Topics
254 programming, AI and security concepts, each with a one-line definition, what to learn first and where to practise it.
Showing 25–35 of 35 in AI & Machine Learning · Clear filters
How LLMs are trained
The pipeline from data and tokenization through pre-training to fine-tuning and preference tuning.
1 articleImbalanced data
Datasets where one class is rare, and the techniques and metrics that handle them.
3 practice questionsKnowledge graphs
Data stored as entities and the typed relationships between them.
1 articleReward hacking
An AI system satisfying the letter of its reward while missing what was intended.
1 articleClassification
Predicting a category, such as spam or not spam.
2 practice questionsData drift
Production data changing over time until a model's accuracy falls.
2 practice questionsOverfitting
A model learning noise in the training data, so it does well in training and badly on new data.
2 practice questionsRegression
Predicting a number, such as a price or a temperature.
2 practice questionsSampling and temperature
How a model picks the next token, and how temperature and top-p change the output.
2 practice questionsReasoning models
Models that spend extra tokens thinking step by step before answering.
1 practice questionRecommender systems
Suggesting items a user is likely to want from past behaviour and similarity.
1 practice question