AIFA / TRACK 1 · AI BASICS / LESSON 1

Let's talk about what AI actually is.

22 MIN total
4 chapters · 4 videos · 3 exercises
You'll unlock Tokens lesson next
01 CHAPTER 1 · WELCOME · 2 MIN VIDEO

The course starts here.

In the next 22 minutes, I'm going to give you the vocabulary that makes everything else in AI make sense. By the end you'll know what an LLM actually is, why your prompts get charged by the token, what hallucinations are, and how to write a prompt that doesn't waste your time.

02 CHAPTER 2 · THE AI FAMILY TREE · 3 MIN VIDEO

AI, ML, GenAI, LLMs — the cast list.

You'll hear all four words used like they mean the same thing. They don't.

  • AI — any system that simulates human intelligence. Includes spam filters and your Roomba.
  • ML (Machine Learning) — subset of AI that learns from data. Inventory forecasts, dog-breed classifiers, self-driving cars.
  • GenAI — AI that creates new content: text, images, code. ChatGPT, Claude, Midjourney.
  • LLM (Large Language Model) — the engine under GenAI for text. GPT-5, Claude Sonnet, Gemini 2.5.
CH 02 · VOCABULARY
The four words · 2:48
★ Allie's note

Don't memorise these. You'll absorb them by using them. The vocabulary is just a coat hook — you're hanging concepts on it as we go.

03 EXERCISE · VOCABULARY CHECK · 2 MIN

Match the term to its definition.

Quick check. Click a term on the left, then the matching definition on the right. Correct = locks in. Wrong = shake & try again. All 6 = chapter complete.

MATCHED · 0 / 6
✓ Vocabulary locked in. You speak AI now.
04 CHAPTER 4 · INSIDE THE TRANSFORMER · 3 MIN VIDEO

The T in ChatGPT.

The transformer is the architecture under every modern LLM. It was invented in a 2017 paper called "Attention Is All You Need." The breakthrough: a mechanism called self-attention.

Before transformers, AI systems treated recent words as more important than earlier ones. Self-attention lets the model weigh every word against every other word in the input, no matter the distance.

CH 04 · TRANSFORMER
Attention is all you need · 3:15
And actually, the T in ChatGPT literally stands for transformer.
— Allie K. Miller · Track 1, Lesson 1
05 EXERCISE · LIVE TOKENISER · 3 MIN

Type something. Watch it become tokens.

Every AI charges by the token, not the word. Roughly ¾ of a word in English. Watch what's actually happening when you type.

DEMO · INLINE
Live tokeniser
Type or paste anything. Tokens stream in, cost ticks up at GPT-5 pricing.
TOKENS
0
WORDS
0
EST. COST (GPT-5)
$0.00
06 CHAPTER 6 · HALLUCINATIONS & RAG · 2 MIN VIDEO

When AI confidently makes things up.

Hallucinations are when an AI states something false with the same confidence as something true. Even the top models hallucinate at under 1% — but that 1% can include fake citations, made-up statistics, and "facts" that sound entirely real.

The fix: RAG (Retrieval-Augmented Generation). Instead of relying on the model's memorised knowledge, you give it your own documents to pull from. Now it has to cite what's actually there.

CH 06 · HALLUCINATIONS
When AI lies (and how RAG fixes it) · 2:45
★ Allie's note

Always verify citations. The link can be real, but the stat or quote inside might not be on that page at all. Verify, verify, verify.

07 EXERCISE · YOUR FIRST STRUCTURED PROMPT · 4 MIN

Try this exact prompt in any AI you have open.

This is the cleanest version of every concept you've learned so far. Copy it, paste it into the AI of your choice, see what comes back. Then we'll iterate together in Lesson 2.

$
EXERCISE · Explain a concept like I'm 12
~4 min

Drop this exact prompt into your AI of choice. Test how clear context matters. Bonus: ask a follow-up that pushes the AI to dig deeper.

Explain how a Transformer (the AI architecture, not the toy or the truck) works, as if you were teaching a curious 12-year-old. Use no more than 200 words. Include one analogy from sports, music, or cooking — your choice. Don't use the word "neural" until your final sentence. End with one question that would help a 12-year-old understand even more.
✓ YOU'RE DONE WHEN
  • You ran the prompt in at least one tool · ideally two for comparison
  • You can spot how the analogy lands differently between tools
  • You asked one follow-up that pushed the answer further
08 WRAP · STEAL THESE · 1 MIN

Three things to take with you.

Pick one. Run it. Save the output to your prompts library.

◆ STEAL THIS · ACTION ITEMS

Pick one by Friday.

  1. 01 Run the prompt above in two different AIs. Compare. Save the better answer to your ~/prompts folder.
  2. 02 Tokenise something you wrote last week — an email, a LinkedIn post. Now you know what each one cost when you ran it through AI.
  3. 03 Spot one hallucination this week. Any AI, any context. Note where it sounded confident and where you'd have been fooled if you hadn't verified.
★ ACCOUNTABILITY · END-OF-LESSON CHECK-IN
How do you plan to apply this?
▸ Next time you sign in, we'll ask: "Did you?" — it's how the Paper Trail builds.
NotebookLM ◇ NOT CONNECTED

Save this lesson — the AI/ML/LLM definitions, the S-T-O-L-E-S checklist, and the 4 Cs of safe AI use — into your research notebook.

New to NotebookLM? Don't worry — Allie covers it properly in Track 2 · Lesson 4 (Tools). You can hook it up now and come back to fill in the why later.
Save to: AIFA Notes
✓ Saved to AIFA Notes. NotebookLM opened in a new tab.
→ Next: Lesson 2 · How AI's "memory" actually works · 7 min