concept~120 mindifficulty

What LLMs Are (Intuition)

You cannot use a tool well without a mental model of how it actually works.

1

Learn it

Watch Karpathy's plain-language 1-hour talk to get the big picture of what an LLM is, how it is trained, and where the field is heading. Then use 3Blue1Brown's visual chapter to see, concretely, how a GPT turns tokens into predictions. Focus on intuition, not the math.

By the end you’ll be able to

  • Explain next-token prediction and why scale produces emergent capability
  • Reason about what LLMs are good and bad at (hallucination, context limits)

Free resources

2

Practice

Write a one-page plain-English explainer answering: what is a token, what does 'next-token prediction' mean, and why do LLMs hallucinate?

3

Build it — your output

A short written 'LLM mental model' note you can refer back to throughout the track.

4

Prove it — check yourself

You’re ready to move on when you can honestly say yes to each:

  • Can you explain next-token prediction to a non-technical friend?
  • Can you name three tasks LLMs do well and two failure modes?
  • Can you describe what a context window is and why it matters?

Do it with AI

Use a free AI tool as your tutor and pair-programmer. Copy a prompt below into Claude, ChatGPT, or Gemini (for building, try Cursor or Copilot).

The habit: Try it yourself first — a little struggle is where the learning actually happens. Then ask for a hint before the answer — never copy blindly.

  • Understand itClaude / ChatGPT / Gemini

    I'm a beginner learning "What LLMs Are (Intuition)". Explain it in simple terms with a real-world analogy, then ask me ONE question to check my understanding — don't reveal the answer.

  • PracticeClaude / ChatGPT / Gemini

    Give me 3 short practice problems on "What LLMs Are (Intuition)" (my goal: explain next-token prediction and why scale produces emergent capability), from easy to hard. Don't include the solutions yet — I'll try them first, then ask you to check.

  • Get unstuckClaude / ChatGPT / Gemini

    I'm stuck on this exercise about "What LLMs Are (Intuition)": [paste your attempt here]. Give me ONE small hint to move forward — do NOT give me the full solution.

  • Build & reviewCursor / Copilot

    Here is my work for a "What LLMs Are (Intuition)" task: [paste your code or answer]. Review it: point out what's wrong and WHY, and suggest improvements — but let me make the fixes myself.

  • Prove itClaude / ChatGPT / Gemini

    Quiz me on "What LLMs Are (Intuition)". Ask me 5 questions one at a time, wait for my answer each time, then tell me if I'm right and briefly why.

My notes