Watch: Why autocorrect makes so many mistakes, according to the former Apple engineer who helped create it

Business Insider US
  • Autocorrect has been a feature on the iPhone for over 10 years, but it still makes so many frustrating mistakes while we text. 
  • To get to the bottom of the issue, we spoke with Ken Kocienda, who helped create autocorrect for Apple.
  • Kocienda explains how it works and what's going on when it misinterprets the word or phrase you're trying to type.

At times, it can really seem like autocorrect is working against you, even after the iPhone has now had autocorrect for over 10 years.

When you type something on a phone there's a lot of work going on in the background. The phone analyses your input and compares it to stored dictionaries and language models. The phone then tries to correctly interpret the word or phrase you're trying to type. So when you type "fopd" your phone changes it to "food" because "fopd" isn't a word but it's only one letter away from "food." But not every example is this obvious.

"The vowels U, I, and O are very close to each other so a word like put, pit, and pot those, those were real challenges," said Ken Kocienda. 

Kocienda has more reason than most to know what's going on behind the scenes of your autocorrect: he's one of the people who developed it for Apple. His job was to come up with a way to make speedy and accurate typing possible on a sheet of glass. 

It turned out to be a lot harder than he thought. The hardest part isn't correcting spelling or grammar, it's interpreting what you meant to say from what you wrote. And autocorrect is actually pretty good at this but users tend to notice autocorrect only when it makes mistakes.

But just one misspelling in 20, can be enough to stand out. Its even more obvious when autocorrect leads to embarrassing mistakes. In most cases Kocienda says this is when we try to swear.

You can do something about it - like going into your phone dictionary and adding and deleting words. It may even be sooner than you think that Machine Learning and will take over this role.

Receive a single WhatsApp every morning with all our latest news: click here.

Also from Business Insider South Africa