In this video, I look at the latest release from Google for Gemini 2.0 Flash and we look at how it can do various multimodal tasks and how it's improved its over its previous versions
Check out Matt Marshall and I discussing the Gemini 2.0 launch and other news of the week: • Gemini 2.0: A New Era of Real-World AI
For more tutorials on using LLMs and building agents, check out my Patreon
Patreon: / samwitteveen
Twitter: / sam_witteveen
Gemini 2.0 Blog: https://developers.googleblog.com/en/...
Google DeepMind: https://deepmind.google/technologies/...
🕵️ Interested in building LLM Agents? Fill out the form below
Building LLM Agents Form: https://drp.li/dIMes
👨💻Github:
https://github.com/samwit/langchain-t... (updated)
https://github.com/samwit/llm-tutorials
⏱️Time Stamps:
00:00 Intro
02:23 Multimodal Audio Output
04:18 Multimodal Inline Image Output
07:25 Multimodal Live API
12:12 Native Tool Use
12:54 Unified SDK
13:29 Google Gemini 2.0 Flash Blog