Get up to speed quickly with generative AI!

AI tools like ChatGPT and Gemini, automated coding tools like Cursor and Copilot, and countless LLM-powered agents have become a part of daily life. They’ve also spawned a storm of misinformation, hype, and doomsaying that makes it tough to understand exactly what Generative AI actually is and what it can really do. Introduction to Generative AI, Second Edition delivers a clearly-written survey of generative AI fundamentals along with the techniques and strategies you need to use AI safely and effectively.

In this easy-to-read introduction, you’ll learn:

• How large language models (LLMs) work

• How to apply AI across personal and professional work

• The social, legal, and policy landscape around generative AI

• Emerging trends like reasoning models and vibe coding

Introduction to Generative AI, Second Edition guides you from your first eye-opening interaction with tools like ChatGPT to how AI tools can transform your personal and professional life safely and responsibly. This second edition has been completely revised to reflect the latest developments in the field—from the latest innovations in prompt engineering and AI agents to fresh coverage of multimodal training, reasoning models, no-code tools, retrieval-augmented generation (RAG), and more.

About the Book

Introduction to Generative AI, Second Edition is an up-to-date guide to the capabilities, risks, and limitations of tools like ChatGPT, Gemini, and Claude. This easy-to-follow guide moves quickly through the basics, giving you the skills and understanding to use AI with confidence. Along the way, you’ll explore how AI is impacting even established industries, with an expert-level look at global investment in AI, AI education policy, AI’s economic impact, and the ongoing legal and ethical issues of AI usage.

About the reader

For anyone interested in generative AI. No technical experience required.

Table of Contents

1 Large language models: The foundation of generative Al

2 Training large language models: Learning at scale

3 Data privacy and safety: Technical

4 Al and the creative economy: Innovation and intellectual property

5 Misuse and adversarial attacks: Challenges and responsible testing

6 Machine-augmented work: Productivity, education, and economy

7 Prompt engineering: Strategies for guiding and evaluating LLMs

8 Al agents: The rise of autonomous Al systems

9 Human connections: The social role of chatbots

10 The future of responsible Al: Risks, practices, and policy

11 Frontiers of Al: Open questions and global trends

About the Authors

Numa Dhamani is a natural language processing expert with domain expertise in information warfare, security, and privacy. She has developed machine learning systems for Fortune 500 companies and social media platforms, as well as for startups and nonprofits. Numa has advised companies and organizations, served as the Principal Investigator on the United States Department of Defense's research programs, and contributed to multiple international peer-reviewed journals.

Maggie Engler is an engineer and researcher currently working on safety for large language models. She focuses on applying data science and machine learning to abuses in the online ecosystem, and is a domain expert in cybersecurity and trust and safety. Maggie is also an adjunct instructor at the University of Texas at Austin School of Information.