Start here: learn AI words in the right order.
Pick a path. Each one teaches a handful of words in the order they build on each other, so every page makes sense when you reach it. Each word page shows your step and the next word.
Understand ChatGPT
The words that explain what happens when you chat with an AI. 10 words, in order.
- 1ChatGPTChatGPT is an app: a chatbot made by OpenAI. The thinking happens in a model called GPT that runs inside it.
- 2Large language modelA large language model, or LLM, is an AI that has read a huge amount of text and writes by predicting a likely next word, again and again.
- 3TokenA token is a small chunk of text, often a word or part of a word, that an AI model reads and writes. It is the unit AI counts in.
- 4TransformerA transformer is the design behind ChatGPT, Claude and Gemini. It reads a whole passage at once and works out which words matter to each other.
- 5Next-token predictionNext-token prediction is how chatbots write: they guess the most fitting next piece of text, add it, and repeat, one piece at a time.
- 6Context windowA context window is how much text an AI can keep in view at once. Anything that falls outside it, the AI simply cannot see.
- 7PromptA prompt is whatever you type or give to an AI to tell it what you want. The AI's answer is built from it.
- 8TemperatureTemperature is a setting that controls how adventurous an AI is when picking its next word: low for safe and predictable, high for varied and surprising.
- 9HallucinationAn AI hallucination is when a chatbot states something false, like a made-up fact or source, in the same confident tone it uses for the truth.
- 10RLHFRLHF trains a chatbot using people's preferences: humans pick the better of two answers, and the model learns to give answers people prefer.
Use AI tools well
Get better answers and avoid the common traps. 9 words, in order.
- 1PromptA prompt is whatever you type or give to an AI to tell it what you want. The AI's answer is built from it.
- 2Prompt engineeringPrompt engineering is the skill of wording your request to an AI so it reliably gives you what you actually need.
- 3System promptA system prompt is a set of standing instructions an AI reads before your message, setting its role, rules and tone for the whole chat.
- 4Few-shot promptingFew-shot prompting means showing an AI a few worked examples inside your prompt, so it copies the pattern for your new case.
- 5HallucinationAn AI hallucination is when a chatbot states something false, like a made-up fact or source, in the same confident tone it uses for the truth.
- 6Knowledge cutoffA knowledge cutoff is the date an AI's training reading stopped. It knows nothing that happened after it, unless it looks things up.
- 7Retrieval-augmented generationRAG lets an AI look up the relevant pages in a set of documents first, then write its answer from what it found.
- 8AI and privacyAI and privacy is about what happens to personal information when AI is trained on it or when you share it with an AI tool.
- 9Human in the loopHuman in the loop means a person checks, approves or can stop what an AI does, instead of letting it act completely on its own.
How machines learn, from zero
What training really means, step by step. 10 words, in order.
- 1Machine learningMachine learning is a way of building software where the computer works out its own rules from examples, instead of a person writing every rule.
- 2Training dataTraining data is the collection of examples an AI model learns from. Whatever patterns, gaps and mistakes it contains, the model tends to pick up.
- 3AI modelAn AI model is the trained part of an AI system: a file of learned numbers that turns an input, like a photo or a question, into an output.
- 4TrainingTraining is how an AI model learns: it makes a guess, checks how wrong it was, and nudges its numbers to do a little better, millions of times over.
- 5Loss functionA loss function is the scorecard of training: one number that says how wrong a model's guesses are, so training can push it down.
- 6Gradient descentGradient descent is how most AI models learn: check which way reduces the error, take a small step that way, and repeat.
- 7Neural networkA neural network is a web of simple maths units, loosely inspired by brain cells, that learns by strengthening or weakening the links between them.
- 8OverfittingOverfitting is when an AI memorises its practice examples, quirks and all, so it looks perfect in training but fails on anything new.
- 9Test setA test set is data kept locked away during training, so we can fairly check how well a model works on examples it has never seen.
- 10InferenceInference is using a trained AI model: feeding it something new, like your question or a photo, and letting it work out an answer.
AI that acts: agents
From chatbots that talk to agents that do things. 9 words, in order.
- 1AI agentAn AI agent is an AI you give a goal, not just a question. It plans steps, uses tools, checks results and keeps going until the job is done.
- 2Tool useTool use lets an AI model ask for outside help, like a search, a calculator or a booking system, and then use the result in its answer.
- 3Model Context ProtocolMCP is a shared standard that lets any AI app plug into any tool or data source the same way, like one charging port for everything.
- 4Computer useComputer use means an AI operating a computer the way you do: looking at the screen, moving the mouse, clicking and typing.
- 5Multi-agent systemA multi-agent system splits one big job between several AI agents, usually a lead agent that hands out parts and combines the results.
- 6Agent skillsAgent skills are packaged how-to guides, with instructions and sometimes code, that an AI agent opens only when a task calls for them.
- 7Reasoning modelA reasoning model is an AI that works through a problem step by step, privately, before it gives its answer. It is slower, but better at hard problems.
- 8Vibe codingVibe coding is making software by describing what you want to an AI, trying what it builds, and asking for changes, without reading the code yourself.
- 9Human in the loopHuman in the loop means a person checks, approves or can stop what an AI does, instead of letting it act completely on its own.
How AI makes pictures, voice and video
The ideas behind image, video and voice tools. 9 words, in order.
- 1Generative AIGenerative AI is AI that creates new things, like text, images, music or code, by learning the patterns in huge numbers of examples and producing fresh ones.
- 2Diffusion modelA diffusion model makes images by starting from pure random noise and removing a little of it, step by step, until a picture appears that matches your words.
- 3Text-to-imageText-to-image AI turns a sentence you type into a brand new picture that did not exist before.
- 4Image-to-imageImage-to-image AI takes a picture you give it, plus a few words, and makes a new picture that keeps the layout of yours.
- 5InpaintingInpainting is AI that fills in a part of a picture you mark, so it matches everything around it: removing a stranger, or adding something new.
- 6Text-to-videoText-to-video AI turns a sentence you type into a short, brand new video clip, frame by frame, with everything moving consistently.
- 7Text-to-speechText-to-speech is AI that reads written words aloud in a voice that sounds human.
- 8DeepfakeA deepfake is a video, photo or voice clip made or changed with AI so that a real person seems to do or say something they never did.
- 9AI detectorAn AI detector is a tool that guesses whether text, an image or audio was made by AI. It gives a probability, not proof, and it can be wrong.
Is AI safe? The key words
The words people use when they argue about AI risk. 9 words, in order.
- 1AI safetyAI safety is the work of making sure AI systems do not cause harm, whether by mistake, through misuse, or as they grow more capable.
- 2AlignmentAlignment is the work of making an AI pursue what people actually intend, not just the literal goal or score it was given.
- 3AI biasAI bias is when an AI system treats some groups of people unfairly, usually because it learned from data that was already skewed.
- 4JailbreakA jailbreak is a trick that gets a chatbot to break its own safety rules, usually by disguising a request it would normally refuse.
- 5Prompt injectionPrompt injection is when text an AI reads, like an email or web page, contains hidden instructions that hijack what the AI does.
- 6GuardrailsGuardrails are the checks and rules wrapped around an AI model that stop it from receiving or giving harmful, off-topic or unsafe content.
- 7Red teamingRed teaming means deliberately attacking an AI system before release, trying to make it misbehave, so its flaws can be found and fixed.
- 8Existential riskExistential risk is the worry that future AI, far more capable than today's, could cause a catastrophe that ends or permanently cripples humanity.
- 9AI regulationAI regulation is the laws and rules governments set for how AI can be built and used, from outright bans to labelling AI content.