Automation and AI

Large Language Model (LLM)

Also called LLM, language model

The kind of AI model trained on very large amounts of text to predict and produce language, behind most chat tools.

Quick facts: Large Language Model (LLM)

Category
Automation and AI
Also called
LLM, language model
Level
Beginner
Affects
Content drafting, support replies, research speed
Where to see it
ChatGPT, Claude, Gemini, and the models inside marketing software
In this article4
  1. How a large language model works
  2. Why large language models matter
  3. Where large language models go wrong
  4. How to act on it

How a large language model works

The model is trained on an enormous amount of written material and learns the statistical relationships inside it: which word tends to follow which, how an argument is usually structured, what an answer to this sort of question normally looks like. Running it means predicting the next piece of text, then the next, until the reply is finished.

Two consequences follow, and almost everything practical comes from them. First, the training stops at a point in time, so the model has no knowledge of anything after that unless the product searches the web or you supply the material yourself. Second, the knowledge it does hold is diffuse rather than filed. It is not looking anything up, so recall is approximate and gets less reliable the more obscure the subject.

Modern models are then tuned to follow instructions and to behave within limits, which is why they take direction so readily. That tuning shapes manner, not accuracy: a well-behaved model can still be confidently wrong.

Why large language models matter

They are the engine underneath almost every AI feature now appearing in marketing software: the assistant in your ad platform, the reply suggestions in your inbox, the website chatbot, the tool that writes product descriptions. Understanding what the engine is stops you misreading what those features can promise.

It also prevents the two errors that cost businesses most. Treating a model as a search engine produces confident nonsense about recent events and niche subjects. Treating it as a colleague who has read your files produces answers about your business that were never grounded in anything you gave it.

Where large language models go wrong

Recency is the first trap. Ask about a platform update, a rule change or a price and you may get a description of how things used to be, delivered with no hint that it is out of date.

Consistency is the second. The same prompt can produce different answers on different runs, which is fine for drafting and a real problem for anything you expected to be repeatable, such as classifying enquiries into fixed categories. If you need consistency, constrain the output rather than hoping.

Confidentiality is the third and the one most often overlooked. Text you paste is processed by somebody else’s service under their terms, and consumer tools are not the place for client data, contracts or customer records. Check what a tool retains and what it may train on before it becomes a habit across the team.

How to act on it

Supply the facts rather than relying on recall. Paste the policy, the brief, the transcript, the current price list, and ask the model to work inside what you gave it. Answers improve immediately and become checkable, because you can see what they were built from. Where the material is large, retrieval and the size of the context window decide how much of it the model can actually consider.

Then set two team rules and keep them. Nothing confidential goes into a tool that has not been approved, and any checkable claim in the output is verified before it is used — the failure mode is always a plausible sentence with nothing behind it. Within those limits, generative tools earn their place on drafting, restructuring and summarising work.

Do and do not

Do

  • Give it the source material instead of trusting recall
  • Ask for reasoning and sources you can check
  • Agree a team rule on confidential data first

Do not

  • Use it as a search engine for recent events
  • Expect two runs to give the same answer
  • Paste customer records into an unvetted tool

Questions people ask about this

Is an LLM the same as a search engine?

No, and the difference matters. A search engine finds documents that exist and shows you where they are. A language model produces text that fits the patterns it learned, with no document behind it unless the product retrieves one. Some tools now do both, searching and then writing. If accuracy about a fact matters, check that the answer came with a source you can open.

Why does the model not know about something recent?

Because its training finished at a point in time, and everything after that is outside what it learned. Some products fill the gap by searching the web during the conversation, but not all do, and the model rarely warns you which situation you are in. For anything recent, supply the material yourself or use a tool that cites live sources.

Is it safe to paste client information into an AI tool?

Not by default. Consumer accounts and business accounts often have very different terms about retention and about whether your text may be used to improve the service. Before anything confidential goes in, check the terms for the specific plan you are on, agree a written rule with the team, and use an approved tool rather than whatever is convenient.

Related terms

Found this useful?

Share it, or ask an AI to summarise it

Back to the glossary

Knowing the term is the easy part

Applying it to your own site and budget is the work. Book a call and I will tell you what actually applies to you.