Actually no. The evolution mechanism is really robust.
Basically, if you have a bunch of random individuals, and the 'evolution' just mashes a bunch of the better ones together, you'll see the increase in fitness occurring. But it's not just a small effect : almost any crazy 'mashing together' method works, and the adaptation will spark off unbelievably quickly.
I know this because I did this for my PhD back in 1995. I had a choice then between going the Neural Net path, and playing around with the Genetic Algorithm/Genetic Programming stuff. Simple experiments proved that making NNs 'do the right thing' was a fairly tricky process of getting things set up right (and your formulae had to be right, etc : a fairly sensitive procedure). But the Genetic stuff was amazingly robust : almost any crazy method of crushing individuals together will produce remarkable innovation and learning (on a population basis).
But don't take my word for it, write a small piece of code yourself. The literature makes it sound like a more exact science that it needs to be. As I said, almost any 'mashup' method will work - the 'evolution thing' will simply find a way to 'protect' the important stuff.
So while this looks like 'old news' in some ways, I'm glad that they've got an eye-opening application : More people should know how much the computer guys can add to the biological evolution debate.