Introduction to Generative AI

Generative AI (artificial intelligence) is a loaded phrase these days. Investors are throwing their money at it, execs are throwing it at each other, and at some point, a manager is probably going to ask you “can we do generative AI too?” or you’re going to get tempted and hack together an LLM-powered bot at 2 a.m. This chapter introduces you, a software engineer, to the booming world of AI, by cutting through all the hype and demystifying AI. I start from the most popular architectures right now and then throughout the book to various models, both open and closed source. I aim to explain these models from the lens of a software engineer as opposed to a data scientist or machine learning scientist. This means the aim is to understand and explain just enough about the foundation models so you can customize and build AI-powered applications, leveraging these models. In particular I’ll focus on diffusion models (you know all those cool AI images you’ve seen on your socials?) and transformer models (think ChatGPT, LLama, music-gen, etc.).