Get more from Gemini 4 Argon with practical prompting techniques that work on real-world tasks. This guide covers coding, research, legal and financial work, long-horizon workflows, optimization and prompt evaluation, with clear examples and strategies for getting reliable results from one of the most capable AI models available.
Your own AI assistant at home: private, local, and safe. Ten step-by-step chapters, each one tested on a fresh machine before publishing.
Build an AI app people pay for, no coding required. The SHIP Method shows non technical readers how to find a money problem, prove demand, build with AI, get users and charge.
6-page kit: 5-beat structure, storyboard template, 7-part prompt formula, credit savers and delivery checklist for 15-second AI product ads.
이 책은 이런 분께 맞습니다: 쇼핑몰·소상공인 제품 광고를 AI로 직접 만들고 싶은 분, 크몽 같은 프리랜서 마켓에서 숏폼 광고 제작 의뢰를 받기 시작한 분, 생성 결과가 들쭉날쭉해서 기준이 필요한 분. 모든 장에 바로 복사해 쓸 수 있는 양식과 체크리스트가 들어 있습니다. 앞 12쪽은 무료 샘플로 먼저 읽어 보실 수 있습니다. 이 책은 AI 도구의 도움을 받아 작성·편집했습니다. 영어판(15-Second AI Product Ads)도 Leanpub에 있습니다.
Inference engineering is now its own discipline, with unique challenges around speed, cost, reliability and scale. This practical guide takes you from core concepts to production systems, showing how modern inference architectures work, how to optimize them and how to make better engineering decisions through measurement and trade-off analysis.
The ultimate bridge from high school AP Physics to modern AI. Start with the familiar physics you know, translate it into Python, and use it as a launchpad to build advanced Machine Learning models and neural networks. Includes 100% solved exercises and click-to-run Google Colab labs.
Build one real AI system end to end, from raw job postings to a deployed, tested API, and learn production AI engineering on the way. 24 chapters, runnable code, and numbers you can reproduce.
What happens when artificial intelligence surpasses human intelligence across nearly every field? Super Intelligence explores how such systems could emerge, what they might be capable of and how they could reshape science, society and civilization. Grounded in research and technical evidence, this book cuts through the hype to examine what super intelligence could really mean.
机器人真正学会做饭,不是因为工程师写完了每一步,而是因为它能从身体经验、失败与恢复中形成自己的手艺。
为什么参数不大的模型,把信息放对地方就能反超更大的模型?本书以"压缩"为主线,把大模型的表示、泛化、推理、RAG 与智能体统一成一道信息管理题:什么该压、什么不能丢、什么该外置、放在哪里、何时取回。18 章、190 张原创图解,从熵一路讲到世界模型。
Your AI agent can sound right and still act wrong. Learn how to secure the path from a model’s suggestion to a real-world action—with practical guidance on data, permissions, tools, adversarial testing, and recovery.
A Comprehensive Engineering Guide to Autonomous Agent Architectures, Multi-Agent Systems, Memory, Tool Execution, Reliability, Observability, and Production DeploymentAutonomous AI agents represent a fundamental shift from conventional conversational applications toward software systems capable of executing multi-step tasks, interacting with external tools, maintaining persistent state, coordinating specialized components, and adapting their behavior to changing conditions. Building such systems requires considerably more than connecting a language model to a prompt. It demands a disciplined approach to execution control, memory architecture, workflow orchestration, security, evaluation, and production infrastructure.Mastering AI Agents: Hands-On Production Code is a practical, implementation-focused engineering reference to designing, building, and deploying autonomous AI agent systems. Across 38 chapters, it progresses from low-level LLM runtime primitives and a zero-dependency Python agent loop to cognitive architectures, persistent memory, stateful workflows, multi-agent coordination, secure tool execution, production observability, and enterprise deployment.
Build a real LLM inference engine from the ground up in portable C. Learn how transformers work, load SafeTensors weights, implement KV caching and optimize inference on the CPU. By the end, you will run TinyLlama locally and generate text with a complete working runtime.