Reference
Glossary
Plain-language definitions of common AI terms, for readers and answer engines.
- AI agent
- A system that uses a model to plan and carry out multi-step tasks, often by calling tools.
- Alignment
- The effort to make AI systems behave according to human intentions and values.
- Attention
- A mechanism that lets a model weigh which parts of the input matter most for each output.
- Chain-of-thought
- A prompting or training approach in which a model works through intermediate reasoning steps before answering.
- Context window
- The maximum amount of text, measured in tokens, that a model can consider at once.
- Diffusion model
- A generative model that produces images or other media by iteratively removing noise from a random signal.
- Distillation
- Training a smaller model to imitate a larger one, keeping much of its capability at lower cost.
- Embedding
- A numerical vector representation of text or other data that captures aspects of its meaning.
- Few-shot learning
- Guiding a model with a handful of examples in the prompt instead of retraining it.
- Fine-tuning
- Further training of a pretrained model on a narrower dataset to adapt it to a specific task or domain.
- Foundation model
- A large model trained on broad data that can be adapted to many downstream tasks.
- Hallucination
- When a model generates text that is fluent but factually incorrect or unsupported.
- Inference
- Running a trained model to produce outputs, as opposed to training it.
- Large language model (LLM)
- A neural network trained on large amounts of text to predict and generate language.
- Mixture of experts (MoE)
- A model architecture that routes each input to a subset of specialized subnetworks to save computation.
- Multimodal
- Describing a model that can process or generate more than one type of data, such as text and images.
- Open weights
- Model parameters that are publicly released so others can run or adapt the model.
- Prompt
- The text or other input given to a model to instruct or elicit a response.
- Prompt engineering
- The practice of designing and refining prompts to get more reliable or useful model outputs.
- Quantization
- Reducing the numerical precision of a model's weights so it runs faster and uses less memory.
- Reasoning model
- A model trained to spend extra computation thinking through a problem step by step before answering.
- Red-teaming
- Deliberately probing an AI system for harmful, unsafe, or unintended behavior before and after release.
- Reinforcement learning from human feedback (RLHF)
- A training method that uses human preference judgments to steer a model toward more helpful behavior.
- Retrieval-augmented generation (RAG)
- A technique that retrieves relevant documents and supplies them to a model to ground its responses.
- Speech recognition (ASR)
- Automatically converting spoken audio into written text.
- System prompt
- A hidden instruction that sets a model's role, rules, and behavior before user input.
- Temperature
- A sampling setting that controls how random or predictable a model's outputs are.
- Text-to-image
- Generating images from written descriptions using a generative model.
- Token
- A unit of text, such as a word or word-piece, that a language model reads and generates.
- Tool use (function calling)
- A model's ability to call external functions, APIs, or apps to complete a task.
- Transformer
- A neural network architecture based on attention that underlies most modern language and multimodal models.
- Vector database
- A database that stores embeddings and finds items by similarity, often used for retrieval in AI apps.