A 12-PART SERIES · AUSSIE SCIENCE CLIPS
How AI Works
What's actually going on inside the AI everyone is talking about: how a machine learns, writes and draws, and why it gets things confidently wrong. Plain words, real mechanisms.
EPISODE 1 · 12 min
What actually is AI, and why does everyone mean something different?
Say AI to five people, and you might get five different pictures. A chatbot that writes your emails. The app that steers you around traffic. A robot villain from a film. The filter that quietly binned your spam this…
EPISODE 2 · 11 min
How can a computer learn without being told the rules?
Last time, we met machine learning: the part of AI that learns from examples instead of following rules people wrote. How can a computer learn something nobody told it? Start with a job that sounds easy to write rules…
EPISODE 3 · 12 min
What is a neural network, and how is it not like a brain?
Last time, Arthur Samuel pointed to a road he didn't take: a network of simple switches inspired by nerve cells. Today's chatbots took that road, with billions of numbers, in what's called a neural network. The name…
EPISODE 4 · 12 min
How does a machine get better by being wrong?
Last episode's artificial neuron multiplies each input by a weight and adds them up. Each weight is like a dial, and the dials decide what the network does. Big language models, in papers from 2020 to 2023, had tens of…
EPISODE 5 · 12 min
Why did AI suddenly get good after 2012?
Last time, we watched a network learn by passing the blame for its mistakes backwards. That recipe, backpropagation, was made famous by a 1986 paper. Then, after an early burst of excitement, it spent years on the…
EPISODE 6 · 12 min
How does a chatbot actually write a sentence?
Last time, we saw data, chips and better methods make AI suddenly good at recognising pictures. But a chatbot writes back whole sentences, in good grammar, on almost any topic. So what is it actually doing? The answer…
EPISODE 7 · 12 min
What is 'attention', and why did one 2017 paper change everything?
Last time, a chatbot wrote one token at a time, and we treated the network inside as a closed box. We stopped on this sentence. The trophy didn't fit in the suitcase because it was too big. What was too big? The…
EPISODE 8 · 13 min
How do you turn the whole internet into a chatbot?
Last time, we opened the box: attention, and transformers that learn it in parallel on graphics chips. But a transformer that has read the internet still isn't a chatbot. Ask it a question, and it may just carry on, as…
EPISODE 9 · 12 min
Why does AI make things up so confidently?
Last time, a politely tuned chatbot explained why some experts say you should eat socks after meditating. So why does AI make things up so confidently? In May 2025, researchers asked three chatbots, ChatGPT, DeepSeek…
EPISODE 10 · 12 min
How does AI make a picture from a sentence?
Last time, we saw a chatbot make things up by accident. Image generators make things up on purpose. You type a sentence, and a little later there's a photo of a place that never existed. The strangest part is where…
EPISODE 11 · 12 min
What is an AI 'agent', and what can it really do on its own?
Last time, we watched a sentence steer random noise into a picture. But you've probably heard that AI can now do things: fix a program, fill in a form, click around a website by itself. What is an AI agent, and what…
EPISODE 12 · 12 min
Why does AI need so many chips, and so much power?
Last time, we watched an agent work in a loop, calling a model again and again. Every one of those calls is arithmetic, done on a chip, in a building, drawing power from a grid.