The original version of this story appeared in Quanta Magazine.
If you’ve been making the same commute for a long time, you’ve probably settled on what seems like the best route. But “best” is a slippery concept. Perhaps one day there’s an accident or road closure, and your fastest route becomes the slowest.
Scenarios like this are also a challenge for researchers who develop algorithms, the step-by-step procedures that computers use to solve problems. Many different algorithms can solve any given problem, and the question of which is best can be frustratingly ambiguous.
For example, imagine an algorithm that’s designed to find the fastest route between two points. There are lots of