Google Mirror Dimension: Tech Giant Builds a Fake Internet to Test Chrome AI Agents Safely
Google has built an entire fake internet to safely train the new AI browsing agents coming to Google Chrome. The project, called the Mirror Dimension, is a giant alternate universe web filled with shopping sites, social media feeds and bank dashboards, except none of it is real. It gives Chrome’s Gemini-powered “auto browse” feature a place to click links, fill out forms, download podcasts and shop online without ever touching a real website or putting actual user data at risk.
The system was detailed on Google’s security blog. It works as a massive, locked-off playground where the AI agents can be tested thousands of times under controlled conditions, so engineers can see exactly how they behave before they are let loose on the real web.
Why Google could not use the real internet
Training an AI agent to handle everyday web errands requires running thousands of tests across hundreds of websites. Doing this on the live internet creates big problems. Real websites change constantly, which makes it hard for engineers to repeat tests accurately.
Worse, letting an unrefined AI loose on the open web is risky, because one mistake could mess up a real account or cause actual harm. There is also a tricky issue called “eval awareness”. Modern AI models are so perceptive that if they figure out they are inside a test, they start acting unusually careful, ruining the results. To see how the AI truly behaves, Google had to trick it into thinking it was browsing the real world.
How the fake internet fools Chrome AI
To pull off the illusion, Google built the Mirror Dimension inside a tightly sealed digital sandbox using a tool called gVisor. Whenever the AI tries to visit a popular website, a local system quietly sends it to a fake copy instead. The clever part is that the web address in Chrome’s bar stays completely normal.
Because Chrome has strict built-in security checks, engineers had to use custom, forged web certificates inside the sandbox so the browser would not flash warning signs. Google stresses that hackers could not do this to regular Chrome users on the open internet, as it only works because the company has total control over its private test network. Every test also starts from a clean slate so previous actions never affect the next run.
AI agents are building the fake web
Building thousands of realistic websites by hand would be impossible, so Google put teams of other AI agents to work. Research agents first plan what a site needs, such as working shopping carts and promo code boxes. Builder agents then write the actual website code, while critic agents use Chrome developer tools to click buttons, take screenshots and send glitches back for fixes.
Together, they have built an entire fake web of online stores, recipe sites, local marketplaces and banking dashboards. The result is a test environment realistic enough to fool the very AI agents being trained inside it.
Fighting hidden attacks
A major goal of this project is protecting users from “prompt injection” attacks, where hackers hide secret, harmful instructions inside webpage text or images to hijack an AI. Early on, Google’s AI spotted these tests by noticing strange web addresses, so engineers began hiding attack triggers inside invisible web headers instead.
This automated setup lets one security engineer create over 1,000 attack tests daily, more than 30 times what a human could make manually. Google did not share how often its AI passed or failed those tests.
Chrome AI security engineer Charles Qian noted that the open web is hostile, but the agent is already developing mature judgement on when to pause and ask users for confirmation. Google engineering director Doug Turner said that the company will keep upgrading this fake web to make it even more realistic as AI gets smarter.
The Mirror Dimension shows how seriously Google is taking the safety of AI browsing agents. As these agents move from experiments into everyday Chrome use, the fake internet gives Google a way to find their weaknesses first, before real users pay the price.
Frequently Asked Questions
What is Google’s Mirror Dimension?
The Mirror Dimension is a giant fake internet built by Google to safely test Chrome’s AI browsing agents. It contains fake copies of shopping sites, social media feeds and bank dashboards, so the AI can practise browsing without touching real websites or real user data.
Why did Google build a fake internet instead of testing on the real web?
Testing on the live internet is unreliable because real websites keep changing, and a mistake by an untested AI could harm a real account. Google also needed to hide the fact that the AI was being tested, because AI models behave more carefully once they realise they are in a test.
What are prompt injection attacks?
Prompt injection attacks hide secret, harmful instructions inside webpage text or images to hijack an AI agent. Google uses the Mirror Dimension to test its Chrome agents against these attacks, with one security engineer able to create over 1,000 attack tests a day using the automated setup.