AI · Article
Google Builds a Fake Internet to Safely Test Chrome AI Browsing Agents
WIRED ·

At a glance
Google's Chrome team built a large, fully controlled fake internet to safely test its AI browsing agents. These agents can use websites and apps the way a person would, so the team needs a space where they can make mistakes without risk. The environment includes social media, shopping, and bank sites that look real.
Key points
- Google built a closed 'Mirror Dimension' web environment that the Chrome team fully controls.
- It includes many fake but realistic sites, such as social media, shopping, and bank dashboards.
- Agents face tests like hidden prompt-injection attacks, which try to trick them with hidden instructions.
- Google had to get around Chrome's safety checks, but only because it controls the whole network.
Why it matters
AI browsing agents can act on real websites, so testing them in a safe space helps prevent costly mistakes and security risks..
Original source
Google Built a Giant ‘Mirror Dimension’ Internet to Test Its Chrome AI Agents
WIRED · Nov 20, 02:00 KST
Read on WIRED ↗AI summarized the original article. Check the original for accuracy. Copyright belongs to WIRED.
More from this field
- Korean Firms Build Three-Way AI Push: Anthropic Stake, HBM Chips, Claude Rollout
Korean companies are expanding their roles in the global AI market around Anthropic's IPO. SK Telecom earned large paper gains from an early investment, while Samsung Electronics and SK hynix are strengthening chip supply ties. Samsung SDS and LG CNS are bringing Anthropic's Claude model into the business AI market.
뉴스웨이 · Nov 21, 06:10 KST - MIT and IBM Team Probes Gaps in Multimodal AI Understanding
MIT and IBM researchers are studying where today's multimodal AI models fall short, even when they handle text, images, and sound fluently. Their team, co-led by MIT's Jim Glass, builds new benchmarks and training methods that need less labeled data. This Q&A walks through how the project started and how it has evolved.
MIT News · Nov 21, 06:00 KST - Leaky AI Supply Chain Exposes Secret User Data at Alarming Rate
A research test sent nearly two million prompts with fake but working secrets through a network of AI services to see where they ended up. Many of the secrets were stolen, and attackers used them to reach cloud accounts. The results point to weak protection of customer data along the chain.
Ars Technica · Nov 21, 05:59 KST - OpenAI Shows How to Claim a Shopify Store in ChatGPT
This video shows how to claim your business in ChatGPT by connecting your Shopify store. You can start in Business Hub or the Shopify App Store. After connecting, you can manage your business information to control how your store appears in ChatGPT.
OpenAI 공식 YouTube · Nov 21, 05:48 KST