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.

The last six years have been a lot of coding and focus and hard work. But maybe it would be fun to remember it as partying and all this crazy drama.

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.

When I'm introspective about the last few years I think the biggest mistake that we made, as a company, is betting too much on HTML5 as opposed to native... because it just wasn't there. And it's not that HTML5 is bad. I'm actually, on long-term, really excited about it. One of the things that's interesting is we actually have more people on a daily basis using mobile Web Facebook than we have using our iOS or Android apps combined. So mobile Web is a big thing for us.

I don't hate anybody. The Winklevi aren't suing me for intellectual property theft. They're suing me because for the first time in their lives, the world didn't work the way it was supposed to for them.

We are so fortunate that our work in connecting the world through Facebook has given us the ability to give back to our local community, our country and the world -- and to work to improve education, health care and internet access for everyone, to serve our community in San Francisco, we can think of no better place to focus than The General.

There are a few other things that I built when I was at Harvard that were kind of smaller versions of Facebook. One such program was this program called Match. People could enter the different courses that they were taking, and see what other courses would be correlated with the courses they are taking.