Apps could show you fewer, better alerts by using a new deep-learning trick.
The problem: If an app sends too many push notifications, users may well delete it. Send too few, and they might not use it. But deep learning could help find the Goldilocks amount of notifications—where they’re not annoying, but help boost use of the app.
A solution: A paper published on the arXiv describes how researchers trained an AI on data like browsing history, shopping history, and financial details to build a recommendation engine for when and what to show in notifications. Using it, they were able to accurately forecast a user’s preferences for frequency and content.
More for less: When the AI was tested out on a number of Taiwanese apps, it reduced the number of notifications while increasing the click-through rate.
Why Meta’s latest large language model survived only three days online
Galactica was supposed to help scientists. Instead, it mindlessly spat out biased and incorrect nonsense.
DeepMind’s game-playing AI has beaten a 50-year-old record in computer science
The new version of AlphaZero discovered a faster way to do matrix multiplication, a core problem in computing that affects thousands of everyday computer tasks.
The White House just unveiled a new AI Bill of Rights
It's the first big step to hold AI to account.
Google’s new AI can hear a snippet of song—and then keep on playing
The technique, called AudioLM, generates naturalistic sounds without the need for human annotation.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.