Build Your Own LLM, Lesson 5: Self-Attention From Scratch
Understand and code the attention mechanism behind transformers: queries, keys, values, the causal mask and softmax — first with NumPy on four tokens, then…
Read article →Category Archives: AI & ML
Artificial intelligence explained by building it: machine learning, neural networks, LLMs, RAG and agents — plus how to build your own language model.
Build Your Own LLM, Lesson 4: Embeddings and Your First Neural Language Model
Build Your Own LLM, Lesson 4: Embeddings and Your First Neural Language Model
Rebuild the bigram model as a neural network in PyTorch, train it with gradient descent, and add embeddings — the vectors that let language…
Read article →Build Your Own LLM, Lesson 3: A Language Model Made of Counting
Build Your Own LLM, Lesson 3: A Language Model Made of Counting
Build a bigram language model with plain Python dictionaries, generate text from it, and measure it with loss — the same number every LLM…
Read article →Build Your Own LLM, Lesson 2: Write a BPE Tokenizer in Python
Build Your Own LLM, Lesson 2: Write a BPE Tokenizer in Python
Build the byte-pair encoding tokenizer used by GPT-style models from scratch in about 40 lines of Python: training merges, encoding, decoding and why the…
Read article →Build Your Own LLM, Lesson 1: How a Language Model Actually Works
Build Your Own LLM, Lesson 1: How a Language Model Actually Works
A plain-English tour of what happens inside ChatGPT-style models: tokens, probabilities, training on next-token prediction, and why a model that only guesses the next…
Read article →Build a RAG Chatbot That Answers From Your Own PDFs and Excel Files (Complete Guide)
Build a RAG Chatbot That Answers From Your Own PDFs and Excel Files (Complete Guide)
Step-by-step guide to retrieval-augmented generation in Python: load PDFs and Excel sheets, chunk them, create embeddings, search by meaning, and answer with a local…
Read article →AI Agents and Tool Calling Explained (With a 20-Line Example)
AI Agents and Tool Calling Explained (With a 20-Line Example)
What people mean by AI agents: a model in a loop that can call tools such as search, a calculator or your database. How…
Read article →LoRA Fine-Tuning Explained: Teach an LLM New Tricks on One GPU
LoRA Fine-Tuning Explained: Teach an LLM New Tricks on One GPU
How LoRA fine-tuning works, why it trains less than 1% of a model’s parameters, when fine-tuning beats prompting or RAG, and a minimal Hugging…
Read article →Using AI to Write Excel Formulas: A Safe 5-Step Checklist
Using AI to Write Excel Formulas: A Safe 5-Step Checklist
AI assistants are great at Excel formulas — when you give them the right details and test the result. A five-step checklist with an…
Read article →Run an LLM on Your Own Laptop with Ollama (Private, Free, Offline)
Run an LLM on Your Own Laptop with Ollama (Private, Free, Offline)
Install Ollama, run open models like Llama and Qwen locally, call them from Python and Excel-friendly scripts, and create a custom model with a…
Read article →Why AI Chatbots Make Things Up (and 6 Ways to Catch It)
Why AI Chatbots Make Things Up (and 6 Ways to Catch It)
LLM "hallucinations" explained simply: why a next-token predictor can sound confident and still be wrong, and six practical habits to catch fabricated facts, formulas…
Read article →Temperature and Top-p Explained: Why the Same Prompt Gives Different Answers
Temperature and Top-p Explained: Why the Same Prompt Gives Different Answers
What the temperature and top-p settings in AI models actually do, with a worked numeric example, and which values to use for code, data…
Read article →