The Complete AI Workshop

← All free chapters

PART 0 · YOUR FIRST STEPS

AI in 2 minutes, no jargon

What you'll be able to do
Explain in your own words what an AI is, what it can do, and above all what it can't.
A person hands a note to a large machine; on the other side, several sheets fan out, one of them crooked.
You ask a question, and several plausible answers come out. You're given only one, and it isn't guaranteed to be right.

In 2 minutes

An artificial intelligence is a program that can carry out tasks we used to think only humans could do: writing, summarising, answering questions, translating, creating an image.

The most accurate image is the very fast, very well-read intern. They have read an enormous amount, they work in seconds, they never get tired. But they need clear instructions, they don't know your situation unless you tell them, and they can get things wrong with unsettling confidence.

The key point, the one that changes everything: AI does not look things up in a database of truth. It works out what is most likely, word after word, from everything it has read. Most of the time, the most likely turns out to be true. Sometimes it doesn't.

1 · What you write
"Why is the sky blue?"
2 · What it does
It works out the most likely string of words. It doesn't go and check anything anywhere.
3 · What you get
A plausible answer. Often right. Not guaranteed.

Let's do it together

Nothing to install for this chapter. Three ideas to lock in, and they'll serve you for the whole rest of the handbook.

  1. Read this sentence twice: AI predicts a plausible answer; it does not look things up in a database of truth.
  2. Remember the consequence. When it doesn't know, it doesn't stop: it makes up something believable. This is called a hallucination. It isn't a rare bug; it's the normal way it works, pushed to its limits.
  3. Remember the reflex. For anything that really matters (a number, a date, a reference, a legal point, medical information), you check elsewhere. For everything else, you can move fast.
Warning
An AI that is making things up gives no warning. It changes neither its tone nor its style, and the false is written just as well as the true. That is exactly why checking matters: you can't spot a mistake by the way it's worded.
Your turn

Pick a subject you know really well: your job, a hobby, your town, a sport. Write it down. We'll use it in the next chapter: it's the best training ground for spotting when the AI is right and when it's making things up, because you're able to correct it.

Pitfalls to avoid
  • Believing everything the AI says because it's well written. The quality of the wording tells you nothing about the accuracy of the content.
  • Thinking it understands the way a human does. It calculates probabilities; it doesn't understand. That takes nothing away from how useful it is, but it does explain its mistakes.
Key takeaways
  • AI handles everyday human tasks: writing, summarising, answering, creating.
  • It offers what is likely, not what is true. When it doesn't know, it invents without warning.
  • Keep your critical eye: anything that matters gets checked elsewhere.
← Welcome, and how to use this handbookOpen your first account →

The rest of the handbook covers Claude, Higgsfield, Claude Design and Claude Code, with 11 recipes and a 30-day programme.

See the full handbook Open in the reader