What large language model means
The adjective “large” describes scale, not quality: the volume of text used in training and the number of parameters adjusted during that process. Adjusting parameters from data is the core idea of machine learning, and an LLM is one special case of it. A parameter is a numeric value inside the network. The network in question is a neural network, and most of its parameters are the weights of the connections between its nodes. Its count gives no basis for deducing how useful the system will be on a specific task, and vendors now hardly ever publish it. Because that network has many layers, an LLM is also a deep learning model.
Three things that get mixed up in everyday conversation are worth separating. The model is the parameter file plus the code that runs it. The assistant is the product around it: interface, fixed instructions, conversation history, tools. And AI search is a third layer, where the assistant queries a web index before composing an answer. The same question can come out differently at all three. An assistant you work with by conversing is a chatbot, though not every chatbot runs on an LLM: rule-based ones follow predefined responses. An LLM is the form of generative AI that produces text; other generative models create images, audio or video.
The other important distinction is temporal. A model is trained on texts up to a cutoff date. Some vendors publish two dates: the one for the training material and an earlier one up to which they consider the information reliable. After that point the parameters hold nothing about your new office, your price change or your rebranding. A system with live retrieval avoids part of the problem because it queries sources at the moment of answering, and it therefore reacts to new facts differently than an isolated model. If those sources are stored as embeddings, the search can run in a vector database.
