OkayStudy
EN English 한국어 日本語 中文 हिन्दी বাংলা اردو Español Português Français Deutsch Русский العربية Bahasa Indonesia Tiếng Việt ไทย Türkçe

How to enable notifications

Notifications are unavailable in this browser or on this address. Try a supported browser on the secure SONUB site.

If notifications are blocked, allow them in your browser settings.

  1. Open the site controls beside the address bar, or your browser’s site settings. Set Notifications for this site to Allow.
  2. In your device settings, allow notifications for your browser and check Do Not Disturb or Focus.
  3. Return to SONUB, reload the page, and use the bell to enable notifications.

On iPhone or iPad, add SONUB to your Home Screen, open it there, then allow notifications.
Intro to Building AI

Build Your Own AI in 9 Steps

Learn AI in nine steps, from a kid-friendly start to building and evaluating a small Python model. New here? Begin with steps 1–3 and the fill-in-the-blank game.

Four nested circles: the outer circle has a robot icon, the next a chart with dots, the next a layered network of nodes, and the innermost two speech bubbles.
  1. Understand it Beginner
  2. Look inside Intermediate
  3. Build it yourself Advanced
The big picture

Where do chatbots fit inside AI?

is a very big word. Inside it are smaller, more specific fields, like circles inside circles. The people use every day are , right in the centre.

Four nested circles: the outer circle has a robot icon, the next a chart with dots, the next a layered network of nodes, and the innermost two speech bubbles.
Each circle sits inside a bigger one: every language model is a kind of , but not every AI is a language model.

  1. Artificial intelligence

    Any that does work we usually think needs intelligence — recognising pictures, recommending videos, playing games or translating.

  2. Machine learning

    AI that learns patterns from instead of following rules a person wrote one by one. A spam filter that learns from many example emails is a good example.

  3. Deep learning

    that uses with many layers. It powers , and translation.

  4. Language models

    Deep learning trained on a lot of text to predict the next . Chat assistants are built on large language models ().

See how a language model chooses its words

All 9 steps at a glance

Bar height = step order (not a measured score)
  • Beginner Use and check its answers
  • Intermediate Look inside a
  • Advanced Build and evaluate with
  1. Level 1 AI, machine learning, and language models
  2. Level 2 Write and check a prompt
  3. Level 3 Text, tokens, and IDs
  4. Level 4 Vectors and embeddings
  5. Level 5 Training, inference, and retrieval
  6. Level 6 Instructions, sampling, and verification
  7. Level 7 Python: run, inspect, change
  8. Level 8 Numbers, predictions, and activations
  9. Level 9 Train and evaluate a small model
A little example to get started

AI is a fill-in-the-blanks champion!

Here, we mean : the kind of you chat with in writing. Let's explore how they produce a reply using an everyday sentence.

What would you put in the blank? Tap an example.

This morning, I __________. This morning, I ate breakfast. This morning, I went for a walk. This morning, I read a book.

These choices are prepared examples. Tap your selected example again to bring back the blank.

Does AI really make replies this way?

Yes, predicting what comes next is the basic idea! A language model uses patterns learned during , your input, and the text so far to calculate what could come next. It chooses a small piece of text called a , which can be a word or part of one, then repeats the process to build a reply.

Filling a blank is an analogy. In a chat reply, the usually keeps adding tokens at the end. It doesn't always choose the most likely one: it can also sample from several candidates according to their .

Then what does “thinking” or “reasoning” mean?

People use these words when AI works through a problem in steps. Underneath, it runs calculations using learned patterns and its input. Fluent language alone is no reason to treat it as a person with feelings or intentions.

A plausible continuation can still be wrong. Check important answers.

Explore how AI uses probability
Beginner

Use AI and check its answers

No coding needed
  1. 1

    AI, machine learning, and language models

    Distinguish a broad field from one kind of .

    Probability Learn
  2. 2

    Write and check a prompt

    1. Task
    3. Constraints
    4. How to check

    State the task, useful , constraints, and a way to check the result.

    AI Teacher Learn
  3. 3

    Text, tokens, and IDs

    1. Text

    Tell text pieces () apart from the numbers () given to them.

    AI Lab Learn
Advanced AI Development

Finished the beginner steps? Go advanced

  1. Intermediate Look inside a language model
  2. Advanced Build and evaluate with Python
Open the advanced course
Keep going

Choose a pending booking to cancel. Each cancellation requires confirmation.

Your :

Close