I use CoPilot to superpower my coding skills, my mom uses ChatGPT to write poems and my 9-year old nephew uses DALL•E 2 to generate images for a dinosaur adventure he's writing. Recent headlines have been dominated by GPT-3.5 (ChatGPT), Codex (GitHub CoPilot), and DALL•E 2, which have a wide range of use cases, including writing assistance, code generation, and image generation. With Azure OpenAI Service, you can use these powerful models as-is, or, customize them to suit your needs for your specific use case all with managed APIs.

In this talk, we will guide you through some fundamentals of using OpenAI in the Azure cloud starting with provisioning resources to selecting a model (what exactly is a davinci?). We will then delve into using completions to generate or manipulate text (ChatGPT anyone?), and we will also explore the many tasks that can be accomplished with Codex (a.k.a CoPilot), such as turning comments into code or completing your next line of code. Additionally, we will walk you through using the Azure OpenAI embeddings API to perform document search, where you can query a knowledge base to find the most relevant documents.

Also, no discussion of AI should be considered complete without discussing the ethics of AI. We will briefly touch on this aspect deriving from Microsoft's Responsible AI approach to ensure that these AI models are only being used for their intended purposes.