The bottom line for mathematicians is that the architecture has to be right. In all the mathematics that I did, the essential point was to find the right architecture. It's like building a bridge. Once the main lines of the structure are right, then the details miraculously fit. The problem is the overall design.

I think that the artificial-intelligence people are making a lot of noise recently, claiming that artificial intelligence is making huge progress and we're going to be outstripped by the machines. But, in my view, this whole field is based on a misconception. I think the brain is analog, whereas the machines are digital. They really are different. So I think that what the machines can do, of course, is wonderful, but it's not the same as what the brain can do.

Aviation is the branch of engineering that is least forgiving of mistakes.

What the world needs is a small, compact, flexible fusion technology that could make electricity where and when it is needed. The existing fusion program is leading to a huge source of centralized power, at a price that nobody except a government can afford.

Some of my friends like to keep science and religion together, but I certainly like to keep them separate.

All stable processes we shall predict. All unstable processes we shall control. Describing John von Neumann's aspiration for the application of computers sufficiently large to solve the problems of meteorology, despite the sensitivity of the weather to small perturbations.

The brain, being analog, is able to grasp images so much better. The brain is just designed for comparing images and some patterns - patterns in space and patterns in time - which we do amazingly well. Computers can do it, too, but not in anything like the same kind of flexibility.