New Issue: Science’s Impossible Questions. Read Now

How the Smartphone Killed Typing—But Started an AI Revolution

The race to find a better on-screen keyboard has spawned new ways for machines to understand us

Join Our Community of Science Lovers!

Steve Jobs often swam against the tide of prevailing opinion. (“You can't make a mouse without two buttons!” “You can't make a computer without a floppy drive!” “You can't make a cell phone without a swappable battery!”) He turned out to be right many times.

Occasionally, though, his decisions took the industry into awkward directions from which we've never really recovered. Jobs was fixed, for example, on the idea of a cell phone without any keys. The iPhone became a hit, it spawned imitators, and the rest is history (or the future, depending on how you look at it).

Eliminating the keyboard has its perks. It leaves more room on the phone for screen area—for photographs, movies, maps and reading material. Only one activity really suffers: entering text.


On supporting science journalism

If you're enjoying this article, consider supporting our award-winning journalism by subscribing. By purchasing a subscription you are helping to ensure the future of impactful stories about the discoveries and ideas shaping our world today.


The first iPhone offered an on-screen keyboard. The advantage, as Jobs pointed out, was it could disappear when you didn't need it. It could also change languages or alphabets in a flash.

But at its core, typing on glass is slow and unsatisfying, especially compared with using a physical keyboard such as the BlackBerry's. The history of contemporary smartphones has been a seven-year quest to fix that problem.

The original iPhone tried to help in two minor ways, which are still at work today. First, the on-screen keys change size based on probability (not visually but behind the scenes).

Second, there is autocomplete: spawner of a billion curses, source of much hilarity but also often quite helpful.

The next big breakthrough was predictive text. That's where you see three words just above the keyboard—words that, statistically speaking, you're most likely to type next. When the phone predicts correctly, you feel a little surge of happiness. You type “the best,” and the phone offers “thing,” then “about.” On the other hand, predictive text brings frustration of its own—such as when the software doesn't catch what you intend.

These predictive algorithms learn over time. And they save a lot of mistakes. But they're not the Ultimate Solution. They force you to split your focus between the keys and the suggestions as you type, which slows you down.

What about speech recognition? Isn't that the perfect solution?

Not really. As we all know, cell-phone dictation is far from perfect; you have to correct the mistranscriptions manually. It's a tough technology to perfect, of course—people have a million different accents and dialects, and you're transmitting their words over a connection to distant servers that convert the lo-fi audio into text.

Even if the accuracy were as good as it is on a desktop PC—when you're in a quiet room, wearing a headset microphone—you would still need a keyboard occasionally. “Bookmark it” sounds like “book market”; “the right or left” sounds like “the writer left.” How can your phone algorithm know which you wanted?

So the world's engineers keep hammering away at the typing-on-phones problem. They have come up with alternative on-screen keyboards for popular phones. Swype and SwiftKey, for example, let you drag your finger sloppily and quickly across the keys, aiming for the letters you want.

The sheer quantity of attempts to solve the text-input problem hints at a larger truth: There is no obvious, perfect solution. There are only different sets of pros and cons.

We can take comfort from the fact that dictation, prediction and autocompletion solutions improve every year. (The word choices on iOS 8's predictive-text buttons, for example, attempt to reflect your style for different contexts—say, texting a friend versus e-mailing your boss—and predict what word you might prefer to use.) But text entry without a physical keyboard may be one of those receding-horizon deals: no matter how far we travel, we'll never quite reach the finish line.

Then again, we made the sacrifice for a good reason: to give ourselves a big, friendly screen for showcasing everything else our phones do. For most of us, it's been a trade-off worth making.

SCIENTIFIC AMERICAN ONLINE
The best smartphone keyboard apps: ScientificAmerican.com/dec2014/pogue

Subscribe to Support Independent Journalism

Great science journalism requires human expertise, time, effort and creativity. And it costs money. That’s why I and the journalists here at Scientific American hope you’ll join our community.

When you subscribe, you are supporting staff and freelance journalists who are passionate about telling science stories that are true, important and compelling. Our editors and reporters are often experts in their fields, which means they understand the nuances of big discoveries and can untangle the breakthroughs from the hype. With a subscription, you are also supporting rigorous fact-checking to ensure the words we publish are precise and accurate. And you’re supporting original illustrations, graphics and photos that bring you closer to an advanced laboratory, an ice sheet in Antarctica or a space mission in orbit. You’re helping us craft other types of high-quality journalism as well: Our newsletters are carefully written, edited and curated by staffers you have or will come to know and love. Our Science Quickly podcast is based on original reporting, collaboration with editors and scientists and exacting production.

Subscriptions keep this engine running so we can continue to deliver thoughtful, rigorous and independent science journalism to you. In an era of viral misinformation, this work is crucial. If you value what we do, I hope you’ll consider joining us as a subscriber

Thank you,

Jeanna Bryner, Editor in Chief, Scientific American

Subscribe