{"id":362,"date":"2025-10-10T09:54:10","date_gmt":"2025-10-10T08:54:10","guid":{"rendered":"https:\/\/generic.wordpress.soton.ac.uk\/genai\/?p=362"},"modified":"2025-12-17T08:09:25","modified_gmt":"2025-12-17T08:09:25","slug":"how-do-genai-and-large-language-models-llms-work","status":"publish","type":"post","link":"https:\/\/generic.wordpress.soton.ac.uk\/genai\/2025\/10\/10\/how-do-genai-and-large-language-models-llms-work\/","title":{"rendered":"How do GenAI and Large Language Models (LLMs) work?\u00a0"},"content":{"rendered":"\n
\"Lots<\/figure>\n\n\n\n

What is GenAI and a LLM? <\/h2>\n\n\n\n

Generative Artificial Intelligence (GenAI) and Large Language Models (LLMs) are types of machine learning models trained on large datasets. LLMs are typically trained on text, while GenAI can include other media like audio, images, and video. These models are developed by companies such as Microsoft, Google, and Meta using vast amounts of data (e.g. web content) and powerful computing resources. Training a GenAI model from scratch can cost millions of pounds. <\/p>\n\n\n\n

Originally, LLMs referred only to text-based models, but now they can handle multiple media types. As a result, the terms GenAI and LLM are often used interchangeably. <\/p>\n\n\n\n

You can access these models through a web browser (for human use) or via an API (for computer systems). This guide focuses on browser-based access. <\/p>\n\n\n\n

The initial training of an LLM is called pre-training<\/strong>. Some companies, like Meta, release their models as open source. This allows others to download and adapt them for specific uses\u2014such as summarising educational texts or identifying mental health risks. This latter process is called\u202ffine-tuning. <\/strong>All models go through a process of \u2018fine-tuning\u2019 to ensure that they are giving the best responses to instructions. <\/p>\n\n\n\n

All GenAI and LLMs are built using a type of model called a\u202fTransformer<\/strong>. For more technical detail, see Huggingface\u2019s guide<\/a>: <\/p>\n\n\n\n

<\/p>\n\n\n\n

How do I use GenAI and LLMs? <\/h2>\n\n\n\n

To use a GenAI or LLM, you provide an input\u2014called a\u202fprompt (instruction)<\/strong>\u2014which can be text, audio, image, or video. You can do this through a website or, with more technical effort, via an API. <\/p>\n\n\n\n

The model processes your prompt using its pre-trained Transformer layers and generates a response\u2014such as text, an image, or another media output\u2014based on what it has learned. It does this by making a prediction of the most likely response based on its training data. <\/p>\n\n\n\n

How well you \u2018talk\u2019 to AI (frame your question and subsequent instructions) has an influence on the kind of information returned to you. In this respect, it can be a bit like working with a human colleague that you exchange ideas back and forth with. <\/p>\n\n\n\n

Types of prompting techniques <\/strong><\/p>\n\n\n\n