AI, machine learning, and language models
Distinguish a broad field from one kind of .
Free trial · No payment
Just tap where the red arrow points. Three taps and you are done.
This teacher has no free trial time you can book right now. Pick another free trial teacher.
Your free trial is booked!
Check your camera and mic before class.
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.
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.
Any that does work we usually think needs intelligence — recognising pictures, recommending videos, playing games or translating.
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.
that uses with many layers. It powers , and translation.
trained on a lot of text to predict the next . Today’s large language models () are built with deep learning, and chat assistants are built on them.
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.
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 .
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.
Distinguish a broad field from one kind of .
Say what you want done, give the background it needs, set limits such as length or format, and decide how you will check the answer.
See how text is cut into and each token becomes a number () — the model calculates with these numbers, not with letters.
Voice chat with Lyen is for members. Sign up first, then start talking. Sign up