Ever since widespread adoption of the Internet began, spam emails have been a near-unavoidable plague upon the average web user — nor has the problem gotten better with time. Today, a stunning 97% of the 60 billion emails sent every day are spam.

Google, however, envisions a future in which people are protected from spam emails by way of powerful artificial intelligence that deletes spam messages before they ever reach your inbox.

According to a July 9 TechCrunch article, Google recently announced that its Gmail spam filters are now more powerful than ever, giving users a nearly spam-free experience.

Gmail has long held a reputation for having one of the best spam filters in the email world. Before Google’s most recent update, the average Gmail inbox’s emails consisted of less than 0.1% spam. Now, with Google’s more sophisticated and brain-like neural networking technology, Gmail users should be seeing no spam at all.

To create such a powerful anti-spam filter, Google equipped its spam filters with machine learning technology, which has allowed the filters to gradually learn what constitutes as spam over time. For example, every time a user marks a spam message as “Spam” or “Not Spam,” Google’s spam filters become more accurate.

“One of the great things about machine learning is that it adapts to changing situations,” said John Rae-Grant, a senior product manager for Gmail.

And for users who need to send non-spam messages in bulk, Google also launched its new Postmaster Tools feature. The service allows qualified bulk senders to better understand how Gmail treats every email sent through its service. TechCrunch calls Postmaster Tools a version of Google Webmaster Tools for bulk email senders.

One thing all Gmail users can anticipate is an email experience that’s more tailored to their individual preferences, Wired.com reports. Because one person’s spam is often another person’s discount or coupon, Google is making its artificial intelligence optimize Gmail for each individual user.

“We track and try to approximate — based on what you have previously paid attention to and reported as spam — what you want in front of you and don’t want in front of you,” Rae-Grant explained. “So, in addition to this big machine learning model that’s learning from everybody’s reporting, we’re then fine-tuning things for the individual.”

One thing’s for certain: the email of today bears almost no resemblance to the email we used back in 2002.