Concepts

AI, explained in plain language

Short, honest explainers for the ideas behind modern AI. No jargon, no hype, no sign-up.

What is an LLM? Read →
The kind of AI behind chat assistants, explained without the jargon: what it is, how it produces text, and where it falls short.
What is an AI hallucination? Read →
When a model states something false with total confidence. Why it happens, and how to protect yourself from it.
What is prompt engineering? Read →
The difference between a vague request and a useful answer is usually the prompt. Here are the parts that actually move the needle.
How transformers work Read →
The neural network design that powers almost every modern language model, and the one idea, attention, that made it work.
Machine learning vs deep learning Read →
Two terms people use interchangeably that are not the same. How they nest, and what actually changed with "deep".
What are AI agents? Read →
The step from a model that answers questions to one that takes actions on your behalf, and why that step is harder than it sounds.
Open weights vs closed models Read →
Whether a model's trained parameters are public or locked behind an API changes who controls it, where it runs, and what you can do with it.
Inference and hosting Read →
Training builds the model once. Inference is every time you actually use it, and hosting is the infrastructure that keeps it fast.
How AI models are trained Read →
The process that turns a random network into something useful: read a lot, adjust, repeat, then teach it to behave.
What are tokens? Read →
Models do not see words. They see tokens, the fragments that pricing, context limits, and speed are all measured in.
What is a context window? Read →
The model's working memory: how much text it can hold in mind at once, and why it seems to forget once you go past it.
What is fine-tuning? Read →
Taking a capable general model and training it a little more on your own examples to make it better at one specific job.
What is RAG? Read →
Letting a model look things up. Instead of answering from frozen memory, it fetches the relevant text first, then answers from that.
What are parameters? Read →
The billions of numbers a model learns during training, and what a label like "7B" or "70B" is really telling you.
What is a reasoning model? Read →
Some models answer straight away. Others generate a long stretch of working first. Here is what that thinking is, and when it is worth waiting for.
What is a mixture of experts? Read →
How a model can have hundreds of billions of parameters and still answer quickly: it only wakes up a few of them for each token.
What is AI sycophancy? Read →
The tendency of a chat model to agree with you, flatter you, and back down when you push. It is a training side effect, and it is worse than it looks.
Why AI writing sounds like AI Read →
You can spot it in a sentence. Here is what the tells are, why every model has the same ones, and what it takes to make them go away.
What is a model cascade? Read →
Instead of one big model for everything, a cascade starts small and escalates. Here is how the routing decision is made and why it changes the economics of AI chat.
Context window vs knowledge cutoff Read →
One is how much the model can look at right now. The other is how recent its training is. They get mixed up constantly, and the fix for each is different.
Which AI models are open weights? Read →
Open weights means you can download the model. The license decides what you can do with it. Here is the map, family by family.
Pre-training vs post-training Read →
The expensive stage that builds the raw ability, and the cheaper stage that shapes it into something you can talk to. Most of what you notice about a model comes from the second.
How LLMs handle Spanish and other languages Read →
The same model, the same question, a different language. What changes under the hood, and what to do about it.