Topics
254 programming, AI and security concepts, each with a one-line definition, what to learn first and where to practise it.
Showing 1–18 of 18 in AI & Machine Learning · Clear filters
Retrieval-augmented generation (RAG)
Fetching relevant passages from your documents and giving them to the model with the question.
6 articles · 15 practice questionsFine-tuning
Training an existing model further on your own examples to change its behaviour.
2 articles · 7 practice questionsVector search and retrieval
Finding the stored embeddings closest to a query, usually with an approximate index.
2 articles · 7 practice questionsTool calling
Letting a model request a function call (search, code, an API) and use the result.
3 articles · 2 practice questionsFeature engineering
Turning raw data into inputs a model can learn from: scaling, encoding and new features.
8 practice questionsPrompt engineering
Writing instructions and examples that get reliable output from a model.
8 practice questionsReverse engineering
Working out how a product or program works by taking it apart and observing it.
2 articlesEnsemble methods
Combining several models, such as random forests and gradient boosting.
5 practice questionsLLM evaluation
Testing language-model output with test sets, rubrics and model-graded checks.
5 practice questionsRegularization
Penalising model complexity (L1, L2, dropout) to reduce overfitting.
4 practice questionsCache-augmented generation (CAG)
Loading a fixed knowledge set into the model's context and cache instead of retrieving per question.
1 articleKnowledge-augmented generation (KAG)
Answering from a knowledge graph of entities and relations, for multi-step reasoning.
1 articleChunking
Splitting documents into passages sized for embedding and retrieval.
2 practice questionsClustering
Grouping similar data points without labels, for example with k-means.
2 practice questionsContext engineering
Choosing what goes into a model's context window and in what order.
1 practice questionDimensionality reduction
Compressing many features into fewer while keeping the important structure (for example PCA).
1 practice questionQuantization
Storing model weights in fewer bits so a model runs faster and in less memory.
1 practice questionStructured output
Getting a model to return JSON or another fixed format reliably.
1 practice question