Book 08
AI & Machine Learning
Essential vocabulary for machine learning, large language models and AI-powered applications.
Contents
- 01Agent2Agent Protocol1The Agent2Agent (A2A) protocol is an open standard that lets AI agents built by different teams or vendors find each other, hand off tasks and share results.
- 02AGIArtificial General Intelligence2AGI (artificial general intelligence) is a hypothetical AI system that could learn and do any intellectual task a person can, not just a narrow set of tasks.
- 03AI Agent3An AI agent is a system that uses an LLM to plan and carry out multi-step tasks by deciding which tools to call, observing the results, and acting again.
- 04AI Alignment4AI alignment is the field of making AI systems pursue the goals and values their designers intend, so they behave helpfully, honestly, and safely.
- 05AI Coding Agent5An AI coding agent is an AI system that takes a programming task, explores the code, edits files and runs commands in a loop until the task is done.
- 06Artificial IntelligenceAI6Artificial intelligence (AI) is the field of computer science that builds systems able to do tasks that normally require human intelligence.
- 07Attention Mechanism7The attention mechanism is a neural network technique that lets a model decide, for each token, which other parts of the input matter most and focus on them.
- 08Backpropagation8Backpropagation is the algorithm that trains neural networks by measuring how much each weight added to the error and nudging every weight to reduce it.
- 09Chain-of-Thought Prompting9Chain-of-thought prompting is a technique that asks an LLM to reason through intermediate steps before its final answer, improving accuracy on complex tasks.
- 10Chatbot10A chatbot is a program that converses with people in text or speech, answering questions or helping with tasks, using scripted rules or a language model.
- 11ChatGPT11ChatGPT is OpenAI's AI assistant: a chat app built on its GPT models that answers questions, writes, analyzes files, searches the web and creates images.
- 12Chunking12Chunking splits long documents into smaller passages before they are embedded and stored, so a RAG system can find and pass on just the relevant parts.
- 13Classification13Classification is the kind of supervised learning where a model predicts a category for each input, such as spam or not spam, or which digit a photo shows.
- 14Claude14Claude is Anthropic's AI assistant and the family of language models behind it, used through chat apps, the Claude API and tools such as Claude Code.
- 15Claude Code15Claude Code is Anthropic's AI coding agent: it reads your codebase, edits files, runs commands and works with git in a terminal, IDE, desktop app or browser.
- 16Computer Vision16Computer vision is the field of AI that enables computers to interpret images and video, such as recognizing objects, reading text, or detecting faces.
- 17Context Engineering17Context engineering is the practice of choosing what an LLM sees on each call (instructions, documents, tool results, history) so it can do the task reliably.
- 18Context Window18A context window is the maximum amount of text, measured in tokens, that an LLM can consider at once, including the prompt, conversation history, and its reply.
- 19Cosine Similarity19Cosine similarity measures how alike two vectors are by the angle between them, from -1 to 1; it is the usual way to compare embeddings in semantic search.
- 20Cursor20Cursor is an AI code editor built on VS Code, with AI autocomplete, a chat and coding agents that edit across files and can use models from several AI labs.
- 21Deep Learning21Deep learning is a subset of machine learning that uses neural networks with many layers to learn complex patterns from raw data such as images and text.
- 22Diffusion Model22A diffusion model is a generative AI model that makes images, audio, or video by starting from random noise and removing it step by step until content appears.
- 23Embedding23An embedding is a list of numbers, called a vector, that represents the meaning of text, images, or other data so that similar items end up close together.
- 24EvalsEvaluations24Evals are tests for AI systems: a set of inputs with expected results or grading rules, run after every change to measure how well a model or prompt performs.
- 25Few-Shot Learning25Few-shot learning is getting an AI model to perform a task from just a handful of examples, most often by placing a few sample inputs and outputs in the prompt.
- 26Fine-tuning26Fine-tuning is the process of taking a pretrained machine learning model and training it further on a smaller, specific dataset to adapt it to one task.
- 27Gemini CLI27Gemini CLI is Google's open-source AI agent for the terminal, built on Gemini models; for most individual users, Antigravity CLI replaced it in June 2026.
- 28Generative AI28Generative AI is artificial intelligence that creates new content, such as text, images, code, or audio, based on patterns learned from existing data.
- 29GitHub Copilot29GitHub Copilot is GitHub's AI coding assistant: it suggests code as you type, answers questions in chat and, as an agent, turns issues into pull requests.
- 30GPTGenerative Pre-trained Transformer30GPT (Generative Pre-trained Transformer) is OpenAI's family of large language models that generate text by predicting the next token.
- 31Gradient Descent31Gradient descent is an optimization algorithm that trains machine learning models by repeatedly nudging their parameters in the direction that reduces error.
- 32GuardrailsAI Guardrails32Guardrails are checks placed around an AI model that screen what goes in and what comes out, blocking unsafe, off-topic or malformed requests and answers.
- 33Hallucination33A hallucination is when an AI model, such as an LLM, confidently produces information that sounds plausible but is false, invented, or unsupported by sources.
- 34Inference34Inference is the stage where a trained machine learning model is used to make predictions or generate output from new data, without changing what it learned.
- 35LLMLarge Language Model35An LLM is a machine learning model trained on huge amounts of text that generates language by repeatedly predicting the next most likely piece of text.
- 36LLM Evaluation36LLM evaluation, or evals, is measuring how well a language model or an AI feature performs on a fixed set of test cases, so that changes can be compared.
- 37LoRALow-Rank Adaptation37LoRA is a cheap way to fine-tune a large model: its weights stay frozen and only small added matrices are trained, so a new skill fits in a few megabytes.
- 38Machine Learning38Machine learning is a branch of artificial intelligence in which computers learn patterns from data to make predictions instead of following hand-written rules.
- 39Mixture of ExpertsMoE39A mixture of experts (MoE) is a neural network design that sends each input to only a few of many small experts, so a huge model costs far less to run.
- 40Model Context Protocol40The Model Context Protocol is an open standard that defines how AI applications connect to external tools, data sources, and prompts through a shared interface.
- 41Model Parameters41Model parameters are the internal numbers, such as weights and biases, that a machine learning model learns in training and uses to turn inputs into outputs.
- 42Multimodal AI42Multimodal AI is artificial intelligence that can understand or generate several types of data, such as text, images, audio, and video, in a single model.
- 43Natural Language Processing43Natural language processing is the field of AI that teaches computers to read, understand, and generate human language in the form of text or speech.
- 44Neural Network44A neural network is a machine learning model made of layers of connected artificial neurons that learn patterns from data by adjusting numeric weights.
- 45OpenAI Codex45OpenAI Codex is OpenAI's AI coding agent: it writes, edits and reviews code from a command line, an IDE extension or ChatGPT, on your computer or in the cloud.
- 46Overfitting46Overfitting happens when a machine learning model learns its training data so closely, including its noise, that it performs poorly on new, unseen data.
- 47Prompt47A prompt is the input text or instructions you give an AI model, such as an LLM, to tell it what task to perform and what kind of answer you want.
- 48Prompt Engineering48Prompt engineering is the practice of designing, testing, and refining the instructions given to an AI model so it produces accurate, consistent, useful output.
- 49Quantization49Quantization is a technique that shrinks an AI model by storing its parameters in fewer bits, such as 8 or 4 instead of 16, so inference is faster and cheaper.
- 50RAGRetrieval-Augmented Generation50RAG is a technique that makes an LLM answer using relevant documents retrieved at question time, so its responses are grounded in current, specific data.
- 51Reasoning Model51A reasoning model is a language model trained to work through a problem step by step before answering, spending extra computation to do better on hard tasks.
- 52Regression52Regression is the kind of supervised learning where a model predicts a number, such as a price, a temperature or a delivery time, from the input it is given.
- 53Reinforcement Learning53Reinforcement learning is a type of machine learning in which an agent learns to make decisions by trial and error, earning rewards for good actions.
- 54RLHFReinforcement Learning from Human Feedback54RLHF (reinforcement learning from human feedback) trains a language model to be more helpful and safe using people's judgments of which answers are better.
- 55Semantic Search55Semantic search is a search technique that finds results by meaning rather than exact keywords, usually by comparing embeddings of the query and the documents.
- 56Small Language Model56A small language model (SLM) is a language model with far fewer parameters than the largest LLMs, cheap and fast enough to run on one GPU, a laptop or a phone.
- 57Supervised Learning57Supervised learning is machine learning where a model learns from labeled examples, inputs paired with correct answers, to predict outputs for new data.
- 58System Prompt58A system prompt is the instructions an app gives a language model before the conversation starts, setting its role, rules, tone and what it should know.
- 59Temperature59Temperature is a setting that controls how random an LLM's output is, from focused and predictable at low values to more varied and creative at high values.
- 60Token60A token is the basic unit of text that an LLM reads and generates, usually a whole word, part of a word, or a punctuation mark, mapped to a numeric ID.
- 61Tool Calling61Tool calling is an LLM feature in which the model asks the application to run a specific function with structured arguments, then uses the result in its answer.
- 62TPUTensor Processing Unit62A TPU (Tensor Processing Unit) is Google's custom chip for the matrix math of neural networks, used to train and run AI models, mainly on Google Cloud.
- 63Training Data63Training data is the set of examples a machine learning model learns from, and its quality, size, and coverage largely determine how well the model performs.
- 64Transformer64A transformer is a neural network architecture that uses attention to weigh how each token in a sequence relates to the others, and it powers most modern LLMs.
- 65Underfitting65Underfitting happens when a machine learning model is too simple or too briefly trained to learn the real pattern, so it does poorly even on its training data.
- 66Unsupervised Learning66Unsupervised learning is machine learning in which a model finds patterns, groups, or structure in unlabeled data, without being given the correct answers.
- 67Vector Database67A vector database is a database designed to store embeddings and quickly find the vectors most similar to a query, which powers semantic search and RAG.
- 68Vibe Coding68Vibe coding is building software by describing what you want to an AI and accepting the code it writes, mostly judging the result by whether it seems to work.