Exploring Gemini 1.5 Pro: Large Context Window and Multimodal Capabilities
Sam Witteveen via YouTube
Overview
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore the capabilities of Google's latest AI model, Gemini 1.5, in this informative video demonstration. Dive into the expanded 1 million token context window and witness its impressive performance across various tasks. Learn about the model's ability to query documents, write code, and analyze video and image content. Compare Gemini 1.5's context window to other leading AI models and gain insights into its potential applications. Watch as the presenter showcases real-time examples, including document analysis, code generation, and multimodal understanding of video and image inputs. Discover how this advanced AI technology pushes the boundaries of natural language processing and multimodal comprehension.
Syllabus
Intro
Google Gemini 1.5 Pro Blog
Context Window Comparison
Demo
Demo: Querying Documents
Demo: Writing some code
Demo: Using Video Sample 01
Demo: Using Vide Sample 02
Demo: Using Video + Images Sample
Taught by
Sam Witteveen