Map the AI · Daily learning
One small lesson. One step forward.
Learn how AI handles text and generates answers through a short experiment and a question. Open the linked tutorial to explore further.
Your learning preferences
Preferences support future recommendations. This foundation practice currently keeps a fixed sequence.
A learning track for your goal
AI Literacy
Understand what AI is, how it works, and where it fails — without writing a line of code.
The full track uses the existing knowledge graph. Short-lesson mastery currently covers the foundation units below.
Foundation lesson progress
Loading progress…A correct answer is a start. Regular reviews help you remember. Take a break whenever you like.
Compare meaning with vectors
Distinguish a learned vector from a token ID and a truth score.
An embedding represents a token or text as a list of numbers learned for a task. Comparing vectors can help find related text. Cosine similarity compares directions; a high score is not proof that a claim is true.
These are handcrafted two-dimensional vectors, not real model output. Choose a phrase to compare it with the others.
The closest example by cosine similarity is: A kitten rests
- A kitten rests · 0.96
- Building software · 0.63
- Writing code · 0.42
Scores compare vector directions, not factual accuracy. Real results depend on the model, task and comparison method.
Loading progress…