1. Introduction to generative AI #

When it comes to AI, we’re still in the early days. The majority of people haven’t yet adopted these tools for their work, hobbies, or day-to-day lives.

Some have experimented with early versions and found them lacking, abandoning ship before the current wave of tools, with their significantly improved capabilities, came into wider use. Even those who have found some applications often don’t venture beyond their starting point, opting to use these models for basic outputs.

Just recently, I assisted a friend who runs a one-person business with employing AI as a virtual marketing consultant. We used the tool to generate content and strategic ideas for the company. Yet, like all things, the assistant had its limitations. It needed many guiding questions and iterative refinements to produce truly valuable output. If you just skim the surface, it will do so, too. But the outcomes were still notably better than what you’d expect from someone with no marketing experience.

Another friend of mine, who isn't into programming, asked me if I could suggest any articles or books that could help them understand a technical concept better.

I suggested a book—and also recommended using ChatGPT as a tutor, which I’ve been doing more often myself. The app is essentially a talking encyclopedia. (A Borgesian nightmare.) It easily breaks down barriers previously caused by a lack of skill, talent, or knowledge.

Not sure how to do something? Pair up with ChatGPT, Claude, or Gemini. Tell it about your current skill level and ask for guidance. It will adapt to your needs, allow you to ask follow-up questions, and even provide practical examples when possible.

I don’t often use it this way for tasks within my expertise, but it’s great for everything else. Just this week, I teamed up with it to brush up on some basic legal concepts related to my business. I later verified the information with a lawyer friend, but thanks to that previous chat, I already had a good understanding of the topic, which saved my friend some time getting me up to speed.

And while I believe the term “prompt engineering,” which we’ll talk about in the later chapters, is overhyped, I do think a particular mindset is necessary when working with neural models: you’ve got to guide and steer them. It’s an iterative refinement process, and anything less will yield rather superficial results—at least as things stand now. Paradoxically, it’s more art than science.

So, if you’re anxiously searching for an avenue to break into the AI field, concerned you’re already behind due to the progress of others, here’s a tip: learn to prompt well and then help somebody who can’t. It's a simple concept, true, but again—we’re still early. Most people don’t use any large language models daily yet. And these apps and models are… broad, to put it mildly. The interface is essentially just a text box, leaving it up to you to figure out how to make it useful for your needs or to learn from how others are using it.

As you can probably guess—this book is my way of helping.