AI & ML

From embeddings to agents — see how modern AI actually works.

1. 1What Is Machine LearningLearn the rule from examples instead of writing it.4m
2. 2Training vs InferenceLearn once, slowly. Answer many times, fast.4m
3. 3EmbeddingsMeaning turned into a fixed list of numbers.5m
4. 4Cosine SimilarityCompare direction, ignore magnitude.5m
5. 5TokenizationModels read chunks, not letters or words.5m
6. 6Attention, IntuitivelyEvery position decides which others to listen to.5m
7. 7Transformers: Big PictureA stack of identical blocks refining one sequence.5m
8. 8What Is an LLMA next-token predictor trained on a lot of text.5m
9. 9Temperature and SamplingOne distribution, many possible answers.5m
10. 10Context WindowsA hard limit on what the model can see at once.4m
11. 11Retrieval-Augmented GenerationFetch the facts first, then let the model write.5m
12. 12Vector DatabasesNearest-neighbour search that stays fast at scale.5m
13. 13Fine-Tuning vs PromptingChange the instructions, or change the weights.5m
14. 14Agents and ToolsA model in a loop that can act and try again.5m
15. 15Evaluating LLMsIf you cannot score it, you cannot improve it.5m