ChatGPT, GPT-4, and similar large models are receiving a high amount of attention across industries. Almost weekly new ways to use those models are unveiled and integration in different products and services announced.

This ranges from generating creative text, doing translations, correcting grammar, answering questions, classifying content, and in some cases even tools to transform natural language into code in a variety of development languages. It is not a question if those models will be used, but how much they will change the way we work. They are already integrated in many Microsoft offerings including M365 and Power Platform.

We will start with describing for non-scientist audiences how those models were built.

We then move on to discuss a few of the most relevant models with a focus of showcasing what you can use them for.

Since this field is innovating frequently, the precise models being featured are subject to change but will at least have the capabilities of OpenAI's ChatGPT and GPT-4 to the degree it is available.

OpenAI Codex and GitHub CoPilot will also be demonstrated with their ability to assist in writing code.

This session will feature a high number of demos.

Finally, the session will cover the issue of some of the risks such as biases that are present in those models.

After this session you will have a better understanding about Large Language Models and their hands-on application beyond what major vendors will tell you.