Book Summary & Highlights: Why Greatness Cannot Be Planned

Book Summary & Highlights: Why Greatness Cannot Be Planned



Pub Date:


Amazon Summary

Why does modern life revolve around objectives? From how science is funded, to improving how children are educated -- and nearly everything in-between -- our society has become obsessed with a seductive illusion: that greatness results from doggedly measuring improvement in the relentless pursuit of an ambitious goal. In Why Greatness Cannot Be Planned, Stanley and Lehman begin with a surprising scientific discovery in artificial intelligence that leads ultimately to the conclusion that the objective obsession has gone too far. They make the case that great achievement can't be bottled up into mechanical metrics; that innovation is not driven by narrowly focused heroic effort; and that we would be wiser (and the outcomes better) if instead we whole-heartedly embraced serendipitous discovery and playful creativity.

Controversial at its heart, yet refreshingly provocative, this book challenges readers to consider life without a destination and discovery without a compass.

About Author: Kenneth Stanley & Joel Lehman

Kenneth Stanley




I am the director of the Evolutionary Complexity (EPlex) Research Group at UCF. Our research focuses on abstracting the essential properties of natural evolution that made it possible to discover astronomically complex structures such as the human brain. Our work is in part an approach to artificial intelligence.

I developed a method, called NEAT (NeuroEvolution of Augmenting Topologies), that begins evolution with a population of very simple networks and complexifies the networks over generations by adding new neurons and connections.

We recently developed an extension to NEAT called HyperNEAT that can evolve neural networks with millions of connections and exploit geometric regularities in the task domain. Here is a page on fracture in CPPNs and HyperNEAT.

Another new approach that we recently introduced is called novelty search. Unlike most evolutionary algorithms, novelty search has no defined objective; instead it simply searches for novel behaviors. Nevertheless, it finds surprisingly robust solutions, raising questions about fundamental assumptions on why search works.

I discuss some of my research interests in several interviews that are available online: This audio interview (9/30/06) conducted by Tom Barbalet for discusses some of my general interests. In this text interview (12/11/08) with, I discuss Galactic Arms Race and my thoughts on automatic content generation for video games through evolution. A TV interview (on G4TV) from February 2010 also discusses GAR. In yet another text interview, I discuss GAR with Game Developer Magazine in April 2010.

Joel Lehman

  • Research Scientist


Author Presentations

Other Book Summaries & Related Resources

Contents I

Description Of How Evolution Creates Complexity Through Its Non-Objective Search Function

As Stephen Jay Gould has pointed out in evolution, once all the simple ways to live are exhausted, the only way to create a new species or niche is to become more complex [48]. In other words, there are only so many ways of being a bacteria. That’s why increasing complexity is almost inevitable if evolution is to continue. But these increases in complexity are not arbitrary. Rather, they reflect the properties of the world in which evolution takes place: Eyes represent the presence of light in the universe. Ears signify mechanical vibration. Legs are reflections of gravity, and lungs of oxygen.

In the usual interpretation of evolution, innovations like eyes or lungs might be considered objective improvements, increasing a creature’s ability to survive. But they can also be viewed as the inevitable tendency of a search with no final objective to accumulate information about its world. After all, there was nothing particularly wrong with the original single-celled organisms that possessed none of these fancy additions. They were surviving just fine. The only problem was that to do something new required reflecting some aspect of the natural world back into the DNA. Sight-driven behavior isn’t strictly necessary—it’s just that if you keep trying new designs through mutation, even though there’s no objective, eventually you will hit upon the fact that light exists. Then it will become a part of evolution’s accumulated inventory of information.

In a sense, over eons our bodies have become a kind of encyclopedia of facts about the universe in which they exist. Not only are many physical aspects of reality reflected in our bodies’ structure (for example, light, sound, gravity, heat, air, etc.), but evolution has continued for so long that we now actually encode incredibly specific details of the universe somewhere within us: Our brains remember which planets revolve around the sun and even the price of a bagel at the corner shop. The ability to learn and adapt over our lifetime has propelled the evolutionary information accumulator to a recent extreme. Of course, that doesn’t mean the process will stop with us. But what we observe again is that a search without a clear objective (evolution in this case) accumulates information as it moves from the most simple single-celled organisms to the most complex animals. That’s why the creatures of Earth have become a kind of mirror held up to the world that reflects back in tremendous diversity the physical possibilities enabled by our universe.

This is where the magic happens. The novelty searches forces the robot to evolve its thinking. Stanley describes what happens next…

In fact, eventually the novelty-seeking robot will even have to enter the doorway on the far side because once again it will exhaust all the possibilities for novel behaviors that remain within the same hallway. The result is something very strange: A robot told only to seek novelty eventually learns how to avoid walls, navigate a hallway, and enter doors even though none of those are ever actually requested or rewarded as objectives. Following this logic, a push towards novelty seems to produce more sophistication than you might expect.At the same time, it might seem that this apparent success is simply a result of “trying everything” (which computer scientists call exhaustive enumeration). If you really have the time to try every behavior under the sun, eventually you’ll end up doing something that seems intelligent, but it might take you almost forever to get to it. That doesn’t sound like a smart approach, and it turns out that discovery in novelty search is deeper than simply trying every behavior you can think of. The reason it’s more interesting than that is that novelty search tends to produce behaviors in a certain order.

Order is a critical factor in search and discovery. In fact, the main reason we have faith in any kind of search is that we expect it to encounter stepping stones in a certain sensible order. For objective-driven search, what we usually expect is bad behavior before good behavior. In other words, we expect the quality of the behaviors to improve over the course of the search. In that way, the objective leads to a succession of discoveries that seems to make sense.[...]For novelties to be continually found, eventually the robot would have to discover that the world is made of walls and doors, and that robots crash into walls but fit through doorways.

The surprising and game-changing point Stanley is making is that is relevant to our lives is that if we use novelty search in our lives, it will take us to the places we want to be. In other words, if we use the criteria of “Is this interesting?” as a filter from which to choose opportunities in our life, we’ll bootstrap more and more complex way of viewing the world, which will create better and better end points.

In other words, if we’re willing to sacrifice the attachment to a specific outcome that comes with goal setting, we may actually end up in a better place than we could have ever set in the beginning.


The point is that novelty can often act as a stepping stone detector because anything novel is a potential stepping stone to something even more novel. In other words, novelty is a rough shortcut for identifying interestingness: Interesting ideas are those that open up new possibilities. And while it might sound wishy-washy to go looking for “interesting” things, interestingness is a surprisingly deep and important concept. In the words of the famous philosopher Alfred Whitehead [42]: “It is more important that a proposition be interesting than it be true.” W.T. Stace [43], another philosopher, adds that “the criticism that interestingness is a trivial end proceeds from a scale of values thus perverted and turned upside down.” Far from trivial, novel and interesting ideas tend to suggest new ways of thinking that lead to further novelties. The important point is that novelty (and interestingness) can compound over time by continually making new things possible. So instead of seeking a final objective, by looking for novelty the reward is an endless chain of stepping stones branching out into the future as novelty leads to further novelty. Rather than thinking of the future as a destination, it becomes a road, a path of undefined potential. This non-objective perspective captures better the spirit of processes like Picbreeder, evolution in nature, and human innovation—ratcheting processes that build stepping stone upon stepping stone, branching and diverging ever outward to everywhere and nowhere in particular. But there might still seem to be a problem. Chasing novelty suggests a kind of aimless uncertainty. How do we know where we’re going? But that’s exactly the point. The greatest processes of innovation work precisely because they are not trying to go anywhere in particular. In this sense, we’ve abandoned the false security of the objective to embrace the wild possibility of the unknown. Of course, there’s still reason for concern. Such a search for novelty still feels unanchored and perhaps even almost random. Would it not simply chart a course from one fleeting novelty to another? Why should we believe that such a process has any meaning to it? It’s natural to fear that hunting for novelty might not lead to anything meaningful. One of the main reasons for this kind of doubt has to do with information. The fear is that the only useful information for guiding search is the kind obtained through considering what you hope to find. But the truth is that novelty is no less information-rich than the concept of the objective. It’s just different information. In fact, the argument can be made that the information driving the concept of novelty is actually more plentiful and reliable than that provided by the objective, especially when you consider that the objective is often a false compass. Rather than relying on a false compass, novelty only asks us to compare where we are with where we’ve been. In short, objectives mean sailing to a distant destination with an unknown path while novelty requires only steering away from where we’ve been already. Deviating from the past is simpler and richer with information because we can look at the whole history of past discoveries to inform our judgment of current novelty. So it’s not unreasonable to believe that novelty is a meaningful engine for progress. Another clue to the importance of novelty in innovation is that humans tend to be very sensitive to it. Often we feel the urge to explore a particular path or idea despite being unsure where it might lead. Our intuitions and hunches often prod us in directions that might not be justified objectively but still lead to something different or interesting. So it’s no coincidence that the concept of interestingness comes up naturally when discussing novelty. When an idea feels genuinely novel, that’s often enough to make us curious. The idea interests us even if its ultimate purpose is unclear. This insight connects to another common myth about achievement. This myth of serendipity is that serendipity is an accident. The classic stereotype for serendipitous discovery is the mad scientist stumbling clumsily into some profound breakthrough. It brings to mind a cartoonish character accidentally exploding a bottle of peanut butter in a microwave oven only to discover the secret to anti-gravity. But this kind of caricature undeservedly gives serendipity a bad name because it’s so rarely a bumbling accident. The reality is that we humans have a nose for the interesting. We understand that if we take the interesting path, it may yet lead somewhere important, even though we might not know where. The history of serendipitous discovery supports this idea. If serendipitous discovery was simply accidental, then it wouldn’t take any particular special education or intellect to make such discoveries. For all we know, being a little disorganized or crazy might even be the best way to start. But that doesn’t seem to be the case in the real world because most major serendipitous discoverers are not fueled by crazy ideas. In fact, most are intelligent, educated, and accomplished.


My Kindle Highlights

  • We can reliably find something amazing. We just can’t say what that something is! The insight is that great discoveries are possible if they’re left undefined.
  • But the more important lesson of non-objective search is that it’s a powerful treasure hunter. However, instead of finding a particular treasure that you might have in mind, as it diverges through the search space it finds many treasures, all of which may be surprises.
  • The treasure hunter is an opportunistic explorer—searching for anything and everything of value, without a care for what might be found. To be a treasure hunter, you have to collect as many stepping stones as you can, because you never know which one might lead somewhere valuable.
  • And even if your own personal journey doesn’t end where you had hoped, the idea of the solitary inventor striving relentlessly towards her inevitable objective was always a myth.
  • Contrary to popular belief, great inventors don’t peer into the distant future. A false visionary might try to look past the horizon, but a true innovator looks nearby for the next stepping stone.
  • The moral is that just because an ambitious objective is ultimately achieved does not mean that it was realized because it was an objective. To believe that would be to believe in the myth of the objective.
  • “Instead of judging every activity for its potential to succeed, we should judge our projects for their potential to spawn more projects.”
  • “So if you’re wondering how to escape the myth of the objective, just do things because they’re interesting. Not everything needs to be guided by rigid objectives. If you have a strong feeling, go with it. If you don’t have a clear objective, then you can’t be wrong, because wherever you end up is okay. Assessment only goes so far. A great achievement is one that leads to more great achievements. If you set out to program computers but you’re now making movies, you’re probably doing something right. If you wanted to create AI but you’re now evolving pictures, you’re probably doing something right. If you imagined yourself painting but you’re now writing poetry, you’re probably doing something right. If the path you’re on does not resemble where you thought you’d be, you’re probably doing something right. In the long run, stepping stones lead to other stepping stones and eventually to great discoveries.”
  • To achieve our highest goals, we must be willing to abandon them.

Most Popular Highlights From Kindle Users

Most Popular Highlights From Goodreads Users