Helping a billion people connect is amazing, humbling and by far the thing I am most proud of in my life.

It only took me two weeks to build the first version of Facebook because I had so much stuff before then.

I mean, we've built a lot of products that we think are good, and will help people share photos and share videos and write messages to each other. But it's really all about how people are spreading Facebook around the world in all these different countries. And that's what's so amazing about the scale that it's at today.

The unsupervised learning is the way most people will learn in the future. You have this model of how the world works in your head and you're refining it to predict what you think is going to happen in the future.

It used to be the case, like, you'd switch jobs, and then maybe you wouldn't keep in touch with all the people that you knew from that old job. Just because it was too hard. But one of the things that Facebook does is it makes it really easy to just stay in touch with all these people.

Google, I think, in some ways, is more competitive and certainly is trying to build their own little version of Facebook.

When you think about it, there's no way to input things into a computer. It's all... the holes only go out, right? Like you can plug a keyboard or a mouse in but that's a trick because the computer thinks the inputs are outputs. That's a programmer trick, basically magic. The key to the future is to make holes that go in too.