Australasian Science: Australia's authority on science since 1938

Can We Program Safe AI?

Credit: iStockphoto

Credit: iStockphoto

By Steve Omohundro

Tomorrow’s software will compute with meaning and be much more autonomous. But a thought experiment with a chess robot shows that we will also need to carefully include human values.

Steve Omohundro is President of Self-Aware Systems.

To view this article subscribe or purchase a yearly pass here.