GPT-4 Vision: Understanding Images
While 2024 is the year of agents, multimodal LLMs are definitely on the horizon!
In this event, we will explore one of OpenAI's latest releases: the GPT-4 Vision API. This new model opens up exciting possibilities for building, shipping, and sharing LLM applications!
Since the capability was recently made generally available and can only be accessed via API as a developer, we thought we’d give it a first look!
What’s the big idea?
GPT-4 Turbo with Vision can answer questions about images
In this event, we focus on building and deploying an LLM application that allows us to upload multiple images and ask questions about them!
During the event, we’ll deep dive into everything you need to know about the GPT-4 Vision API, including:
🖼️ How to pass images to the API; how it deals with multiple images.
🤔 What is the model good at, and what are its current limitations?
💵 The costs associated with processing low and high-fidelity images.
This is a very early release of the tool, and we are curious to give it a first look!
Join us live to build with the latest with us and get your questions answered!
📚 You’ll learn:
To build an end-to-end application for image question-answering.
How OpenAI is setting the tone with this first general multimodal model release.
What we expect on the horizon soon in the space!
If you are not yet familiar with the foundational concepts and code that we’ll leverage, we recommend checking out some of our previous content, including:
Speakers:
Dr. Greg” Loughnane is the Co-Founder & CEO of AI Makerspace, where he is an instructor for their AI Engineering Bootcamp. Since 2021 he has built and led industry-leading Machine Learning education programs. Previously, he worked as an AI product manager, a university professor teaching AI, an AI consultant and startup advisor, and an ML researcher. He loves trail running and is based in Dayton, Ohio.
Chris “The Wiz” Alexiuk is the Co-Founder & CTO at AI Makerspace, where he is an instructor for their AI Engineering Bootcamp. During the day, he is also a Developer Advocate at NVIDIA. Previously, he was a Founding Machine Learning Engineer, Data Scientist, and ML curriculum developer and instructor. He’s a YouTube content creator YouTube who’s motto is “Build, build, build!” He loves Dungeons & Dragons and is based in Toronto, Canada.
Follow AI Makerspace on LinkedIn and YouTube to stay updated about workshops, new courses, and corporate training opportunities.