Large Language Models
How LLMs are built, trained and used in production.
AI Hallucination
A hallucination is an LLM output that is fluent and plausible but factually incorrect or unsupported by any reliable source.
AI Tokens
A token is the unit of text an LLM processes — typically 3-4 characters or roughly three-quarters of an English word. Prompts, replies and pricing are all measured in tokens.
Context Window
The context window is the token budget an LLM can read and write within a single request, covering the prompt, retrieved data, previous turns and the response itself.
Fine-tuning
Fine-tuning is additional training applied to a pretrained model on curated examples so the model specialises in a task, tone, format or domain.
Foundation Model
A foundation model is a large-scale, general-purpose model pretrained on broad data and designed to be adapted to many downstream tasks via prompting, fine-tuning or tool use.
Generative Engine Optimisation
GEO is the set of editorial and technical practices that increase the likelihood a page is retrieved, quoted or cited by generative AI systems when they answer a user's question.
Inference
Inference is the stage at which a trained machine learning model processes new input and produces an output, distinct from training, which is the earlier process of building the model's parameters from data.
LLM
An LLM is a neural network trained on very large text datasets to predict the next token in a sequence, which enables general-purpose language understanding and generation.
Reinforcement Learning
Reinforcement learning is a machine learning paradigm in which an agent learns to make decisions by receiving reward signals for its actions in an environment.
SLM
An SLM is a language model built with a smaller parameter count and training footprint than large flagship models, optimised for efficiency, low latency and deployment on limited hardware rather than maximum general capability.
Temperature
Temperature is a numerical parameter, typically between 0 and 2, that adjusts how a language model samples from its predicted probabilities for the next word, controlling the balance between predictability and variation in its output.
Transformer Model
A transformer is a neural network architecture built around self-attention, which enables efficient modelling of long-range dependencies in sequences.
Vision Model
A vision model is a neural network trained to process and interpret visual data, such as photographs, screenshots or diagrams, often paired with a language model so it can describe or reason about that visual content in text.