Articles

Artificial intelligence

The articles in this section explain how language models and neural networks work in plain words, but without the simplifications that turn into falsehoods: where the technology has limits, we say so directly.

What the section covers#

"Artificial intelligence" names very different things today: an academic field more than seventy years old and a specific chat window in your browser. The articles go from the general to the specific. First, what the term actually means and how the current wave differs from earlier ones. Then how language models and neural networks work: tokens, predicting the next token, the context window, the difference between training a model and running a finished one. After that, practice: how to phrase a request, which prompting techniques really change the result, how agents are built and why a long chain of automatic steps does not become more reliable. A separate article covers learning: how to use a model to understand a subject rather than to replace that understanding with ready-made text.

Product names appear only as examples. Ranking them by "strength" makes no sense here: models are updated faster than a page goes out of date, and any "this one is better" becomes untrue within a month.

One rule for every page#

All of this technology shares one property that matters more than any technique: a model produces plausible text, not verified text. It is wrong in the same calm, confident tone in which it is right, and it cannot tell you that it does not know something. That is why every article has a section on limits: what to check by hand, which links and quotes do not exist, what data you should not send to someone else's service, and where a model's answer is no substitute for a real specialist — a doctor, a lawyer, a financial adviser.

Artificial intelligence What is artificial intelligence
Artificial intelligence is not one technology but the name of a whole field. In everyday speech the word covers programs that do tasks which used to need a person — recognising speech, translating, writing text, picking an answer.
Artificial intelligence What is an LLM
An LLM (large language model) is a program trained to continue text. Everything it does comes down to one operation: look at what has been written so far, predict the next small piece, and repeat.
Artificial intelligence Prompt engineering
Prompt engineering is choosing the input text so that a model more often produces the result you need. It is not a set of magic spells but ordinary engineering work — a hypothesis, a test on a set of examples, rolling back changes that did not help.
Artificial intelligence How to write a prompt
A good prompt differs from a bad one not in length or politeness but in having everything the work needs — the task, the material, the shape of the answer and what a usable result looks like.
Artificial intelligence How to use AI
Getting started is simpler than it looks: you need one service, one real task from your own work and the habit of checking the result. Everything else is detail you pick up along the way.
Artificial intelligence How neural networks work
A neural network is simpler than its name suggests. Inside there are no thoughts or images — there are tables of numbers multiplied by the input values, and a procedure that keeps nudging those numbers until the answers get more accurate.
Artificial intelligence AI for studying
A model can explain a confusing point three different ways and answer a silly question patiently, without judgement. It can also hand you a finished assignment that leaves you unable to do anything new.
Artificial intelligence AI agents
An agent is not a special, smarter model but a harness around an ordinary one: the model gets a list of tools and is allowed to call them in a loop until the task is finished — or until patience runs out.