Books

Pull a model onto a machine you own, shape it with a Modelfile, fine-tune your own adapter, and build a chat app that calls tools and talks to an MCP server, all running on your own hardware. By the end, you'll know exactly where owning your AI beats renting it, and where it doesn't.

A hands-on guide to downloading, running, serving, and maintaining open-weight LLMs on your own machine (489 manuscript pages).

Artificial Intelligence is no longer a distant possibility—it is becoming a collaborative partner in education, research, software development, and professional decision-making.But how do frontier AI systems actually work?What makes safety-centered AI different from earlier generations of language models?How can students, researchers, educators, and professionals prepare for a future shaped by increasingly capable AI systems?In Claude 4 (Anthropic): Safety-First Frontier AI in 2026, author Anshuman Mishra presents a comprehensive and academically grounded exploration of one of the most influential frontier AI systems of the modern era.From Constitutional AI and advanced reasoning architectures to multimodal intelligence, agentic workflows, educational transformation, governance frameworks, workforce implications, and future AI research directions, this book provides readers with a balanced understanding of both opportunities and challenges.Rather than focusing on hype or speculation, the book emphasizes evidence-based analysis, responsible innovation, ethical deployment, and human-centered AI development.Whether you are a student seeking AI literacy, a researcher exploring frontier models, a professional adapting to technological change, or a policymaker shaping future governance frameworks, this book offers the knowledge needed to engage thoughtfully with the next generation of intelligent systems.The future of AI will not be determined by technology alone.It will be shaped by how responsibly humanity chooses to use it.

Serious AI research no longer needs a data center. This is the field log of training, fine-tuning, serving, and shipping real models on a single petascale desktop, with the code to reproduce every result. For engineers building AI on NVIDIA hardware who want depth, not hype.

Learn Claude Code by building real projects. This hands-on companion turns the Claude Code Masterclass workshop into a practical self-paced guide for planning, coding, testing, reviewing, refactoring, and shipping software with AI.

MCP is the protocol powering the next generation of AI agents, and this is the only book that teaches you all of it. From Python fundamentals to low-level SSE transport, go from zero to production-ready MCP developer.

CPython 3.15 runs without the GIL, ships an experimental JIT, and rewrites the C API for a free-threaded world. No hand-waving. No stale docs. Just the interpreter, laid open.

An introduction to actor-critic algorithms as dynamical systems: featuring hand-computable examples, fast-slow reductions, and machine-checked Lean 4 proofs