Vlad Iliescu
Microsoft MVP on AI
Iaşi, Romania
Software architect, manager, and Microsoft Most Valuable Professional on AI, with more years of professional experience than I’d like to remember. Apart from developing software and playing the ukulele, I enjoy exploring the capabilities of AI, its strengths and weaknesses, and sharing my knowledge and experience with others.
I blog about life, the universe and software development at https://vladiliescu.net
Links
Area of Expertise
Topics
Real-Time Machine Learning with Azure ML Online Endpoints
Are you using the most appropriate machine learning approach for your use case?
Some machine learning tasks can be completed in real-time, while others require batch processing. This talk will compare and contrast the pros and cons of both approaches, so that you can assess the differences between batch and real-time inference. You will also learn how to do real-time ML using the new Azure ML Endpoints, going from deploying a simple ML model to iterating the changes you need to make in order to get a production-ready service.
By the end of this talk, you will be able to determine whether your projects need batch or real-time ML, and know how to deploy a real-time machine learning model using Azure ML Endpoints.
Future-Proof Development with GitHub Codespaces, Copilot, and Azure OpenAI
In this talk, we will delve into the world of cutting-edge software development tools and explore how GitHub Codespaces, GitHub Copilot, and GPT-4 can work together to reshape the way developers create, test, and maintain code, optimizing their efficiency and streamlining collaboration.
We’ll start by exploring GitHub Codespaces, which lets developers quickly create tailored, cloud-based development environments, eliminating the need for extensive local setup, and ensuring a consistent workspace across teams. We’ll then take a closer look at GitHub Copilot, an AI-powered programming assistant that uses OpenAI’s GPT-3 to suggest contextually relevant code suggestions, significantly reducing the time spent on writing boilerplate code and debugging.
Finally, we’ll dive into the possibilities and potential impact of GPT-4, the latest iteration of OpenAI’s language model. Here, we will discuss advancements such as the ability to use twice as much contextual information, but also its improved reasoning and code generation capabilities.
Throughout the talk, we will explore real-world examples via Azure OpenAI and provide insight into the integration of these tools, ensuring that you leave equipped with valuable knowledge on how to future-proof your development practices and stay ahead of the curve.
Poor Man's BingChat - Building an Internet-connected Search Assistant from scratch*
Have you seen BingChat's/ChatGPT's ability to reason about current events, even though the underlying models have been trained with data only up to September 2021? Have you wondered how it works behind the scenes, what did they do to make it work?
During this talk Vlad will be talking about the ways to achieve this, including possible options such as fine-tuning and retrieval augmented generation, but also limitations such as models' slow inference times and limited context window sizes. He will demo a an app that can talk about current events, and you will learn how to build your own, from scratch*.
*from scratch = with nothing but Python, pandas, and the Azure OpenAI APIs
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top