[ADCES]Azure OpenAI’s GPT-4V(ision) and DALL-E 3 & Testing at scale
Presentation 1: Vision Meets Fashion: Crafting Watch Aesthetics with Azure OpenAI’s GPT-4V(ision) and DALL-E 3
Description:
In this increasingly digitized era, the fusion of artificial intelligence and design is reshaping creative industries. This talk provides a practical exploration of this synergy, with a focus on enhancing watch designs (or just picking the “right” watch strap) using advanced AI technology.
Participants will be guided through a hands-on demonstration of analyzing a watch face with Azure OpenAI’s GPT-4 Vision, for identifying design attributes. Leveraging these insights, attendees will learn how to generate suitable strap ideas and designs that complement the watch’s aesthetics using the same AI.
The session will pivot towards actualizing these designs with DALL-E 3, demonstrating the model’s capability to render realistic images of watches with the new straps. Attendees will observe the Python code in action, gaining insights into how these powerful models can be controlled and utilized for design prototyping.
This session is designed for those interested in the practical application of AI in design, as well as developers and hobbyists eager to understand how to integrate such models into their Python projects. Attendees will gain firsthand experience in using state-of-the-art AI to bridge the gap between conceptualization and visualization in the design process, leaving the talk with actionable skills and knowledge.
Presenter : Vlad Iliescu, https://vladiliescu.net/
Presentation 2: Testing at scale – how to test when you go globally with a fleet of thousands of machines
Description: There are multiple types of tests we’d like to run – unit tests, end-to-end tests, manual tests, A/B tests. How should we organize them so they are fast and reliable?
What to do if we need to handle GDPR-protected data? How to run those tests when we have thousands of machines handling the traffic? How to rollback?
In this talk we’ll see how to build a real-life end-to-end testing pipeline used in biggest companies in the world. We’ll start with unit tests running locally in milliseconds, go through correctness tests, regression tests, performance tests, security tests, and finally end with A/B tests proving that our code is not only correct but also provides better experience for the customers. All of that based on experience with desktop, mobile, service, and machine learning domains at biggest companies.
Presenter : Adam Furmanek, https://blog.adamfurmanek.pl/
https://www.meetup.com/bucharest-a-d-c-e-s-meetup/events/297158675/