Large Language Models (LLMs) Explained

Large Language Models (LLMs)

1 min readPublished 22 Jul 2026

Track your progress. Sign in to mark this guide complete and build your Job Readiness Score.

Large Language Models (LLMs) like GPT, Claude and Gemini power modern AI assistants. Understanding how they work is the key to using them well.

Interactive explainer

Anatomy of an LLM

Tokens, context, temperature and hallucination.

Tap or hover a part to learn more.

Tokens

Text in pieces.

LLMs break text into tokens (words or word-pieces) and predict the next token repeatedly. Everything an LLM does is next-token prediction at scale.

Check your understanding

1. What is the context window?

2. Why do LLMs hallucinate?

Keep learning

Large Language Models RAG Microsoft AI-900

Practise this in AI Interview™

How LLMs work

Tokens — LLMs break text into tokens (word pieces) and predict the next one, over and over.
Training vs inference — trained once on huge datasets; inference is when you use the model.
Context window — the amount of text the model can consider at once; exceed it and earlier content is forgotten.
Temperature — controls randomness/creativity of output.
Hallucination — LLMs can confidently state false things, because they predict plausible text, not truth. Ground them with RAG and verify outputs.

This foundation makes prompt engineering and agents make sense.

Interview Intelligence

How this topic actually shows up in interviews — and how to demonstrate you understand it.

Why employers ask about this

Using LLMs effectively — and knowing their limits — is fast becoming a core professional skill.

Technical questions

Why do LLMs hallucinate, and how do you reduce it?+

They predict plausible text, not truth; reduce it with grounding (RAG), clear prompts and verifying outputs.

Behavioural questions

Describe using an AI tool responsibly at work.+

Show verifying outputs and not blindly trusting the model.

Real-world scenarios

“An LLM confidently gives a wrong answer.”+

Expected answer: Recognise hallucination — verify against a trusted source, and ground the model with RAG or provided context.

Practise in AI Interview™Rehearse these questions, scored.Plan with Career Coach™A personalised path to your goal.Evidence it in Career Passport™Prove this skill to employers.

Employability Intelligence

Where this knowledge takes you — the jobs, skills and certifications it feeds into.

Relevant roles

AI EngineerPrompt EngineerAutomation Engineer

Skills you're proving

LLMsContext windowHallucination

Recommended certifications

Microsoft AI-900 (AI Fundamentals)Microsoft AI-102AWS AI Practitioner

Career progression

AI & Automation Fundamentals → AI engineering roles.

What employers expect

That you can use AI tools effectively, understand their limits, and automate work responsibly.

Frequently asked questions

What is a token?

A chunk of text (a word or word-piece) that an LLM processes; models predict the next token repeatedly to generate text.

What is the context window?

The maximum amount of text an LLM can consider at once; content beyond it is not 'seen' by the model.

Why do LLMs hallucinate?

They predict plausible-sounding text rather than retrieving verified facts, so they can state false things confidently.

Practise what you've learned

Turn this guide into real, evidenced progress

Missiora helps you measure, improve and evidence the capabilities employers actually value — start with the tools best suited to this topic.

Published by

Missiora

Missiora is an AI Employability Intelligence platform. Our resources are researched and reviewed by the Missiora team to help you measure, improve and prove your career readiness.