AI & Developer Tips
Short, practical explanations and tools for AI, Linux, and everyday development.
2026
- How should you chunk documents for RAG? A chunk-size experiment
- What is a context window, and what happens when the input is too long?
- Prompting vs RAG vs fine-tuning: which one do you need?
- RAG explained in 50 lines of Python (with a local model)
- Train, validation and test sets: what overfitting looks like in numbers
- What does temperature do in an LLM? Temperature, top-k and top-p explained
- Why you should always build a baseline model first
- What are embeddings? Semantic search with cosine similarity in Python
- Why is 99% accuracy useless? Precision, recall and F1 explained
- What is a token, and why do LLMs count tokens instead of words?
