There are a few other things that I built when I was at Harvard that were kind of smaller versions of Facebook.

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 was in college I did a lot of stupid things and I don't want to make an excuse for that. Some of the things that people accuse me of are true, some of them aren't. There are pranks, IMs.

You can be so bad at so many things... and as long as you stay focused on how you're providing value to your users and customers, and you have something that is unique and valuable... you get through all that stuff.

Critics worry that if we spend time paying attention to that new kind of media or technology instead of talking to each other that that is somehow isolating. But humans are fundamentally social. So I think in reality, if a technology doesn't actually help us socially understand each other better, it isn't going to catch on and succeed.

If Facebook were a country, it would be the 8th most populated in the world, just ahead of Japan.

Move fast and break things. Unless you are breaking stuff, you are not moving fast enough.