Paired with Google Instant, autocomplete, the feature whereby Google predicts what it is you're in the middle of typing, can make searching incredibly fast. But the problem with autocomplete is that many people who use Google for their online searching are looking for things that not many others are looking for -- there's just too many possible term combinations -- and the feature works largely by looking at the most popular searches across the site.

Yesterday, the search giant rolled out some changes to autocomplete for users of google.com in English that should make it more accurate. Instead of making predictions based on your entire search term, "now what we're doing is making predictions based on only part of your search -- specifically, the last word or words," software engineer Bartlomiej Niechwiej explained on the official Google blog. (Emphasis is original.) "While few people have searched for [florida state senate building], many more have searched for [state senate building]. By looking at just the last part of what you've typed into the box, in this case "state senate bui," we can generate a prediction for "building." You'll see a dropdown box below the end of your search with predictions for just that word."

autocomplete-enhancement.png

The change isn't a huge one, but it's the next step in building the perfect search engine, one that knows what you're thinking before you can get the words out on the page.

We want to hear what you think about this article. Submit a letter to the editor or write to letters@theatlantic.com.