The depth and breadth of what GP can do just isn't known by the techies. This book should scare those that are content to repeat the same old design rules. The book is a bit dry for someone with only a passing interest, but I think that was the author's intent: show in unhyped, and no-uncertain terms that GP can do what we do. For someone with a curious mind, this is proof of a brave new world.

Since the "look inside" doesn't contain the toc, here it is from Barnes&Nobles:

Table of Contents
1 Introduction 1
2 Background on genetic programming 29
3 Automatic synthesis of controllers 49
4 Automatic synthesis of circuits 129
5 Automatic synthesis of circuit topology, sizing, placement, and routing 175
6 Automatic synthesis of antennas 205
7 Automatic synthesis of genetic networks 221
8 Automatic synthesis of metabolic pathways 229
9 Automatic synthesis of parameterized topologies for controllers 281
10 Automatic synthesis of parameterized topologies for circuits 301
11 Automatic synthesis of parameterized topologies with conditional developmental operators for circuits 341
12 Automatic synthesis of improved tuning rules for PID controllers 367
13 Automatic synthesis of parameterized topologies for improved controllers 387
14 Reinvention of negative feedback 413
15 Automated reinvention of six post-2000 patented circuits 421
16 Problems for which genetic programming may be well suited 483
17 Parallel implementation and computer time 515
18 Historical perspective on Moore's law and the progression of qualitatively more substantial results produced by genetic programming 523
19 Conclusion 529

Since using evolutionary algorithms for my work, it is easy to see how many of the current EAs can be used to solve or tackle various real world problems. But what Koza does once again is to argue the case that GP is more than just an optimization algorithm but instead an algorithm that tries to show what AI should do and how user and AI should interact to solve a problem. Once again numerous examples are given, with detail on how problems are laid out so as to get the best results from the GP. Koza shows that with well thought out planning GP's can be applied to all sorts of fields.
In one of the chapters he presents the characteristics a problem should have for GP to be applicable.
All-round Great work, my advice get all his books and digest how he approaches various problems with GP. This example format Koza uses is far more useful than talking about what GP is and its theory. Though for a good intro into Evolutionary Algorithms including GP get either Foundations of Genetic Programming or an Introduction to Genetic Programming. An all round good intro is Introduction to Evolutionary Computing.