1
AI, machine learning, and language models
- AI
- Machine learning
- Language models
- Machine learning
Distinguish a broad field from one kind of model.
Sign up to keep track of your learning progress.
Log inBuild Your Own AI in 9 Steps
From an elementary-school level all the way to Python code
-
Understand it Beginner
-
Look inside Intermediate
-
Build it yourself Advanced
All 9 steps at a glance
- Beginner Use AI and check its answers
- Intermediate Look inside a language model
- Advanced Build and evaluate with Python
- Level 1 AI, machine learning, and language models
- Level 2 Write and check a prompt
- Level 3 Text, tokens, and IDs
- Level 4 Vectors and embeddings
- Level 5 Training, inference, and retrieval
- Level 6 Instructions, sampling, and verification
- Level 7 Python: run, inspect, change
- Level 8 Numbers, predictions, and activations
- Level 9 Train and evaluate a small model
AI is a fill-in-the-blanks champion!
Here, we mean language models: the kind of AI 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 training, your input, and the text so far to calculate what could come next. It chooses a small piece of text called a token, 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 model 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 probabilities.
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.
Beginner
Use AI and check its answers
No coding needed-
-
2
Write and check a prompt
- Task
- Context
- Constraints
- How to check
State the task, useful context, constraints, and a way to check the result.
-
3
Text, tokens, and IDs
- Text
- Tokens
- Token IDs
Separate text pieces from their numeric identifiers.