Last month, we reported that Google is developing an AI agent As a browser extension that can do the work for you in web browsers. And in today’s time Gemini 2.0 Following the announcement, Google has finally unveiled Project Mariner, an early prototype that could unlock the future of human-agent interactions.
Powered by the latest Gemini 2.0 models, Project Mariner can understand what it sees on your browser screen and use that information to perform tasks for you. It can understand web elements like forms, text fields, code, images and more. The web extension powered by Project Mariner can type, scroll, and click in the active tab, but for sensitive actions like purchasing something, it requires final confirmation from the user.
Google says the early prototype is slow at the moment and not always accurate, but it will rapidly improve over time. In a demo shown by Google, Project Mariner can remember company names from Google Sheets, browse the web, find companies’ websites, and pull out contact details.
In the WebVoyager benchmark, which tests the agentive capabilities of models on real-world web tasks, Project Mariner achieved 83.5%, the highest score ever. Google says it’s working with trusted testers to improve Project Mariner, but there’s no information on its release date.
related to project astra Which was announced at Google I/O 2024, Google says it can now understand multiple languages and use tools like Google Search, Maps, and Lens to deliver a better experience. Project Astra is also getting better at remembering things. It can now remember up to 10 minutes of memory during a session for better personalization. Google has also reduced latency significantly.
The release date of Project Astra is unknown, but Google says its capabilities will be integrated into the Gemini app and other form factors like glasses.
Additionally, Google also announced that it is working with game developers to find out how its AI agents behave in games like Clash of Clans and Hay Day. Google’s Gemini 2.0-powered AI agents can see the screen and make suggestions in real time. These AI agents can also use Google search and provide gaming knowledge on the go.
Finally, Google introduced Jules, an AI code agent for developers that integrates directly into GitHub workflows. It can detect issues, develop a plan and execute it under the supervision of the developer. You can find more information about Jules here Here,
