What is an LLM?
Kahu team·Updated 2 Oct 2026·5 min read
An LLM, or large language model, is an AI model trained on huge amounts of text so it can understand and write language. It works by predicting the next piece of text, over and over, which lets it answer questions, draft emails and summarise documents. LLMs are the engines inside chat assistants like ChatGPT, Gemini and Claude.
What each word means
- Large: trained on a vast amount of text and built with an enormous number of internal settings.
- Language: it works with words, so it can read, write, translate and summarise.
- Model: the trained engine that apps send requests to.
How an LLM writes
An LLM breaks text into small pieces called tokens, which are whole words or parts of words. Given your message, it calculates which token is most likely to come next, adds it, and repeats until the answer is complete. Because it has seen so much writing, those predictions add up to fluent, sensible text. But it is predicting, not looking up facts.
Two terms worth knowing
| Term | What it means | Why it matters to you |
|---|---|---|
| Context window | How much text the model can consider at once | Long documents or chats may go beyond it, and earlier details get dropped |
| Training cut-off | The point after which it learned nothing new | It will not know recent events unless the tool can search the web |
Good at, and not so good at
- Good at: drafting, rewording, summarising, answering from text you give it, sorting messages by topic.
- Not so good at: exact sums, facts it was never given, recent news without search, and saying I do not know.
- Risky for: anything legal, medical or financial that a customer will rely on without a person checking.
Where Kahu fits
Two Thursday gaps at 11:00 and 14:30. Drafted messages to 6 waitlisted customers.
Updated the hours on your site and Google profile to Sat–Sun 8–2.
One post about the new hours, using your Sunday counter photo.Frequently asked questions
Is an LLM the same as generative AI?
An LLM is one kind of generative AI, the kind that works with text. Image and video generators are other kinds.
Why do LLMs make things up?
Because they predict likely text rather than retrieve stored facts. When they lack the information, a plausible guess can come out sounding certain.
Can an LLM answer questions about my business?
Only if you give it your information, for example by pasting it in or using a tool connected to your own details.