In a recent interview, Jeff Bezos highlighted:
Amazon is not too big to fail...In fact, I predict one day Amazon will fail. Amazon will go bankrupt. If you look at large companies, their lifespans tend to be 30-plus years, not a hundred-plus years.
Jeff Bezos made a great point, and he reminded us that companies that have scaled will not necessarily survive the next business wave, especially if new technologies becoming commercially viable will ask for a wholly new business playbook, to which existing giants can hardly adapt to.
While this fear is probably acknowledged by most of the tech giants (they are well aware of the evolving tech landscape) that puts them in a position to behave like startups to try to stay on top of their game.
As highlighted in my previous article, one of the things that made Amazon survive the dot-com bubble was its ability to become a leaner company during the 2000s.
And as it grew Amazon retained its ability to be fast, obsessed with customer experience and extremely focused on things that worked.
While that has worked wonders, in terms of growth and ability to scale.
There is a certain threshold to which tech giants can't act anymore as startups, at least on their core business. Let me show you why.
Exponentially more complex
When a company scales to become a multibillion dollar giant, with hundreds of thousands of employees, it will also become exponentially more complex.
In the digital business world, we're all aware of positive network effects. Those make platforms more valuable as they scale.
However, as a platform has reached a certain threshold, those network effects become marginal, until they become negative and the scaled company becomes a burden to itself and to those stakeholders which contributed to its success in the first place.
We might call it, the paradox of scale.
Breaking implicit contracts
Each company that is building a viable business model has a set of implicit contracts. Those are informal loosely held agreements between the company and its key partners, that create value for all.
When Google launched its search engine, it made search go mainstream. That created a huge opportunity for everyone.
The Google's algorithm pushed more and more people to click on the list of ten blue links available in each of its search results page. Thus, making publishers the natural key partners for the aspiring tech giant.
However, a company to be successful often has to juggle with multiple value propositions. And while Google focused on growing its user base. Publishers providing free content to feed the growing beast, was among the most valuable stakeholders.
The implicit agreement was pretty simple "you (publisher) are going to fatten me (Google's search algorithm) in exchange for an endless stream of free traffic."
That implicit contract was based on the assumption that publishers would open their gates (by enabling indexation of all the content) to the Google's algorithms to let users find the most relevant articles through the search results pages.
As result, Google would monetize its pages with text-based ads.
This implicit agreement worked pretty well, as it could balance multiple conflicting value propositions. Users could find any kind of content on the web, for free. Publishers could get traffic against their pages which could get easily monetized, as there was free traffic in abundance for all.
In exchange for aligning those conflicting value propositions, Google would make billions in advertising revenues as a side effect, for decades to come.
That implicit contract started to be broken (unilaterally by Google) when the search engine unleashed its AI, starting in 2016, to provide more and more functionalities, extracting content from the web to provide direct answers.
The new unbundling age driven by tech monopolies
The last example of Google extracting content on the web to provide direct answer from the browser thus (potentially) shrinking visibility for content providers.
Publishers which got selected by the Google's algorithm for almost two decades, based on page views, suddenly started to be selected for the ability of the content to provide certain answers or for their strong brand.
In short, Google, a tech giant, started a process which in the business world can be defined of unbundling. That is not new, it's something that started with the web.
And the publishing industry went already through this process. Before the web, you needed to buy a whole newspaper to read that single, or a few articles you wanted to.
The web unbundled the newspaper, by making available online only the articles you wanted to read. And Google helped unbundle the newspaper by making it easy to find any article online.
At the same time the tech giant also enabled publishers to easily monetize their pages through Google Ad Network. This balance worked wonders for almost two decades and it enabled new publishing outlets to rise.
As Google extracts more and more content from publishers, that (seemingly) safe real estate, that publishers gave for granted might soon to start eroding under their feet. To be sure, as of now, there is no proof of this happening.
Indeed, as more users access Google through direct answers, they might perform more queries, thus growing the volume of search even further. However, over time we can expect this process to turn against the publishing industry.
That, in turn, requires a change in business models of publishers, which as of now optimized for page views. Those same publishers need to learn how to monetize their pages more effectively. Which calls for alternative monetizations strategies, that go beyond advertising.
Many publishers (NY Times for instance) successfully completed this transition. Many others stumbled in the process.
Those same publishing outlets born as representation of the new digital media models (like BuzzFeed, AOL, Yahoo, HuffPost, and Vice Media) started to massively lay off in 2019, which made many question whether there was viable business models after all for digital publishing.
What's different today?
With the rise of the web, consumers got the control over who would disrupt the next industry. Many processes were bottom-up driven. And the web brought an immense opportunity for people across the world to be connected.
As tech monopolies started to build up. Those tech monopolies also got hundreds of billions in budget and massive distribution pipelines. Therefore, something like the web, envisioned as a bottom-up technology, became primarily top-down driven.
Today companies like Amazon and Google can push their technologies to billions of people across the world. While this process will not last forever. If those companies do keep control over digital distribution pipelines, they might dominate for at least the coming decade (unless they are broken up by regulations).
Adults behaving like kids
On a recent thread on Twitter it was exposed how Amazon pretty much copied a shoe brand called Allbirds, by launching a clone shoe on Amazon store.
Companies like Amazon, Google and Facebook, nonetheless their size, still act - in certain circumstances - as aggressive and disruptive startups. While this might be seen as a good trait for small companies with a complete lack of resources, it is not certainly so for large tech monopolies.
Why so? Because their scale has potential to destroy, redefine and unilaterally change entire industries. And in many cases this isn't necessarily in the interest of users or consumers.
Thus, all is left for new companies, trying to enter a space dominated by those tech giants, is just "a fistful of dollars."
A Fistful of Dollars
As tech companies build business models wired for growth, those models oten imply the ability to create sustainable ecosystems, where industries are built, and opportunities are created for all.
This sort of win-win situation is at the basis of the success of those companies. In short, while we all praise the aesthetics of the iPhone, what made this device really successful was the ability to nurture an ecosystem of developers willing to build any kind of app. That enhanced the capability of an otherwise relatively useful device.
When Facebook first started to scale, it was a very simple platform with extremely basic functionalities. As the company employed a lean approach, it also opened up its API to developers to access its data and build applications on top of it. That strategy enabled Facebook to scale more quickly, test the applications that worked, and make its users happier. However, as it scaled further Facebook closed and restricted its API access for several reasons (security, loss of control on the platform and business reasoning).
Usually, as companies scale up and their business becomes mature, they need to slow things down on the core business, keep as much control, and optimize for profitability. Which suddenly reduces the opportunities for previous key partners, and makes the previous implicit contracts suddenly fall.
And those that once had a viable business built on top of a scaling tech giant suddenly find themselves out of business.
Is breaking up tech giants the solution?
In this period voices of breaking up tech giants are intensifying. To be sure those tech giants are helping this process to happen. However, breaking those companies up is a top-down approach, which might be extremely dangerous.
As policy-makers struggle to make sense of how those companies work in the first place, they give for granted that by simply coming up with a set of rules to break them up might work.
However, I believe this is the wrong solution as it can have irreversible negative consequences that are wider than the problem it would solve.
We need to start over by redefining the problem.
Too big to mess things up
The companies that find themselves leading this digital age are not intrinsically bad.
At a certain point, scale becomes a problem that doesn't concern a company anymore, but it is a collective issue. Just like during the 2007-8 crisis we figured that we could not have banks that were too big to fail. Right now we're realizing that we can't have tech giants that are too big to mess things up.
In short, any company should be given the opportunity to mess things up, because they need to experiment, innovate and build new things. When they lose this opportunity that is when scale is a problem. Companies like Facebook and Google need to be continually experimenting on their core products. But as they do so, those experiments can become societal damages.
When Facebook changed its motto from "move fast and break things" to "move fast with stable infrastructure" it understood the collateral, irreversible damage it could make on its own business.
At the same time, the company didn't realize that at that scale, moving fast, might be extremely damaging for society.
So how do we solve that?
Restoring the American dream
Many think the American dream is primarily about rising to the top. However, the American dream might be as much about rising to the top, than falling back down again. In short, a complex system that enables only upward mobility is not sustainable as those that moved upward will reduce opportunities for those trying to reach the top.
As a few players take control of the market, they reduce the opportunities for new entrants to reach the top which make the whole premise of the American dream in jeopardy. Venture capitalists, lke Peter Thiel, PayPal co-founder expressed this idea clearly in the book, Zero to One.
He explains how companies that stay successful for long-time keep secrets. And among those secrets there is the fact they are monopolies. You won't never hear a monopoly defining itself as such. Because according to this business view you won't make much money in a free competition scenario. Quite the opposite, in that case, margins will be so thin that your incentive of doing business is marginal.
In a monopoly scenario, the company holding monopolist position can retain fat margins for decades. But in order to do so it has to prevent other from opening up new spaces, which can't be controlled.
Slow down tech giants from limiting competition
When a company has reached a scale in which it can't mess things up, as this would be a too high cost for society, regulation has the potential to slow down those tech giants.
While a regulation that tries to impose a corporate structure to those companies might actually do more harm than good. A regulation which slows those tech giants substantially can have a positive impact, without creating necessarily irreversible consequences for the market and the economy in general.
Thus, a good regulation might be that which slows down substantially those tech giants when they try to reduce competition, by using their distribution platforms.
For instance, among other things, the United States v. Microsoft Corp. antitrust case, in the 2000s did slow down Microsoft attempt to dominate the next wave of the web. That in turn created enough space and opportunity for other players to emerge.
Where we used to have a single company dominating the tech landscape, after about two decades we found ourselves in a tech oligopoly.
Can we hope and expect for the next decades to have many center of powers, yet none really in control, or able to hijack the whole system? If so, what do we need to avoid?
Final remarks
In this scenario, there are a few things we might want to avoid for sure:
- Unleashed AI: as AI evolves exponentially we don't have enough time to think things through and test them carefully enough to make them work at larger scale. Thus, one thing to avoid at all cost is to have unleashed AI which go on its own. This scenario seems still far from reality as the AI of major tech companies still needs a lot of human labor to work well at scale. But machine learning algorithms are evolving with a wider and wider degree of freedom. So once the human data curation is over, the unleashed AI might really have the potential to go on its own.
- No more elephants in the room: prevent scale when companies become too big to mess things up.
- Enable upward and downward business mobility: a market that works well can take care of many things. And in order for it to do so it has to enable people to reach the top. But also to fall back down.
(Disclaimer: The author is the Founder of Four Week MBA)