Want to learn more about AI tools? Join the community https://mrc.fm/cmc

First up, Google's new Gemini 2.0 multimodal live API is a incredible, allowing you to talk, show, and share your screen with AI. Then, I'll show you how I used Gemini to help create an iOS widget in Xcode and even translate Vietnamese street audio! Finally, we'll dive into a deep comparison of different AI language models (ChatGPT, Claude, and Gemini Flash) to see which is the best for summarization and long-form content. Plus, a bonus look at my AI Advent Calendar content in the community for December!

Google Gemini 2.0 API https://mrc.fm/aistudio
Cursor (code editor) https://mrc.fm/cursor
Xcode https://mrc.fm/xcode
HeyGen (avatar creation) https://mrc.fm/aivideotranslator

0:00 Intro to Gemini 2.0 Live API
0:24 Talking to Gemini (accent & emotion analysis)
0:40 Showing Gemini (dragon fruit recognition)
0:52 Screen Sharing with Gemini (Minecraft gameplay)
1:32 Gemini Helps with Xcode and iOSWidget Creation
3:34 Gemini Translates Vietnamese Street Audio
4:08 The Future of AI Agents
4:47 AI Models Comparison
8:14 Transcript Analysis Demo
11:20 Why I Switched to Gemini Flash for Content Summaries
12:07 Outro