AI Basics

The ideas underneath the tools — what a model is doing when it answers you.

What a large language model actually predicts
What a large language model actually predicts
12/09/2026 — admin@byqreal.test

A model does not look anything up and does not decide what is true. It estimates which token comes next. Almost everythi...

Tokens, not words: how a model reads your text
Tokens, not words: how a model reads your text
10/09/2026 — admin@byqreal.test

Models do not see characters or words. They see tokens — and once you know how text becomes tokens, several odd behaviou...

Why temperature changes the answer, not the knowledge
Why temperature changes the answer, not the knowledge
08/09/2026 — admin@byqreal.test

Turning temperature down does not make a model more accurate. It makes it more repeatable — and confusing the two is how...

Embeddings explained without the linear algebra
Embeddings explained without the linear algebra
06/09/2026 — admin@byqreal.test

An embedding turns text into coordinates, and nearby coordinates mean related meaning. That single idea is what makes se...

Training, fine-tuning and prompting are three different tools
Training, fine-tuning and prompting are three different tools
04/09/2026 — admin@byqreal.test

Teams reach for fine-tuning when they need context, and for prompting when they need behaviour. Knowing which problem ea...