# LLM Development {% hint style="info" %} This page is currently in draft {% endhint %} Large Language Models (LLM) are familiar from notable implementations of generative AI such as Open AI's Chat GDP. LLMs need to be fine tuned to provide more specfic contextual responses. This is typically done with Prompts. SinguarityNet's Ambassador programme is made up of workgroups. Since 2022 the Archive Workgroup has been gathering record keeping data on the activities of workgroups in the Ambassador program. The Archive workgroup aims to use generative models for - * **Self-taught learning (didactic learning) materials** - to promote learning by doing in the Archive Workgroup * **Data Analysis** - to supplement knowledge management and data mining of the intellectual property of the Ambassdor Program. * **Enhanced Record keeping** - supporting decentralised governance through enhanced analytic data on decision-making * **Augmentation** - that applies a local context and enforces ethical standards. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://snet-ambassadors.gitbook.io/singularitynet-archive/development/llm-development.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.