Paul Buchheit explains how he and Noam Shazeer built Google’s “Did you mean?” feature

When I started at Google, one of the first features I added was the spell corrector, because I was looking at the query logs and I would see that I'm not the only person with this problem. Like a third of the queries were misspelled or something like that. So it was like the easiest quality win ever was just to fix the spelling.

Wait, so you built the original spelling corrector at Google?

I did the first did you mean Feature. I built it just based off of kind of an existing spell corrector library. But it would give really dumb corrections. Like if you typed in TurboTax, it would, would try to correct it to TurboTax Turbot being a type of fish. And so I did some basic, like statistical filtering that would say, like, that's an idiotic correction, don't show it. And so I would just like filter the results. And then I was working on building a better spell corrector because I knew we could just use all of the data. We had a copy of the web and we had billions of search queries. There's like a lot of information there. So I was working on making something better. And then I was just using it as an interview question. So when I would interview engineers, I would be like, how would you build spell corrector? And I would say like 80% of engineers just had no idea. And the other 20% gave sort of mediocre answers. But then there was this like one guy who gave a really, really good answer. He was ahead of where I was already, so I was like, we have to hire him. I gave him as his like intro project. I just gave him all of my code and showed him how to, how to run projects on the cluster. And then I went away for a couple weeks for Christmas and when I came back, he had invented what we now know as like the did you mean feature. And so he did all of that in like his first two weeks at Google. And it was like this incredible thing that could spell correct my last name. You know, no one had ever done a spell corrector that would correct proper nouns and things like that. And so that person was Noam Shazir, who then is also the person who later on invented AI. So he's, he's one of the key people on the all you need is attention paper. And then he's, he's now since started character AI.

I never connected those dots. But I remember in 2000 when the original Google spelling corrector launched, it was a big deal because was one of the first instances of AI that was like widely used by the general population, because the earlier spelling correctors, they'd all been very simple things based on just, like, a list of dictionary words and edit distance. And so it couldn't handle proper nouns. It made all kinds of, like, dumb suggestions. The Google one was the first one that was trained on real data.

Exactly.

So it actually worked.

Right. So the Google Spectrocur has no dictionary. It's just based on looking at the Web and at query logs and then just predicting what is the, you know, most likely correction.