Google detailed this week some upcoming improvements coming to its Chrome browser with the help of machine learning. Some of Chrome’s accessibility and security features already use machine learning to make the web safer and more inclusive, and the Chrome team is now building an ML model to make notification permission prompts less annoying.
In the next release of Chrome, the web browser will use machine learning to predict when permissions prompts are unlikely to be accepted by users based on their previous interactions with similar prompts. The machine learning model, which will run entirely run on the device, will silence these permissions requests after evaluating that users are unlikely to grant them.
The Chrome team is also exploring the use of machine learning to dynamically change the buttons on the Chrome toolbar on Android depending on the type of activities you’re more likely to do at a specific time of the day. “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.). Of course, you’ll be able to customize it manually as well,” the team explained.
Having an inconsistent UI on such an essential app as a web browser may not exactly sound like the best idea, but Google is being reassuring about it. “Our goal is to build a browser that’s genuinely and continuously helpful, and we’re excited about the possibilities that ML provides,” the team said. Because all these features are powered by on-device machine learning models, the Chrome team also emphasized that “your data stays private, and never leaves your device.”