20 posts found
What a large language model actually predicts
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
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
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
An embedding turns text into coordinates, and nearby coordinates mean related meaning. That single idea is what makes se...
The context window is a budget, not a memory
Bigger context windows did not give models memory. They gave you a larger envelope to fill on every single request — and...
Why models hallucinate, and what actually reduces it
Hallucination is not a glitch that a better model will one day remove. It is what generation does when it has nothing to...
Choosing between a large model and a small one
Most production traffic does not need the largest model available. Routing by task rather than defaulting to the top of...
Why agents fail on long tasks
An agent that handles five steps beautifully can fall apart at twenty. The reason is rarely reasoning — it is that the c...
Giving an agent memory without giving it amnesia
Memory is not a feature you enable. It is a set of decisions about what to keep, what to summarise and what to let go —...
When a workflow beats an agent
If you already know the steps, do not ask a model to rediscover them on every request. A fixed pipeline with model calls...
Reviewing AI-generated UI: a checklist
Generated interfaces fail in a predictable set of places. Knowing which ones turns review from a vague unease into a lis...
RAG in one page: retrieve, rank, answer
Retrieval-augmented generation is three steps and a lot of tuning. The architecture is simple; the quality lives almost...