Attention MechanismThe core operation inside a transformer model that lets it weigh how much each word relates to every other word.3 Apr 2026architecturemodelsconcept
Context WindowThe maximum amount of text a model can hold in its working memory at once.3 Apr 2026architecturemodelsconcept
EmbeddingsA way of representing text as numbers so a computer can work with meaning, not just characters.3 Apr 2026vectorsconcepttechnique
Foundation ModelA large model trained on massive data that can be adapted for many tasks.3 Apr 2026modelsconcepttraining
HallucinationWhen a model generates confident-sounding text that is factually wrong.3 Apr 2026safetyconceptmodels
In-Context LearningTeaching a model how to behave by giving examples in the prompt itself, without changing any weights.3 Apr 2026promptingtechniqueconcept
Knowledge GraphA structured representation of facts as entities and relationships.3 Apr 2026architectureragconcept
Large Language Model (LLM)A neural network trained to predict and generate text at scale.3 Apr 2026modelsconceptarchitecture
LatencyHow long it takes from sending a prompt to receiving the first token.3 Apr 2026performanceinfrastructureconcept
Multi-ModalA model that handles more than one type of input or output, like text plus images.3 Apr 2026modelsarchitectureconcept
Prompt EngineeringThe practice of crafting inputs to get better outputs from a model.3 Apr 2026promptingtechniqueconcept
System PromptInstructions given to a model before the user's message, usually hidden from the user.3 Apr 2026promptingconceptagents
TemperatureA parameter that controls how random model outputs are.3 Apr 2026conceptpromptingtechnique
TokenisationThe process of splitting text into tokens, the chunks a model actually processes.3 Apr 2026conceptmodelsarchitecture
Zero-ShotAsking a model to do something without any examples in the prompt.3 Apr 2026promptingtechniqueconcept