What AI Actually Is (and Isn’t)
Separate the hype from reality in a Defence and government context. Test your assumptions with an interactive quiz, then explore how Large Language Models actually work through an animated diagram.
Myth vs Reality Quiz
For each statement, decide: is it a Myth or Reality? These are tailored to Defence and government contexts. Click to reveal the truth.
How an LLM Actually Works
Click each stage to explore how a Large Language Model processes your prompt and generates a response. It is not magic — it is pattern matching at an extraordinary scale.
Your Prompt
You type a message. The model receives raw text — it has no idea who you are, your clearance level, or your role in Defence.
Tokenisation
Your text is split into tokens — chunks of words, subwords, or characters. Each token maps to a number the model can process.
Embedding & Attention
Each token becomes a high-dimensional vector. The attention mechanism figures out which words relate to which, resolving ambiguity in context.
Next-Token Prediction
The model calculates the probability of every possible next token. It does not “know” the answer — it predicts what text is statistically most likely to follow.
Token-by-Token Output
One token is selected, appended, and the process repeats. Each new token considers everything before it. This is why responses stream in piece by piece.
Key insight: LLMs do not understand anything. They are sophisticated pattern-matching machines. This is why they can sound confident while being completely wrong — they predict plausible text, not verified facts. For Defence personnel, this means every AI output must be treated as a draft, never as a source of truth.
Try It Yourself
Open any of these AI tools and start a conversation. Notice how the response streams in token by token — now you know why.