Babak Bagheri

Attention is a scarce commodity. This is strange given the fact that there are now over 6,000,000,000 of us humans on this planet. Surely, there should be a sizable audience for almost anything. Well, there is but not all that sizable. There are many reasons for this, but the core reason has to do with the limitations of the human brain. Yes, you read right; that magnificent instrument we all have in our skulls is limited. The important limitation here is our capacity to analyze and remember. We cannot possibly evaluate and recall the value of everything even a small fraction of humanity produces. So we rely on others’ judgments.

Small World Graph with Hubs

Not only do we rely on others’ evaluations, but we simplify even these second-hand judgements. The upshot of this human tendency is that we’ve created a world of “hubs” of attention. A very few people and groups, “hubs,” dominate our collective attention. Not only do the hubs dominate, but away from the hubs attention falls off exponentially.

In other words, points of attention form a “small world” graph with very big hubs. This power law of attention can be a boon for those who make up the hubs. So how do you become a hub? You’ve probably been given one answer by marketers: Niche Thyself. Basically, become a hub in a small group, then parlay that into becoming a bigger and bigger hub. The niche advice is probably the soundest one there is. But there are other things you can do.

Here’s a partial list:

• Do something stunning (good or bad doesn’t matter, but good is better).
• Do something encyclopedic (create a point of reference).
• Do something helpful (indispensable is even better).
• Connect others together (this is very popular these days).
• Ignore the hubs and go for the “long tail” (if you’re feeling clever).

You may want to make your own list along these lines.

Network effects had been neglected for quite a long time. The classical “reductionist” view of the world was simply this: if we understand the rules that govern the pieces of the universe, then we can easily deduce large-scale behaviors. The past century has shown that this is wishful thinking at best.

Much has now been said about the level of complexity that interconnections among simple components introduce. This appreciation for network effects has not yet been exploited for engineering purposes fully. The old reductionist views still dominate in most engineering disciplines. The same is true about other practical arts; we do not yet have good ways of purposefully exploiting network-introduced complexity.

The reasons for this neglect are deep. To exploit the kind of complexity that network connections bring about we need to look at design differently. We need to view design as guidance instead of control. Complex systems do not respond well to direct control; they can, however, be guided and steered. We know very little about techniques to do this kind of guidance and control effectively.

Japanese Zen Garden (National Geographic)

There is one group, though, that has been struggling with these methods for some time: teachers and trainers. Living systems, especially people and groups of people, present exactly the kind of complexity that requires guidance and steering. Unfortunately, the track record for teaching and training is not stellar.

Perhaps the most effective of trainers have been spiritual teachers, for example Zen masters. Zen spiritual leaders have instinctively understood that guiding a complex mind requires meticulous attention to the environment. These environments are arranged to evoke the proper frames of mind that encourage the right mental changes.

We should start thinking of the machines we build as potential trainees and students. Our task is to design into them the kind of complexity that can be guided as we need. If a machine is simple enough to be controlled directly (“programmed”), then it’s probably too simple to do anything really interesting.

Software-controlled machines have been around for some time now. But we’re nowhere near a world filled with robotic helpers. There are deep reasons for this. One important reason is this: we’ve been using the wrong approach to program the machines.

Techniques for programming robots have an odd quality about them: the software contains numerical methods combined with symbolic heuristic methods. The numerical methods are essentially those used in computational physics. The symbolic methods are essentially those used to analyze symbolic phenomena like language and “mental processes”. Both sets of methods are analytical in nature. They are invaluable in understanding the world, and that understanding is very useful in creating robotic software. But I believe it is a mistake to use the methods directly.

A Neural Network

Let’s see what a different approach may look like. There is one set of relevant methods that is synthetic in nature: these are “computational kernel” methods. The set includes cellular automata and fractals. Ironically, these synthetic techniques are often proposed for analyzing physical phenomena. They may be useful analysis, or even paradigm-changing as some claim. But they are much more promising as a basis for robotic software.

To control a machine, we do not need to program into it sophisticated techniques for understanding how machines work. We just need to provide the right computational kernels that, in aggregate, lead to sophisticated behavior. This kind of approach has been seriously attempted only by “neural network” (and their close cousins “probabilistic graphs”, “bayes nets”, etc.) researchers and practitioners . Unfortunately, neural networks have suffered from the analysis-synthesis confusion as well; they have been constrained by the analytical need to model biological brains.

It’s time to get beyond this confusion and design synthetic techniques that learn the behaviors we want. We can then use analytical techniques to understand why the systems we create behave the way they do. But that analysis will be separate from the computational kernels we use to program them.

True entrepreneurship is disruptive. You can certainly be in business without being disruptive, but I wouldn’t call that true entrepreneurship. If assumptions are not put to the test and, at least, revalidated, then the promise of enterprising work is betrayed. A new enterprise must try to cross “regions of unfitness” in the fitness landscape. Trips across these regions of unfitness are challenging. Images of mountain climbing and arctic expeditions come to mind.

Mountain Climbing in India (The Silk Road Group)

During these hazardous trips, it certainly pays to be well-prepared. But it pays even more to be agile and prepared to do whatever is necessary to get across. Just attempting this kind of agility changes our fitness profile. What looks like an impossible path to the unpracticed is often a cake walk for the seasoned mountain climber.

Here’s an obvious point to keep in mind: live to climb another day and take another trek. Fortunately, few business situations are hazardous to one’s life and limb. There are business analogies to sudden death that one should avoid; they are mostly related to accounting and the law.

In the normal course of events, the hazards of entrepreneurial treks are not nearly as dangerous as we imagine. Disruption is challenging, but rarely life threatening.

Traction, be it sales or just attention or “eyeballs,” is a must-have in the entrepreneurial pursuit. Gaining enough interest in each step to be able to take the next one is essential.

So how do we get traction? For the answer we need to go back to psychology and the street savvy we’ve talked about. We should scan the social environment, with our “itch X-Rays,” routinely to detect itches that can be scratched. We should then use our social imagination to guess if solutions we find will stick. We should then do inexpensive experiments to see which of these guesses pan out.

Being able to do all this well is a challenge to say the least. So a good deal of mythology surrounds these abilities. We hear about the “guys with golden guts” whose every guess is right and can pick exactly the right people to get it all done. It would be nice if there were such heros, but in real life it’s usually persistence that wins. Some have even tried to quantify these abilities and claim to be able to tell you if you’ll succeed by comparing your background with historical data. There’s even a startup to do this kind of evaluation online! How’s that for itch scratching? Give us a little data and we’ll tell you if you’ll make it; yeah right.

Male Peacock (by Laurence Shan)

A lesson from the animal kingdom is worth keeping in mind. Evolution is the quintessential traction detector. What is the main lesson from evolution? Lots and lots and … lots of trials. Another important lesson is: call attention to yourself and what you’re doing. Don’t think that helps? Take a look at the male peacock.

How fast can you earn money? Are there bounds, and if so what are they? We all hear the statistics about Gross Domestic Products: the rates of GDP growth which vary from -10% to 10% or so; although the extremes are rare. Rates of growth for smaller groups or individuals can fluctuate much more wildly. But what is the upside limit, if any, and how does one approach it?

Here is a recent claim form one of the few successful “dot-coms:” from $0 to $170 million in three years. (The claim is fairly legitimate. It’s the story of “mint.com” being sold to Intuit after three years of operation.) Can we use data like this to come up with the earnings speed limits we’re looking for? I think the answers would be interesting if anyone did a study like this. The highest rates of accumulation would probably go to lottery winners, then traders of various kinds (commodities, stocks, etc.), then entrepreneurs and VCs with earnings capitalization, then the rest. In other words, the highest rates of accumulation would go with the lowest probability events.

John L. Kelly

What does all this mean to enterprising folks? It means the careful market experiments we conduct have to take into account the “hail mary” or “home run” factor. We should have at least one “bit bet” type experiment going at any given time, but we should try many more smaller bets with higher probability. This kind of calculation is familiar to gamblers and some traders. William Poundstone gives an entertaining account of a particular approach to this betting problem in his book “Fortune’s Formula.” It’s the story of what I call proportional betting invented by John L. Kelly. The basic idea is to modulate the amount you bet by the odds the market offers and how likely we think success is. Seems obvious, but most people forget ignore both the problem and Kelly’s and others’ ideas in the heat of battle.

Are experiments the only way to navigate the bootstrap process? Are there no rational shortcuts? The answer, as usual, is “yes, but.” The alternate or complementary approach is what I call “social imagination:” the ability to imagine the effect an enterprising act will have on a group. This is really an exercise in imagination, not calculation. We don’t have any formulas to compute what the effect of any act will be on a complex social environment. But we humans seem to be endowed with brains that can imagine various social outcomes in uncanny ways.

Adult-Born Neurons (Veronica Piatti et. al.)

Recently, there have been a number of publications and discussions about these human abilities. They all point out that our social imagination is related to the constituents of our brains and how they are wired, or, more accurately, continuously rewired.

Social imagination seems to be built into us in ways that we’re just beginning to understand. A very dramatic example of these abilities is attributed to the “mirror neuron system” of the brain. The system, discovered by accident in an Italian laboratory, allows us to copy the brain state of another person by mere observation.

Apparently, our abilities go beyond mirroring: we can play out scenarios of what people will think. There are, most likely, severe limitations here. I don’t believe we have social crystal balls built into our brains. It’s also most likely that people differ a great deal in their capacity for social imagination like they differ in every other capability.

To complement actual experiments, then, we’re well advised to carry out “thought experiments” to see what the possible outcomes may be. These imaginative musings should be guides for framing the actual experiments and hopefully they will increase the probability of success. As with all other mental abilities, social imagination will improve with practice; so the more we do this the better we’ll be. Hence the value of experience.

The line between stupid and brilliant innovation is blurred. People have tried to systematize and show the difference in dramatic ways. Guy Kawasaki has a graphical way to illustrate the difference in his “The Art of the Start” book. He points out two dimensions: how novel an innovation is and how much people like the innovation. Presumably, the stupid innovations are the ones that are novel, but nobody likes.

The Art of the Start

The problem with Guy’s illustration of stupid innovation is that it’s static. Both dimensions change over time, sometimes very quickly. We’re familiar with how fickle people’s tastes can be. But the other dimension, the novelty of an innovation, can also change rapidly. As you’ve guessed by now, the reason is our old friend subjectivity. What people consider novel today, they may consider old hat tomorrow.

So what are enterprising folks to do? Shooting a moving target is not easy. And the target is moving fairly quickly these days. A good answer, of course, is our old standby experimentation. The trick is to lower the cost of failure and do as many reasonable trials as possible as quickly as possible. I did sneak in a qualifier here: reasonable.  It’s probably best not to try patently silly things, but there are plenty of cases where patently silly things turn out to be exactly what’s needed. So the “reasonable” qualifier is a soft one.

The safe and usual solution has been to copy existing successes. It’s not an approach I like, but I don’t knock it. Empires have been built this way. The formula is: find something that’s been somewhat successful, then tweak and polish it. It’s safe if you can “execute,” hence all the recent spilling of ink about “execution.”

E. F. Schumacher

The business bootstrapping process should be a series of small steps. Each step should test one or more hypotheses about the market and produce enough interest and/or cash to lead to the next step. An important question to answer at each step is: how small should the step be? As always, there is no one answer for all circumstances. There is, most likely, no formula for determining the step size either. But the general guideline is: each step should be as small as possible. In general, credit for realizing this principle goes to E. F. Schumacher who wrote about it in his “Small is Beautiful” book; although, the context he was considering was different.

The main point Schumacher makes is that large “boil-the-ocean” solutions often do more harm than good. And the harm is often big enough that a correction is difficult or impossible. The same point is true about the business bootstrapping process. Each step should be so small that if it doesn’t pan out, then the next step can be a small correctional one. Like all principles of this kind, this one is easier to articulate that to implement.

Do the constraints that markets put on innovation help or hurt? The reigning consensus has been that they help. The constraints help presumably because they force innovators to husband scarce resources properly. Trying to scratch every possible itch in every possible way would be just too expensive. But any set of constraints in a human setting has unintended consequences.

Joseph A. Schumpeter

Let’s look at market constraints related to how money is invested and how results are vetted. To allow enough exploration to go on, investments have to be spread among as many choices as possible. To be fairly sure that experiments aren’t stopped prematurely, the size of the investments need to be adequate. A tiered approach to investment has evolved to address these constraints: invest progressively larger amounts in a large enough sample of attempts. Going from one tier to the next is a gate-keeping event; each gate forces a kind of Schumpeterian destruction. This all sounds well and good, if the destruction is not, well, destructive.

The difficulties, like the devil, are in the details. In a social environment with real people, many human factors come into play at the investment gatekeeping events. These factors include, not surprisingly, those pointed out by Cialdini in his “Influence” book.

Every self-respecting entrepreneur, therefore, knows that influencing and selling to investors is even more important that selling to potential customers. Most entrepreneurs then train their itch-detecting X-Rays on investors. Sometimes this works out, especially when the investors’ view of the market is essentially accurate and they reflect those views faithfully. Often, the entrepreneur ends up with an offering that pleases the investors more than it does customers.

There are, of course, many other devilish details at work here.