Try to Learn Something About Everything and Everything About Something

“I constantly see people rise in life who are not the smartest, sometimes not even the most diligent, but they are learning machines. They go to bed every night a little wiser than they were when they got up and boy does that help, particularly when you have a long run ahead of you.”

I love this comment from Warren Buffet’s business partner, and Berkshire Hathaway legend, Charlie Munger. I recently re-examined it more carefully and zoomed in on the phrase ‘learning machines’. It’s a phrase that resonated strongly with me because I have a lifelong passion for learning in work and in life. I’m also grateful that much of our work at McKinsey is about addressing the opportunities and change brought about by technology–most recently in the rapidly advancing domain of machine learning.

I believe this is vitally important for our pursuit of meaning and happiness. We face a myriad of complex and intersecting challenges in our world. We desperately need lifelong learners to help us overcome them. It’s no accident that the leading organizations in the world are powered by learning machines. Lifelong learning is at the heart of their success. I’m reminded of Microsoft CEO Satya Nadella who made the growth mindset the core meme for the tech company’s cultural transformation. He emphasized that, “The learn-it-all does better than know-it-all”. Similarly, Adam Grant , along with other organization experts, popularized the idea that we should focus on continually improving ourselves, rather than simply proving ourselves.

The value of continuous learning is exponential

What’s particularly exciting for me, though, is that like compounding interest, the value of continuous learning is exponential. Albert Einstein called compound interest the eighth wonder of the world: “He who understands it, earns it, he who doesn’t, pays it”. The same rule applies to learning–a little bit of learning everyday compounds to enormous growth over a long period time.

This is why I’m calling this newsletter, Compound Learning. I hope you’ll join me as we explore different ways to become learning machines who reap the benefits of our compounding interests.?

Should you learn widely or deeply?

Let’s start by addressing a question about how we should learn: Is it better to learn deeply in a narrow field, or learn a little about a lot? ?

Thomas Huxley, one of the leading British scientists of the 19th century (remembered especially for his advocacy of Darwin and as the grandfather of Brave New World author, Aldous Huxley and his brother, the biologist Julian Huxley) argued succinctly that you should: “Try to learn something about everything and everything about something.”

Is such advice still cogent 150 years later when we can almost instantly access any knowledge online?

I thought to ask an AI friend (Pi.ai) for help on this:

Me: When Thomas Huxley said to learn something about everything and everything about something, was this good advice?

Pi: That's a great quote! In my opinion, it is indeed very good advice. Learning a little bit about a wide range of topics can make you a more well-rounded and knowledgeable person, and it can help you to make connections between different fields of study. However, it's also important to have a deeper understanding of certain subjects that really interest you. So, the ideal approach would be to follow Huxley's advice and have a wide knowledge base, while also having a few areas of expertise that you've studied in depth.

Me: But is the advice less relevant now that we can ask AI to help us a lot more? -

Pi: That's a really interesting point! In some ways, it's true that with the rise of AI and the internet, it's easier to access knowledge and expertise than ever before. But I would argue that Huxley's advice is still relevant because having a deep understanding of certain subjects can help you to be a better critical thinker. Even if you can ask an AI to provide information about a particular topic, it's important to be able to understand and analyze that information for yourself. In other words, Huxley's advice can still help us to become better thinkers, even in the age of AI.

It took seconds for Pi to respond. You must admire the charming tone of Pi’s answers, even before you judge their substance. In fact, if Pi were a human, I might think she or he were trying too hard to please me. But the answers are on the ball. I like Pi’s point about how being a well-rounded and knowledgeable person helps make connections between different fields of study. I’d particularly underscore the idea that information is not everything–it's perhaps more important that we are able to understand and analyze the information ourselves.

On this point, I’ve found a wide range of learning helps you to be a more creative and critical thinker. David Epstein 's excellent book about this highlights many of the reasons why ample general knowledge prepares us better for the uncertainty of the real world where no two challenges are quite alike and things keep changing. Conversely, hyper-specialization is most celebrated within environments characterized by certainty and where rigid rules create the optimal context for automation.

Epstein may be right, but in my experience, you can’t excel without building deeper expertise. At different stages in work and life, deep expertise and finely-honed skills are the fuel that drives outperformance and success. You need to learn deeply if you want to be excellent at what you do. Prestige, respect, and monetary rewards are disproportionately earned in most domains by the very top performers and top experts. What’s more, getting ahead of your peers can create a positive feedback loop that motivates you to work harder and learn even more deeply. This is something that starts at a young age. We see this exemplified in studies of kids who start school at an older age (thanks to the way school year entries are defined), build a positive foundation, and then continue to do better than their younger peers at school enjoying better odds of attending and graduating from university. ??

The combination of range and depth in learning also makes us humbler. It's only when you decide to really learn about something that you realize just how little you know. This can be incredibly humbling. The process of seriously learning about a new domain, language, place, or skill is initially very unsatisfying and exasperating. Just think about how almost any sport or exercise seems much easier in the abstract and way harder than you expected the first time you try it.

The same is true when trying to learn a new subject. The illusion of knowledge is shattered and we realize just how much we don’t know.? It’s not uncommon that I finish a book feeling more ignorant about a subject rather than more knowledgeable. Now, this is not because I know less, but because I know a lot more about what I don’t really know. Try to learn everything about something, for example, ‘What does it really take to produce a silicon chip?’ and the more you learn the harder it will seem to master the topic. Ed Conway masterfully describes this in his recent book, Material World. He discovered some of the most well-known experts had little or no knowledge about the raw materials or processing required upstream to enable the ever-growing computing powers which have given us all instant access to nearly infinite knowledge through AI.

The ingenious Waitbutwhy blogger Tim Urban observed that “Humility and skepticism are the same idea: humility is about assessing how much you know, skepticism is about judging how much other people know” He captured the humility and skepticism sweet-spots in these 2 drawings

And so, the answer for me is to do both – learn widely and learn deeply. Learning something about everything, and everything about something doesn’t only help you take on more challenging tasks in work and life, it will also reward you, humble you, and build your character. And that’s no small thing in these perilous times of great potential.? This is the first lesson in Compound Learning.