Skip to main content
  1. Home
  2. Computing
  3. News

Chrome will soon tell you what you were reading a while ago with tab-aware AI

Add as a preferred source on Google
Google AI Mode interface on Chrome for smartphone.
Google

Google Chrome will soon let AI Mode access and understand what you’re reading and use that information to provide contextual answers to your questions. Spotted in the Chrome Canary builds by Windows Report, the “Ask Google about previous tab” lets the browser source content from your recent tabs when answering questions.

Instead of treating each question separately, Chrome’s AI Mode will understand (or at least try to understand) your queries in the context of your browsing session, not just the tab you’re currently on, but also the previous one, letting you ask natural follow-up questions without starting from scratch.

On Android, Chrome’s AI lets users attach a recent tab to their queries by tapping the “+” button in the address bar. This means you can ask the browser to clarify a doubt, summarize key points, or research a particular topic explained in a web page, without reopening the tab or manually copying anything.

Recommended Videos

The update expands Chrome’s AI Mode, which already allows users to interact with the browser through conversational prompts. Traditionally, browsers simply follow the inputs you provide them via text. However, the new addition introduces awareness, allowing the browser to understand the flow of your web activity.

If you regularly juggle between multiple Chrome tabs, you know the pain of losing track of information and having to spend those precious minutes relocating it. But now, you can read something, move on, and ask the browser to recall or summarize it, saving time and reducing friction.

The feature will also help everyday users by eliminating the need to copy and paste information manually. Tab-aware AI is among the first steps toward an all-in-one AI browser that not only helps you perform tasks but also takes them off your hands.

In the future, the browser can summarize information across multiple tabs, fill out forms on your behalf, organize information into notes, or help you complete tasks like shopping or planning a vacation. Most recently, Google released multiple Gemini-powered tools for Chrome, turning it into a native AI browser.

Shikhar Mehrotra
For more than five years, Shikhar has consistently simplified developments in the field of consumer tech and presented them…
The maker of ChatGPT wants to make open-source projects less of a security bargain
OpenAI launches Patch the Planet for open-source security, with over 30 open-source projects on board.
openai-chatgpt-os

OpenAI has launched Patch the Planet, a new initiative aimed at fixing one of the internet's quietest problems – the chronically underfunded security of open-source software.

Patch the Planet pairs OpenAI's most security-capable AI models with Trail of Bits, a security firm that has committed its entire research organization to the effort, alongside support from HackerOne and Calif.

Read more
I sifted through the Prime Day chaos to find the best Apple deals actually worth buying
Apple's about to hike prices. Prime Day 2026 is your last chance to save up to $150 on MacBooks, AirPods, and iPads.
Prime Day Deals on Apple Products

Apple is set to increase the prices for its upcoming iPhones and MacBooks, as the company can no longer offset the rising RAM and storage costs. That means, if you are looking to upgrade your aging device, you should buy the current-generation Apple products rather than wait for the new ones.

And since Amazon Prime Day is offering good discounts on the latest iPhones, iPads, MacBooks, and other Apple accessories, this is the perfect time to buy them. Here are my favorite Amazon Prime Day deals for Apple products. 

Read more
This sneaky photo trick gets AI chatbots to ignore their safety rules
Florida International University researchers built a method that nearly doubled the rate of harmful responses from a tested AI model using nothing but pixel-level edits in an image.
JaiLIP AI chatbot exploit image

A photo that looks completely ordinary to you could carry a hidden instruction to trick an AI chatbot into ignoring its safety rules, according to new research out of Florida International University. The study found that pixel-level alterations in an image that are invisible to the human eye can be enough to confuse the model reading the image and lead it to generate responses it would normally block.

Hacking what the AI sees

Read more