Gemini 2.0 Flash: An outstanding multi-modal LLM with a sci-fi streaming mode
Simon Willisonsimonwillison.net
Gemini 2.0 Flash: An outstanding multi-modal LLM with a sci-fi streaming mode
Wrote up my initial impressions of the new Google Gemini 2.0 Flash model - it's really good, and the streaming mode (where you can stream video and audio to it and get audio streamed right back) is pure science-fiction https://t.co/23yuotBTm7
Simon Willisonx.com
Introducing the new Realtime Multimodal API, powered by Gemini 2.0 Flash!
You can stream audio, video, and text in, while dynamic tool calls happen in the background (Search, code execution, & function calling). Truly a wild experience, try it right now in AI Studio 🤯 https://t.co/SnMc9N4lI0
Google raised the bar with Realtime AI.
It enables AI to see your screen and chat with you in real-time, and users are discovering incredible use cases.
10 wild examples: https://t.co/lwIQ8a8vba