Luis Von Ahn
π€ SpeakerAppearances Over Time
Podcast Appearances
Interpreters, we don't because we don't do what you would see on the UN, doing real-time interpretation like that. But translators, we do. Not very many. We have been reducing that number for a while. And at this point, it's dozens. It's not a lot.
Interpreters, we don't because we don't do what you would see on the UN, doing real-time interpretation like that. But translators, we do. Not very many. We have been reducing that number for a while. And at this point, it's dozens. It's not a lot.
Interpreters, we don't because we don't do what you would see on the UN, doing real-time interpretation like that. But translators, we do. Not very many. We have been reducing that number for a while. And at this point, it's dozens. It's not a lot.
Generally, they're going over the things that computers have done. Because most of the stuff we do with computers, yeah, double-checking, making sure. Now, it depends on what for, by the way, I should say. There are certain, you know, there's a difference in importance in text.
Generally, they're going over the things that computers have done. Because most of the stuff we do with computers, yeah, double-checking, making sure. Now, it depends on what for, by the way, I should say. There are certain, you know, there's a difference in importance in text.
Generally, they're going over the things that computers have done. Because most of the stuff we do with computers, yeah, double-checking, making sure. Now, it depends on what for, by the way, I should say. There are certain, you know, there's a difference in importance in text.
For example, if it's our content, as in like our learning content, there's so much of that, thousands and thousands and thousands of kind of sentences and words and paragraphs. That is mostly done by computers, and we probably spot-check it. But if it's things like the user interface of Duolingo, where we say like, you know, the button says quick,
For example, if it's our content, as in like our learning content, there's so much of that, thousands and thousands and thousands of kind of sentences and words and paragraphs. That is mostly done by computers, and we probably spot-check it. But if it's things like the user interface of Duolingo, where we say like, you know, the button says quick,
For example, if it's our content, as in like our learning content, there's so much of that, thousands and thousands and thousands of kind of sentences and words and paragraphs. That is mostly done by computers, and we probably spot-check it. But if it's things like the user interface of Duolingo, where we say like, you know, the button says quick,
and we have to translate that is all done with humans. And we spend a lot of effort on that, but that's because each one of those is highly valuable. Like we cannot have a mistake in the quit button or in the button that says purchase now or whatever. We just cannot have a mistake.
and we have to translate that is all done with humans. And we spend a lot of effort on that, but that's because each one of those is highly valuable. Like we cannot have a mistake in the quit button or in the button that says purchase now or whatever. We just cannot have a mistake.
and we have to translate that is all done with humans. And we spend a lot of effort on that, but that's because each one of those is highly valuable. Like we cannot have a mistake in the quit button or in the button that says purchase now or whatever. We just cannot have a mistake.
And not only, it's not just about mistakes is we want to make sure that the voice is consistent throughout the app, et cetera.
And not only, it's not just about mistakes is we want to make sure that the voice is consistent throughout the app, et cetera.
And not only, it's not just about mistakes is we want to make sure that the voice is consistent throughout the app, et cetera.
Yeah. For example, in our app, we have made the decision that in Spanish, we use the informal second person pronoun. So when we refer to somebody in the app, we refer to the user informally. When we say you, we say the informal you. It's like usted versus... TΓΊ is informal. Usted is formal. We don't use usted. We use tΓΊ. The people that do our user interface in Spanish know that.
Yeah. For example, in our app, we have made the decision that in Spanish, we use the informal second person pronoun. So when we refer to somebody in the app, we refer to the user informally. When we say you, we say the informal you. It's like usted versus... TΓΊ is informal. Usted is formal. We don't use usted. We use tΓΊ. The people that do our user interface in Spanish know that.
Yeah. For example, in our app, we have made the decision that in Spanish, we use the informal second person pronoun. So when we refer to somebody in the app, we refer to the user informally. When we say you, we say the informal you. It's like usted versus... TΓΊ is informal. Usted is formal. We don't use usted. We use tΓΊ. The people that do our user interface in Spanish know that.
I know that very well. If you were to just ask a computer to do it, It may be inconsistent in different screens. It may be something. So we just want to make sure that it's all consistent, that it has the same voice. same playful voice, et cetera. And so for that, we still employ humans.
I know that very well. If you were to just ask a computer to do it, It may be inconsistent in different screens. It may be something. So we just want to make sure that it's all consistent, that it has the same voice. same playful voice, et cetera. And so for that, we still employ humans.