
Articles
When to use retrieval-augmented generation — and when not to
Retrieval fixes access, provenance and staleness — not every weakness a model has.
Where inference actually runs, and the vocabulary that nests AI, machine learning, deep learning and LLMs: what a model knows, and how tokens work.

Retrieval fixes access, provenance and staleness — not every weakness a model has.

Where the weights sit decides who operates what, and what leaves your machine.

How AI, machine learning, deep learning and LLMs nest — and what each term does not imply.

What sits in a model's parameters, what its training cutoff freezes, and what you supply.

Why text becomes tokens, what a tokenizer and vocabulary are, and how generation works.