In this video, I cover using Gemini 2.0 models for browser use. While things like Project Mariner are not available publicly yet, we can use open-source frameworks like Browser Use to emulate the same kind of functionality. 

Browser User Github: https://github.com/browser-use/web-ui
AI Studio: https://aistudio.google.com/

For more tutorials on using LLMs and building agents, check out my Patreon
Patreon: https://www.patreon.com/SamWitteveen
Twitter: https://x.com/Sam_Witteveen

🕵️ Interested in building LLM Agents? Fill out the form below
Building LLM Agents Form: https://drp.li/dIMes

👨‍💻Github:
https://github.com/samwit/llm-tutorials

⏱️Time Stamps:
00:00 Intro
00:07 Google Gemini 2.0 Project Mariner
01:01 Browser Use
01:16 Browser User Docs
01:29 Browser Use Web UI Github
02:13 Browser Use Installation Guide
05:06 Browser Use Demo
06:53 Browser Use Demo: Searching Product in Amazon
12:05 Browser Use Demo: Searching for Articles on VentureBeat

Sam Witteveen AI is a publication offering insights, tutorials, and resources for artificial intelligence (AI) enthusiasts and practitioners. Readers can learn about machine learning algorithms, deep learning frameworks, and AI applications. With tutorials, case studies, and expert interviews, Sam Witteveen AI provides  guidance and expertise for building and deploying AI solutions.

Sam Witteveen

Google's Gemini 2.0 models, especially the flash version, are highly efficient for browser use and other multimodal tasks. While Project Mariner remains in testing, a startup has released an open-source version of their browser automation tool that integrates Gemini models, which outperforms prior benchmarks. The setup involves cloning the repository, installing dependencies, and configuring the model settings. The tool is useful for tasks like automated price checking and browsing but requires careful prompts to optimize accuracy. The potential for customizing and expanding the tool for various use cases, including AI-driven news aggregation and automated reservations, is significant.

Gemini Browser Use