A practical, no-code introduction to generative AI: large language models, context engineering, orchestration, retrieval-augmented generation, and agentic task execution.
"Artificial intelligence" has meant several different things at different points in its own history, and a good deal of confusion in how people talk about it today comes from treating those as one continuous technology…
A first encounter with the idea that underlies search engines, recommendation systems, and the atlas on this site
Underneath every capability an LLM appears to have — answering questions, writing code, holding a conversation — it is doing one specific and much narrower thing on every single step. It predicts which token (roughly, a…
A language model writes its answer one token at a time and can't take one back. That single fact explains most of what people call its "thinking," why it sometimes corrects itself mid-answer and often doesn't, and why…
Two people can type the same three-word question into the same chat window and get very different quality of answer, and the difference is rarely luck. It is usually that one of them is working with the model's raw…
Generation, summarisation, and paraphrasing look like three separate buttons in most AI tools, but underneath they are the same mechanism doing three different jobs: predicting plausible next text, given whatever…
The simplest way to use a large language model is to ask it one question and read one answer, with nothing before and nothing after. The most common way people actually use one — a chat window open for twenty minutes, a…
When a language model answers purely from what it absorbed during training, it is doing something closer to reciting from memory than looking anything up — and, as the previous page on question-answering systems…
"AI is transforming business" and "AI is transforming education" are two of the least useful sentences in circulation, because they are compatible with almost any outcome — a productivity gain, a stalled pilot project…
"Vibe coding" — Andrej Karpathy's term for building software by describing what you want in prose and iterating on an LLM's output rather than reading or editing its code 1 — is now a default way many students and…
Every idea preceding this page in the module has been building towards one capability: the judgement to decide how AI should be involved in solving a real problem, rather than defaulting to "type the problem into a chat…