Loading video...

Video Failed to Load

Go Home

Google Gemini 2.0 realtime AI is insane. Watch me turn it into a live code tutor just by sharing my screen and talking to it. We’re living in future. I’m speechless.

624,751 views • 1 year ago •via X (Twitter)

11 Comments

Mckay Wrigley's profile picture
Mckay Wrigley1 year ago

This is why the “Is it AGI???” conversations are so silly. 90% of people would’ve said this was AGI if you showed this to them 2 years ago. The goalposts will keep moving… And it won’t matter. Because it’s already magic.

Mckay Wrigley's profile picture
Mckay Wrigley1 year ago

Now I’m REALLY hoping one of OpenAI’s 12 days is AVM with video. Give me alllll the realtime products you can feed me. Feeling so lucky to be living in a genuine technological revolution. Imagine what this can do for education alone! So happy rn 🥲

Mckay Wrigley's profile picture
Mckay Wrigley1 year ago

Predictably, OpenAI has launched their version the next day. The race is on and I’m here for it.

Mckay Wrigley's profile picture
Mckay Wrigley1 year ago

Prompt engineering 101.

Pulze.ai's profile picture
Pulze.ai1 year ago

Seamlessly switch between AI models like ChatGPT and Gemini. Why limit yourself? Explore the power of choice with #AI #Flexibility #AdvancedFeatures

kwindla's profile picture
kwindla1 year ago

I had early access to this and have been building APIs/SDKs for the realtime/multimodal things that Google launched today. The voices are great and the video and spatial reasoning are super-impressive. If you want to build your own app that has conversational, multimodal features, there are Open Source client SDKs with Gemini 2.0 multimodal support. Web, React, Android, iOS, and C++ — part of the @pipecat_ai ecosystem and officially blessed by Google. These SDKs have device management, echo cancellation, and noise reduction built in. Plus lots of other features including hooks for function calling and tool use. They support both WebSocket and WebRTC network transport. Here’s a full-featured starter kit built on the React SDK — a chat application with: - a voice-to-voice WebSocket mode, - an HTTP mode for text and image input, and - a WebRTC mode with text, voice, camera video and screenshare video.

Mckay Wrigley's profile picture
Mckay Wrigley1 year ago

Excited to see what you and others have built 👀

Dan Mac's profile picture
Dan Mac1 year ago

Google beat OpenAI to the punch with this one This is a ridiculously powerful capability You’re right that we have arrived in the future

Mckay Wrigley's profile picture
Mckay Wrigley1 year ago

Hoping for AVM + video as one of the remaining 12 days

Shawn Chauhan's profile picture
Shawn Chauhan1 year ago

Live coding assistance in real-time is going to revolutionize how we learn and work with code.

Mckay Wrigley's profile picture
Mckay Wrigley1 year ago

Education revolution and nothing short of it

Related Videos