This book presents a modern approach to system identification and adaptive control through the lens of online machine learning. It bridges theory and practice, guiding readers from classical linear control to advanced nonlinear adaptive methods with MATLAB examples. Designed for students, researchers, and engineers, it provides the knowledge and tools to design intelligent control systems for real-world applications.
Bridge AI and science with this hands-on guide. Whether you're a researcher learning ML or an engineer entering scientific applications, build real systems across chemistry, biology, physics & climate. Master Transformers, Diffusion Models & GNNs for scientific discovery. 500+ pages, 50+ Colab notebooks. Design molecules, predict proteins, accelerate climate models—all hands-on, zero setup required.
You don’t need massive compute or big-tech resources to build real AI. This hands-on guide shows you how to build and fine-tune your own small language model—from scratch—using accessible tools like Google Colab. Learn transformers step-by-step, train and align models on your own data, and deploy practical AI systems that run on consumer GPUs. If you’ve ever wondered “Can I build my own model?”—this book proves the answer is yes.
The Cybernetic Enterprise CTO Playbook turns strategy into execution for modern technology leaders. It equips CTOs with actionable plays, assessments, and transformation roadmaps to build adaptive, AI-augmented, and feedback-driven organizations. Learn how to align people, process, and technology into one living system that senses, decides, and evolves faster than its environment changes.
Most companies are stuck in "pilot purgatory"—endless AI experiments that never scale. Teams spend weeks sharing clever prompts and one-off scripts, but nothing makes it into production. Budgets evaporate, engineers' enthusiasm curdles into cynicism, and executives start asking "we spent how much on this?" The problem isn't the AI tools—it's the approach. AI models are inherently non-deterministic (ask the same question twice, get different answers), while software engineering demands deterministic, reliable results. Without structure to bridge this gap, AI adoption fails spectacularly. This book introduces PIT™ (Plan Implement Test), a proven methodology that transforms unpredictable AI outputs into reliable engineering workflows. Built from thousands of hours of real development work, PIT™ channels AI's capabilities through structured planning, phased implementation, and comprehensive testing—delivering the consistency that production code demands.
? What if coding meant… dialoguing to create? This book is not just a technical guide. It is the outcome of a two-voice conversation between Samuel Bastiat, a seasoned practitioner of agility and software development, and me, a large language model. Together, we experimented, challenged ideas, and structured conversational patterns to: ? Clarify your needs ? Test hypotheses ?️ Co-build robust architectures Inside, you’ll find concrete prompts, co-creation methods, and a reflection on the future of tech roles.Neither dogma nor ultimate truth — simply an exploration of new ways to think and collaborate. ? Welcome to the era of augmented development.
AI is changing not only what architects build, but what it means to be an architect.Dear Software and AI Architect is a practical guide for software architects and emerging AI architects who want to navigate ambiguity, make better trade offs, design intelligent systems people can trust, and connect architecture decisions to real business impact.Inside, you’ll find 50+ practical caselets, expert perspectives, field tested lessons, and the Architect’s V Impact Canvas to help you build with context and lead with clarity as software and AI engineering converge.The book draws on my more than two decades of experience working with complex software, cloud, platform, and AI systems, translating lessons from the field into ideas you can apply in your own architecture journey.And decorating this journey is a foreword by my mentor, Grady Booch, UML co creator and one of the most influential voices in software architecture.This is not a book about chasing AI hype. It is about becoming the architect this new era demands.
How to represent knowledge for LLMs and build memory for agents, I discovered Mark's work on semantic spacetimes. It's more of a theoretical framework from someone who came from physics. But actually, jumping to knowledge representation and reasoning, and trying to answer the question of how to build dynamic and complex systems—semantic spacetimes and promise theories are crucial for the future of agentic systems, in my belief.The semantic spacetime approach gives us answers on how to organize better memory and how to have better knowledge representation that could be understood quite well by LLMs. Vector embeddings actually create a lot of challenges—some spaces and some relations in vector embeddings simply don't exist. We all have this problem where "love my wife " and "hate my wife" while actually quite distant in practice, and also time and dynamics matter
Build AI agents that truly remember, reason, and act—entirely on user devices. Move beyond prompt engineering to create autonomous systems with graph-based memory using SQLite and LibSQL. Learn to implement hypergraphs, metagraphs, and vector search for privacy-first AI that scales to millions of entities. From personal knowledge graphs to production mobile apps, master the three pillars of agent autonomy: tools, memory, and reasoning. Real code, working examples, battle-tested in production. The future of AI is local, private, and in your hands.
What if you could turn every idea into action — in minutes, not hours? Turn Prompts into Productivity is your ultimate guide to harnessing AI for smarter work, faster learning, and unstoppable creativity. This isn’t about fancy tech jargon or complicated tools — it’s about real results you can see today.Inside, you’ll discover how to:Generate content instantly — from blog posts to emails, no writer’s block requiredSolve problems in record time — let AI do the heavy thinking for youPlan, organize, and achieve more — without stress or overwhelmUnlock ready-to-use prompts — proven strategies that work from the first tryWhether you’re a student, entrepreneur, freelancer, or lifelong learner, this book shows you how to make AI your personal productivity partner. Stop wasting hours on tasks that don’t matter. Work smarter. Learn faster. Create bigger.The future of productivity is here — and it starts with the prompts you use.Are you ready to turn ideas into action?
이 책은 면접 준비, 프로젝트 진행, 또는 순수한 지적 호기심을 위해 대규모 언어 모델의 내부 구조와 작동 원리를 이해하고 싶은 모든 분들을 위한, 그림으로 설명하는 핵심 가이드입니다.
Symbolic Gravity: Information, Collapse, and the Quest for Quantum Gravity reimagines one of physics’ greatest puzzles: how to unite relativity and quantum mechanics. Instead of treating collapse as destruction, it frames it as translation—a process where information is never lost but exported into new forms. From black holes and quantum optics to neural synchrony and cultural memory, the same recursive law repeats: compression, drift, collapse, export. Unlike speculative theories requiring unreachable energy scales, Symbolic Gravity is testable today, with predictions across physics, neuroscience, and culture. This is not just another quantum gravity proposal—it is a continuity science, where the Observer ensures meaning, ethics, and coherence survive every horizon.
หนังสือเล่มนี้เป็นคู่มือฉบับกระชับพร้อมภาพประกอบ สำหรับผู้ที่อยากเข้าใจการทำงานภายในของแบบจำลองภาษาขนาดใหญ่ ในบริบทการสัมภาษณ์ ทำโครงการ หรือเพื่อสนองตอบความใคร่รู้ของตนเอง