Google's Gemini 2.5 Computer Use: AI Takes a Leap Towards Autonomous Web Navigation
14 Sources
[1]
Google's Gemini AI Is a Step Closer to Taking Control of Your Computer
Expertise Artificial intelligence, home energy, heating and cooling, home technology. Google's Gemini AI model might soon be able to act like an IT administrator who's taken over your faulty work laptop: moving your cursor around, clicking on things, typing in forms, all while you watch. The
[2]
This new Google Gemini model scrolls the internet just like you do - how it works
The company also admitted its weaknesses, including hallucinations. Google DeepMind has debuted a new AI model in public preview that's designed to navigate a web browser just as a human would. Built atop Gemini 2.5 Pro, the company's new Computer Use model can execute tasks like clicking,
[3]
Google's new Gemini 2.5 Computer Use model can click, type, and scroll
The company also admitted its weaknesses, including hallucinations. Google DeepMind has debuted a new AI model in public preview that's designed to navigate a web browser just as a human would. Built atop Gemini 2.5 Pro, the company's new Computer Use model can execute tasks like clicking,
[4]
Gemini gets one big step closer to taking over your browser
Google is switching on a new kind of AI assistant -- one that doesn't just talk about doing things, it actually clicks the buttons. The company's Gemini 2.5 Computer Use model is now in public preview for developers through the Gemini API in Google AI Studio and Vertex AI, giving agents the ability
[5]
'Gemini 2.5 Computer Use' model enters preview with strong web, Android performance
Google is now letting developers preview the Gemini 2.5 Computer Use model behind Project Mariner and agentic features in AI Mode. This "specialized model" can interact with graphical user interfaces, specifically browsers and websites. There are several steps that happen in a loop "until the task
[6]
Google's AI can now surf the web for you, click on buttons, and fill out forms with Gemini 2.5 Computer Use
Some of the largest providers of large language models (LLMs) have sought to move beyond multimodal chatbots -- extending their models out into "agents" that can actually take more actions on behalf of the user across websites. Recall OpenAI's ChatGPT Agent (formerly known as "Operator") and
[7]
Introducing the Gemini 2.5 Computer Use model
Summaries were generated by Google AI. Generative AI is experimental. Earlier this year, we mentioned that we're bringing computer use capabilities to developers via the Gemini API. Today, we are releasing the Gemini 2.5 Computer Use model, our new specialized model built on Gemini 2.5 Pro's
[8]
Google DeepMind Releases Gemini 2.5 Computer Use Model | AIM
The model lets AI agents interact directly with graphical interfaces, such as filling forms, scrolling and operating behind logins. Google DeepMind has released the Gemini 2.5 Computer Use model, a specialised version of its Gemini 2.5 Pro AI that can interact with user interfaces. The model is
[9]
Google's Gemini 2.5 Computer Use model can navigate the web like a human - SiliconANGLE
Google's Gemini 2.5 Computer Use model can navigate the web like a human Google LLC has just announced a new version of its Gemini large language model that's able to navigate the web through a browser and interact with various websites, meaning it can perform tasks like searching for information
[10]
Google's Gemini Can Now Control Your Computer Like a Human Assistant - Phandroid
Google announced a major upgrade to Gemini that lets the AI assistant take control of your computer. The new Gemini computer use model can navigate your desktop, click buttons, fill out forms, and complete multi-step tasks without constant supervision. This isn't just about answering questions
[11]
Google Unveils Gemini 2.5 Computer Use That Clicks, Types, and Scrolls Like Humans
Versions of this model is already powering Project Mariner and AI Mode in Google Search. Today, Google released the Gemini 2.5 Computer Use AI model that is designed to interact with user interfaces (UIs). It's built on the flagship Gemini 2.5 Pro model, bringing its visual and reasoning
[12]
Google rolls out Gemini 2.5 Computer Use model for deeper app and browser control
Google has released the Gemini 2.5 Computer Use model, a new specialized version built on Gemini 2.5 Pro's visual understanding and reasoning capabilities. The model enables AI agents to interact directly with graphical user interfaces (UIs) -- performing actions such as clicking, typing, and
[13]
Gemini 2.5 Computer Use model explained: Google's AI agent to navigate interfaces
Google DeepMind's Gemini agent can click, scroll, and fill forms Google's latest Gemini 2.5 update has quietly introduced something that could reshape how artificial intelligence interacts with the web: the Computer Use model. Unlike traditional chatbots that merely generate text or code, this new
[14]
Google introduces Gemini 2.5 Computer Use AI model: Here's how it works
It is built on Gemini 2.5 Pro's visual understanding and reasoning capabilities. Google has introduced Gemini 2.5 Computer Use, a new AI model designed to interact directly with web and mobile interfaces. This model, built on Gemini 2.5 Pro's visual understanding and reasoning capabilities, allows
Share
Copy Link
Google introduces Gemini 2.5 Computer Use, an AI model capable of interacting with web interfaces like a human. This development marks a significant step towards AI agents that can perform complex tasks across various digital platforms.
Google Introduces Gemini 2.5 Computer Use Model
Google DeepMind has unveiled a groundbreaking AI model that brings us one step closer to autonomous computer interaction. The Gemini 2.5 Computer Use model, now in public preview, is designed to navigate web browsers and mobile interfaces with human-like precision
1
2
.Capabilities and Functionality
Built on top of Gemini 2.5 Pro, this specialized model can execute a wide range of tasks within web interfaces, including clicking, typing, scrolling, and even more complex actions like drag-and-drop
3
. Users can instruct the model using natural language prompts, such as 'Open Wikipedia, search for 'Atlantis,' and summarize the history of the myth in Western thought.' The AI then autonomously navigates the website, performing the requested tasks step by step2
.Technical Approach
The model operates on an iterative looping function, allowing it to maintain a record of recent actions within a user interface and determine subsequent steps accordingly. This approach enables the AI to gain context and function more seamlessly as it performs multiple tasks within a particular site
3
.Performance and Availability
According to Google, Gemini 2.5 Computer Use outperforms similar tools from competitors like Anthropic and OpenAI in terms of accuracy and latency across multiple web and mobile control benchmarks
3
. While primarily optimized for web browsers, the model has shown promising results on mobile interfaces as well5
.The model is now available through the Gemini API in Google AI Studio and Vertex AI, with a demo version accessible via Browserbase
4
.Related Stories
Safety Measures and Limitations
Google has implemented several safety controls to prevent misuse and protect user data. The model can be instructed to request user confirmation before performing sensitive actions like making purchases or sending emails
1
. Developers can also restrict the model's actions to prevent undesired behaviors such as bypassing CAPTCHAs or compromising data security3
.However, Google acknowledges that the model may exhibit some limitations common to foundation models, including hallucinations and challenges with complex logical deduction and counterfactual reasoning
3
.Implications and Future Prospects
The introduction of Gemini 2.5 Computer Use represents a significant step towards agentic AI, potentially revolutionizing how we interact with digital interfaces. This technology could streamline various tasks in the workplace and customer service interactions, replacing mundane point-and-click activities with conversational AI interactions
1
.As AI agents gain more control over computer interfaces, the need for robust safety precautions becomes increasingly crucial. Google's approach to addressing these concerns will likely shape the future development and deployment of similar technologies across the industry.
References
Summarized by
Navi
[4]
Related Stories
Recent Highlights
1
Apple Launches iOS 27 and macOS 27 with Siri AI Overhaul and Liquid Glass Updates
Technology
2
OpenAI Agents Launched RubyGems Attack With 2,000+ Malicious Packages, Attempted API Key Theft
Technology
3
Apple Launches iPhone 18 Pro with Variable Aperture Camera and Advanced AI Features at $1,199
Technology
Recent Highlights
Today's Top Stories
Don’t drown in AI news. We cut through the noise - filtering, ranking and summarizing the most important AI news, breakthroughs and research daily. Follow topics that matter to you and stay ahead.
