Google Chrome Will Use Machine Learning to Make Browsing Less Awful

pcmag.com:

Google has revealed its plans to use machine learning to make browsing the web suck less.

The company says(Opens in a new window) it already uses machine learning to enable some features, such as flagging potentially malicious websites or grouping browsing history based on specific topics, in Chrome. But it's planning to introduce additional features informed by machine learning in the future.

It's starting with annoying permission requests from websites. You've almost certainly encountered these before—it often seems like every other site you visit requests permission to send notifications, learn your location, or gain access to something on your device.

"To help people browse the web with minimal interruption," Google says, "Chrome predicts when permission prompts are unlikely to be granted based on how the user previously interacted with similar permission prompts, and silences these undesired prompts. In the next release of Chrome, we’re launching an ML model that makes these predictions entirely on-device."

That feature demonstrates how Google can use machine learning in a reactive way. On the proactive side, the company says that future versions of Chrome will use the technology to enable a toolbar that can automatically change itself to accommodate user behavior.

Google says it wants "to make sure Chrome is meeting you where you’re at, so in the near future, we’ll be using ML to adjust the toolbar in real-time – highlighting the action that’s most useful in that moment (e.g., share link, voice search, etc.)." (The company says Chrome users will still be able to customize the toolbar manually, so this feature shouldn't be too disruptive.)

Sign up for What's New Now to get our top stories delivered to your inbox