#llm
8 articles about llm
Filter by topic
Episode 0: Why Code LLMs From Scratch
Understanding how LLMs work without a PhD in mathematics: what this series promises, what you will learn, and the one idea that ties every episode together.
Episode 1: Attention Is Just 4 Mathematical Operations
Behind Transformers and the attention mechanism there are only four simple operations: matrix multiplication, transposition, scaling and softmax. Here they are, in Rust.
Episode 2: Q, K, V — Why 3 Matrices Instead of One?
Query, Key, Value: why real models project each word into three different spaces, and what that separation of roles changes for attention.
Episode 3: Embeddings — Absolute at the Start, Contextual at the End
Is an embedding the word on its own or the word in context? Both, at different moments. Plus the three engineering details around attention: multi-head, masking and position encoding.
Episode 4: Transfer Learning — Reusing Existing Knowledge
Why nobody trains a model from zero: where transfer learning comes from, what it saves you, and its three strategies — feature extraction, fine-tuning and LoRA.
Episode 5: The Key Concepts Around Transfer Learning
Pre-training, fine-tuning, catastrophic forgetting, freezing, domain shift and learning rate: the transfer learning terms you hear all the time, explained simply with an analogy for each.
Episode 6: Embeddings and Vector Databases
From keywords to meaning: how embeddings and cosine similarity let you search by proximity, why you need a vector database, and how it all comes together as a RAG.
AI Commit Messages Without Handing Over Your Git History
AI git tooling tends to come in two shapes: a text box you copy out of, or an agent that runs commands and tells you afterwards. There is a third option, and it comes down to where the approval sits.