.

Build, debug and maintain websites with Claude Code through 7 practical workflows. Includes a downloadable practice project, reference code and 30 automated tests to help you verify what the AI produces.

Curious about agentic AI but not sure where to start? This beginner-friendly guide takes you from the basics to building your own AI agents, even if you have no coding experience. Learn how agents work, choose the right tools and turn your ideas into practical, reliable solutions for real-world problems.

Kill an AI agent mid-refund and the retry bills every model call again and refunds twice. This book crashes one agent on purpose and recovers it on DBOS, Temporal, Restate and Prefect, with the real output of every run.