How AI Works, in Plain English: Chatbots, Images and Voice

By the WahLiao desk · Last verified 3 October 2026

A Super Intelligence chatbot, the kind of AI behind ChatGPT, Claude, Gemini and Copilot, works by prediction. It has learned from an enormous amount of text how language usually runs, and when you ask it something, it builds an answer piece by piece, choosing what most plausibly comes next. People then tune it to be helpful and to turn down harmful requests. Unless it’s connected to web search, it isn’t looking anything up, and it has no built-in sense of when it’s wrong.

That one idea explains nearly everything. It’s why it can draft a polite letter to your town council in seconds, why it can explain your CPF letter in simpler words than the letter itself, and why it can also name an MRT station that doesn’t exist, with total confidence.

How it works: quick facts

Training	The model learns patterns from very large collections of text, code, images or audio
Prediction	It writes an answer a small piece at a time, picking what most plausibly comes next
Tuning	People rate its answers so it becomes more helpful, polite and safe
Search	Some tools can search the web and show sources; it’s still worth opening them
Mistakes	“Hallucinations”: fluent answers that are wrong or made up
Images and voice	Built in a similar way, but learned from pictures and recordings

The WahLiao Verdict

Best at	First drafts, summaries, explanations, translation and brainstorming.
Weakest at	Exact facts, fresh news without search, and knowing its own limits.
The habit to build	Ask for sources, then actually open them.
Never paste in	Passwords, NRIC numbers or anything you wouldn’t email a stranger.
Remember	Fluent isn’t the same as correct.

Step one: training

Before a model can answer anything, it has to be trained. Engineers feed it a vast amount of text, from books and websites to computer code, and the model slowly adjusts billions of internal settings until it gets very good at one narrow job: guessing the next piece of a passage. Along the way it picks up grammar, facts, styles, arguments and the shape of a good explanation.

What it doesn’t do is keep a tidy encyclopaedia. Its knowledge ends up spread across those settings as patterns. That’s why a model can recall a fact nicely in one conversation and garble it in the next, and why its knowledge stops wherever its training data ended.

Step two: prediction

When you type a question, the model breaks it into small chunks called tokens, roughly pieces of words, and writes its reply one token at a time. Each choice depends on everything before it: your question, instructions from the company that runs it, and the words it has already written. Picture your phone’s autocomplete, grown to the size of a library and given the patience to plan a whole paragraph.

Step three: tuning

Left raw, a model will happily continue any text, helpful or not. So companies tune it, largely by having people compare and rate answers, until it behaves like a useful assistant that follows instructions, admits some limits and declines harmful requests. This tuning is why different chatbots have different personalities, even when they learned from similar material.

Why it makes confident mistakes

Because it predicts plausible text rather than fetching checked facts, a model can give you an answer that sounds right and is wrong. The industry calls these hallucinations, and Singapore’s Model AI Governance Framework for Generative AI, published by IMDA in 2024, lists them among the new risks generative tools bring. The danger zones are the precise things: prices, dates, names, legal rules, citations and medical doses. The model doesn’t change its tone when it’s unsure. It sounds just as confident when it’s making things up.

Two habits help a lot. Ask the tool for sources, and if it can search the web, open the links it shows you. And for anything with real consequences, such as a contract, a tax filing or your health, treat its answer as the start of a question to a person or an official page, not the end of one.

When it searches the web

Many chatbots can now search the internet, read the results and summarise them with links. That makes them much better at recent events and current prices, but not infallible: they can misread a page, lean on a weak source or blend two sources into one wrong sentence. The links are there so you can check, so do give them a click.

Image makers, voice tools and agents

Image generators learn from huge numbers of pictures paired with descriptions. Give one a prompt and most will start from visual noise and refine it, step by step, into an image that matches your words. Voice tools learn the sound and rhythm of speech, and some can imitate a particular person from a short recording. So if a call in a relative’s voice asks for money, always check by calling them back on a number you know.

Agents go a step further than chat. They can take actions, such as browsing, filling in forms or working through a task in several stages. That’s handy, and it also means you should check what an agent did before anything is paid for or sent.

Good at, bad at

Good at	Bad at
Drafting emails, letters and reports	Exact figures and current prices, unless it searches
Explaining a hard idea simply	Knowing when it’s wrong
Summarising long documents	Citing sources it hasn’t actually read
Translating and rewording	Local rules that changed recently
Brainstorming options	Judgment calls that need your context

How AI works: FAQ

How does an AI chatbot like ChatGPT work?

It has learned patterns from a vast amount of text, and it writes answers by predicting, one small piece at a time, what most plausibly comes next. People then tune it to be helpful and safe.

Does AI look things up?

Only when the tool is connected to web search, or to documents you give it. Otherwise it answers from patterns it learned in training, which can be out of date.

Why does AI make things up?

Because it generates plausible text rather than fetching checked facts. These errors are called hallucinations, and they sound every bit as confident as correct answers.

Can AI copy someone’s voice?

Yes. Some voice tools can imitate a person from a short recording. If a call in a familiar voice asks for money or codes, hang up and call back on a number you already know.