I have spent some time listening to the two sides of the AI (and the future of jobs) forecasting debate. From where I sit, Tyler Cowen has the more optimistic take. On the other hand, you have the AI Futures folks. I read their AI 2027 last summer, and from my recollection, its forecast was directionally strong, but too fast, I think. They recently came out with this new report, AI 2040, which I have not yet read. But I did listen to what I believe is the gist of it in a two-hour podcast the other day.

As I listened, I wondered what Tyler Cowen might say in response to Daniel Kokotajlo’s arguments. So, I assembled a prompt for GPT-5.6 Sol, as one does these days, asking it to stage a debate between Kokotajlo and Cowen using their latest available materials and content, something light I could read after a hard day of work. The result, which you can read below is quite good. And I am deliberately presenting what GPT 5.6 sol gave me back, largely untouched, because 1) there is not much I could add given the time constraint of writing this essay 2) I believe that the “medium” itself is the message: The synthesis itself makes a case about the subject matter.

The Crux of it is, or at least part of the crux of whole debate, is that Kokotajlo assumes that AI capability growth may outrun institutional adaptation, while Cowen assumes that institutional friction, expanding demand and human preference will remain powerful even after capability becomes extraordinary. My reading of it is that Cowen offers the stronger model of the next several years; Kokotajlo identifies the regime change that becomes decisive if autonomous AI research and general-purpose robotics advance rapidly.

Here are the References synthesized into the debate:

So you can read (or watch) the source materials for yourself.

Cowen, T. (2026, July 8). Human life in a post-AGI world. Google DeepMind. https://tylercowen.com/human-life-in-a-post-agi-world-talk/

Cowen, T. (2026, June 28). My ARC talk on AI and jobs. Marginal Revolution. https://marginalrevolution.com/marginalrevolution/2026/06/my-arc-talk-on-ai-and-jobs.html

Cowen, T. (2026, May 13). Some non-obvious reasons why AI will create some transitional problems in employment. Marginal Revolution. https://marginalrevolution.com/marginalrevolution/2026/05/some-non-obvious-reasons-why-ai-will-create-some-transitional-problems-in-employment.html

Roberts, R. (Host). (2026, March 30). AI, employment, and education (with Tyler Cowen). In EconTalk. Econlib. https://www.econtalk.org/ai-employment-and-education-with-tyler-cowen/

Pangambam, S. (2026, July 13). Transcript of Daniel Kokotajlo interview: Diary of a CEO podcast. The Singju Post. https://singjupost.com/transcript-of-daniel-kokotajlo-interview-diary-of-a-ceo-podcast/

The Diary Of A CEO. (2026, July 13). He risked everything to warn you: No one is ready for what’s coming, and the AI companies know it! YouTube.

Veld, S. (2026, January 11). What happens when superhuman AIs compete for control? AI Futures Project.

*** GPT 5.6 Sol Synthesis** *

Moderator: By the 2030s, will most people still have jobs?

Daniel Kokotajlo: Not if companies successfully build superintelligence. The usual response—“technology destroys some jobs but creates new ones”—works only while humans retain capabilities machines lack. Once AI is better, faster, and cheaper than humans across essentially every cognitive task, it can perform the newly created jobs too. Add sufficiently capable robotics, and eventually almost all economically useful human labour becomes technically replaceable.

Tyler Cowen: That moves too quickly from technically possible to economically and institutionally implemented. Economies are not benchmark suites. Firms, governments, laws, buildings, energy systems, professional norms and consumer preferences change slowly. Electricity took decades to diffuse fully. Even very capable AI must pass through human organisations, and those organisations are full of bottlenecks. I expect substantial disruption and more leisure, but not the disappearance of employment.

Round 1: Does comparative advantage save human labour?

Cowen: Even when one party is better at everything, comparative advantage can preserve trade and specialisation. Humans will remain useful where our participation is legally required, socially preferred or tied to trust, legitimacy and personal meaning. People will pay to see a human musician, talk to a human political representative, receive human reassurance or experience something created by a particular human life.

There will also be enormous new sectors: gathering real-world data, conducting physical and biomedical experiments, integrating AI into institutions and helping different societies adopt it on their own terms. Humans may use AI throughout these jobs, but that does not mean the humans vanish.

Kokotajlo: Comparative advantage does not guarantee that wages remain high enough to sustain a mass labour market. Horses technically retained comparative advantages after automobiles arrived; their economic role nevertheless collapsed.

Your examples are plausible transitional jobs. But an AI that can design experiments, operate robots, persuade people, administer organisations and rapidly improve the relevant technology will progressively absorb them. Eventually the remaining human jobs exist because society politically reserves them for humans—not because humans are economically necessary.

Cowen: But “politically reserved” is not a trivial exception. Politics, liability, status and preference are part of economic demand. We do not consume only the cheapest technically adequate output. We consume stories, identities, authenticity and relationships.

Kokotajlo: Agreed—but that supports a boutique market for human authenticity, not necessarily employment for billions of people.

Round 2: Why has mass unemployment not appeared already?

Cowen: The current evidence should reduce confidence in imminent labour-market collapse. Even young-worker unemployment has not clearly broken from its pre-AI trend. AI-exposed work is changing, but aggregate employment is not falling off a cliff.

The more realistic near-term problem is transition. New jobs may be concentrated in slow, regulated sectors such as energy and healthcare. Employers may struggle to identify who is actually good at supervising AI. Governments may spend money poorly because they cannot distinguish competent AI-enabled workers from people producing polished-looking nonsense. That can create painful mismatch without creating permanent mass unemployment.

Kokotajlo: Current employment data are a lagging indicator of the scenario I am worried about. Frontier companies are not trying to automate the whole economy first. Their sequence is more like:

1. Automate parts of AI research.

2. Use that acceleration to develop much more capable AI.

3. Deploy the resulting systems across the economy.

Therefore, widespread unemployment may arrive only after systems have become strategically powerful. Waiting for unemployment statistics to prove the danger could mean waiting until the crucial decisions have already been made.

Cowen: That depends on a fast intelligence explosion. I assign more probability to bottlenecks, diminishing returns and imperfect deployment. Humans will slow the process even when the underlying models improve quickly.

Kokotajlo: Yes. The disagreement is largely about whether AI research automation produces an unusually fast takeoff. If progress stalls, your account becomes much more plausible.

Round 3: Will AI create more work—or make work optional?

Cowen: AI is already making some highly motivated people work more, not less. It raises the return to initiative: one ambitious individual with agents may accomplish what previously required an organisation. The immediate response for young people should therefore be to learn these systems intensely rather than assume there will be nothing left to do.

The winners may not be conventional rule-following professionals. They may be unusually curious, energetic people who repeatedly experiment with the technology. Intelligence remains valuable, but initiative, judgement, charisma and the ability to discover worthwhile problems become relatively more important.

Kokotajlo: That is good advice during the transition. In the late 2020s or early 2030s, many jobs may indeed consist of managing teams of agents. But “learn to manage AI” is not a permanent refuge if the AI eventually becomes better than you at managing AI.

I expect a period in which AI greatly increases individual productivity, followed—conditional on superintelligence—by a world where human employment is largely a political choice.

Cowen: You are describing the technological endpoint. I am describing the lived economic path. That path might last decades and contain enormous quantities of work, entrepreneurship, relocation and institutional rebuilding.

Kokotajlo: And I worry that the path could compress into several years.

Round 4: Who loses first?

Cowen: Not necessarily the poorest workers. A particularly vulnerable group is the highly paid, upper-middle-class knowledge worker whose advantage consists of processing information within established systems: consultants, lawyers, administrators, junior analysts and some academics.

They may remain employed but suffer a large status and income reduction. A partner earning $1.5 million might become a manager in an energy company earning $300,000. That is not destitution, but it could produce intense political backlash because these people currently possess disproportionate cultural and institutional power.

Kokotajlo: I agree that white-collar status disruption comes early. But I would emphasise entry-level positions. If AI performs the basic writing, coding and analysis through which juniors learn, firms may hire fewer beginners. Eventually, however, the distinction between junior and senior matters less: sufficiently capable agents threaten both.

Cowen: The apprenticeship problem is real. We will have to redesign education and employment so that people learn by supervising, testing and challenging AI rather than by spending five years producing first drafts. I have argued that a substantial share of education should involve learning to use AI properly.

Round 5: Is income the main problem?

Kokotajlo: No. People need both income and power.

A citizen’s dividend, AI tax or broad ownership mechanism can distribute some of the enormous output produced by AI. But employment currently gives ordinary people leverage. Workers can strike, withhold expertise and make themselves economically costly to ignore.

If almost all production comes from AI companies, data centres and robot fleets, governments may become less dependent on the population. People could receive comfortable payments while losing political influence. A post-work settlement therefore needs durable democratic control, not merely UBI.

Cowen: That is one of Daniel’s strongest arguments. A wealthy post-work society is not automatically a liberal society. Concentrated AI capability could become a power magnet for corporations or the state.

But I resist designing the entire economy around the assumption that labour will become worthless. Prematurely freezing a particular redistribution system could entrench incumbents and slow the very growth that makes abundance possible. Build energy, housing, healthcare, research capacity and broad access to AI first.

Kokotajlo: The danger is that “wait until displacement is obvious” becomes “wait until the owners of AI possess overwhelming bargaining power.”

Closing statements

Cowen: AI will radically alter work, destroy particular career ladders and reduce the returns to some forms of intelligence. Yet human wants are expansive, institutions are slow and economic activity is not a fixed quantity. Expect turbulent reallocation, more experimentation, new human-facing work and eventually more leisure—not a permanent society in which virtually nobody works.

Start learning AI now. Develop initiative, embodied skills, judgement, persuasion and the ability to work on problems the models cannot cleanly specify.

Kokotajlo: Historical reassurance is unreliable when the technology being developed is a general substitute for human cognition and may accelerate its own development. If superintelligence arrives, the question will not be which jobs AI can perform. It will be which roles society deliberately keeps human.

Prepare before unemployment becomes the headline: slow dangerous races, solve alignment and control, distribute ownership, and protect the political power of citizens in a world that may no longer economically need their labour.

Subscribe now

A few weekends ago, I started building this real-time simulator of bacterial evolution and antibiotic resistance (calling it evodish).

I just got around to finishing it up.

Antibiotic resistance is still a very big problem. In the United States alone, more than 2.8 million antimicrobial-resistant infections occur each year.

In this simulator, you drop antibiotic discs into a digital petri dish, natural selection unfolds.

I tried to capture as much biology as possible without overcomplicating it (random mutations, horizontal gene transfer, metabolic fitness costs, etc.).

> 💻 Try it here: evodish.vercel.app

> 📺 Video Guide:

Subscribe now

Last Fall, I ate my own cooking, put my money where my mouth is. After my Postdoctoral Fellowship at Georgia Tech, I transited to a research affiliate role at the Institute and I decided not to take a new employment.

About a year ago now, I stumbled on a LinkedIn post, where a pertinent question was asked, just before a brief articulation of the obvious incursion of AI tools into knowledge work. The fellow wrote, “What’s left in research when so many things can be done by AI? 🤔 …”

Some people who might have found that take a bit hyperbolic at the time might not anymore, particularly if they have tried tools like CodeScientist, Autodiscovery, and Kosmos, to mention just a few.

My response was as follows:

"A researcher could, and probably should, deliberately increase their breadth (and depth) of knowledge/competency. Many aspects of research will be aggressively automated over the next few years (This is true for all knowledge work) So, insights (reads: your knowledge bank) would be ultimately highly priced in a world where some research can be done quasi-on-demand. And the 'insights' are going to scale to the extent to which one leverages AI; you probably don't want to be the third servant, in the Parable of Talents who buries the one talent received into the ground, and ends up with nothing. And this parable maps to what we will be seeing going forward. 5 to 10, 2 to 4, and so on. The talent is your knowledge of what you know is possible. The (research) questions you ask. It's probably the best time to be a generalist."

Today, my response could really use some workshopping, but that’s not the reason for this essay. The only thing I would add is that, as a hypothesis, we are approaching even more pronounced barbell territory: hyperspecialist or (hyper)generalist. A plausible scenario is that everything in the middle will be gobbled up by AI. We can argue about timeframes, but again, that isn’t the purpose of this essay. This essay is, in part, an attempt to show what acting on that hypothesis looks like in practice.

After my fellowship, I passed on a couple of opportunities that would have been great in the pre-ChatGPT era (we really need a name that rolls off the tongue for this). But as I was saying, history is no longer “settled”; it’s moving fast — too fast in some domains. The future is profoundly uncertain, and precisely because of this, actions matter more than usual.

And it was principally the barbell and the “moving history” arguments that propelled me in this direction, in spite of the fact that the move ain’t cheap, to say the least.

And now, with the privilege of hindsight, I realize I actually could have used some rest. The path through graduate school and a postdoc is fiercely intellectually stimulating, but undeniably stressful. Add the years spent navigating the U.S. immigration system as an international student, alongside the recent relentless pace of tracking the AI disruption like a hawk, and stepping back makes some sense.

Subscribe now

I have had a fairly eclectic academic journey so far, perhaps this exposes my generalist bias. I hold a PhD in Biochemistry and Molecular Biology. I did some work in yeast genomics and studied Caenorhabditis elegans early in grad school. As a senior graduate student and postdoc, I published several works on applied AI/ML in biomedicine.

One of the main ‘skill issues’ I’ve had over the past couple of years (and for the engineers reading, that pun is fully intended) arose simply by virtue of being in a research environment. It was the ability to take an idea and turn it into production-level software with all the bells and whistles. I could do bits and pieces, but not the full gamut.

To solve this, the core challenge of my break became building intelligent systems end-to-end: models, agents, backend infrastructure, and user experience. What people now call full-stack AI/agent engineering. It felt like a reasonable way to expand my wingspan. I was already adjacent to the field through a number of side projects, so this seemed like a natural escalation. It was a sufficiently hard problem, and increasingly, an important one, since the next iteration of knowledge work is clearly automation (for better or for worse). And how long the skillset itself will be “useful” simply depends on which Substack newsletter you read, or which AI lab CEO you listen to.

However, as I hinted earlier, my break soon turned into a much-needed respite. I worked less — by virtue of being more focused (and leveraging AI) — read more books, played video games, and exercised much more.

I’ll give an example. All my life, I had wrongly assumed I was not a good long-distance runner, despite being, at least by American standards, very active. These days, I run 10 kilometers most days of the week. (It’s crazy how we tell ourselves we are not good at things we simply haven’t tried enough.) Along the way, I built a holistic, bespoke personal operating system from the ground up, one that incorporates work, learning, exercise, rest, and more.

However, one of the main projects I am working, now close to an alpha launch, is an experiment to test a hypothesis on what knowledge navigation, consumption, and collaboration might look like in a world where research is commodified.

Over the next weeks and months, I will share more artifacts (essays, apps, videos) publicly, and I would be glad to hear your feedback. I will share my “in-the-trenches” micro-updates mostly on Substack Notes, and I will also collect them here. General essays will be on Episteme Engine, while technical AI and engineering deep dives will be on my AI blog — The Epsilon. Video updates will be shared here as well.

Calling this a career break is somewhat of a misnomer, more like building through an AI transition (admittedly, that doesn’t roll off the tongue either). The work didn’t stop; it changed shape. Whether this turns out to have been the right call is still an open question. But even if the barbell hypothesis is wrong (which I strongly doubt), a wider wingspan is not the worst thing to have built.

P.S.

1. If you are an experienced engineer, especially in the United States, looking for a new AI adventure around (scientific) research, biomedicine, or science education, feel free to reach out to discuss the possibility of teaming up. I have far too many projects and feature ideas, and too little time.

2. I am considering publishing a full length memoir essay at some point in the future, structured as a sequel to “Plans Are Overrated“, express your interest here.

I listened to the first part of this podcast on my 10k run today.

There are many threads running through the podcast, but I will focus on just one thread.

Dr. Alok Kanojia, whom I encountered for the first time today, eloquently explains that the ego is constructed from the labels and definitions we assign to ourselves, making it an inherently comparative entity. When we fall into the trap of comparing ourselves to others or copying what we see them pursuing (often driven by external conditioning from social media where we adopt others’ desires as our own) we end up chasing goals that do not align with our true selves. While allowing the ego’s comparative nature to fuel our ambition might lead to worldly success and gratify our desire to prove ourselves, it ultimately comes at the cost of genuine happiness because the ego is never satisfied and continually moves the goalposts. To find true fulfillment, he argues that we must step away from these externally programmed desires and peel back the comparative layers of the ego to tap into our authentic, intrinsic drive.

(As a Girardian of some sort myself, it wasn’t particularly hard for me to see that his analysis is drenching in the language of “Mimesis” and “Metaphysical Desire”)

This quote from the classic epistolary novel The Sorrows of Young Werther (published in 1774) by the German polymath Johann Wolfgang von Goethe, has to be the shortest best thing I have read on this matter at hand.

I urge the reader to read it carefully.

“Since we are so made that we compare everything with ourselves and ourselves with everything, happiness or misery lies in the objects we associate ourselves with. . . . The power of our imagination, driven by nature to elevate itself, nourished by the fantastic images of literature, raises up a series of beings of whom we are the lowest and everything outside ourselves seems more glorious, every other person more perfect. And that happens quite naturally. We feel so often that we are lacking so much, and just what we lack another person often seems to possess, to which we also add everything that we possess, and project a certain ideal contentment on top of it. And thus the other person is made happy, complete, and perfect, a creature of our own making.”

given the times we live in, this extract is even more telling:

“...nourished by the fantastic images of literature, raises up a series of beings of whom we are the lowest and everything outside ourselves seems more glorious, every other person more perfect.”

Literature?!

Talk about Social Media.

If Johann Wolfgang von Goethe could visit us for a day, I wager that he would lose his mind, and so would his compatriots.

Share

I have also published two essays on the subject matter in the past:

We Are All Copycats

Prestige as an Illusion

Subscribe now

An essay landed in a group chat the other day. I read it and started flooding the chat with messages, and then realized quickly that this probably wants to be an essay. So here we are.

The original essay, titled “The Prison of Financial Mediocrity” by , argues that younger generations, locked out of traditional wealth paths and facing accelerating disruption from AI, are rationally turning to high-variance “casino” systems (crypto, prediction markets, sports betting) as the only remaining sources of perceived agency.

As white-collar career ladders erode and social media amplifies status anxiety, gambling becomes less about ignorance and more about desperation under constraint. The author frames this as a structural, not moral, phenomenon and concludes that the winning move is to be “long the platforms”, the argument that because the house always wins, the only rational move is to invest in, or align with, the “casinos” extracting fees from the desperation.

(Another, more general side note on the original essay: I read what is going on as a symptom of late-stage capitalism, one in which pressure is no longer absorbed quietly but expelled through multiple “exhaust pipes.” The same blocked-agency pressure that vents economically through casino-styled systems is also venting politically (say, Groypers-styled movements). The casino is just one outlet. It is not the only one—and it may not even be the most dangerous.)

A False Dilemma

The essay quietly advances a binary:

1. White-collar work is cooked

2. Therefore, gamble

This framing collapses too many alternatives and overfits to a narrow slice of the economy. Even granting that many white-collar knowledge jobs are under threat from AI, the author underweights blue-collar and asset-backed paths (plumbing, construction, electrical work, welding, farming) fields that can scale into real businesses, compound locally, and remain stubbornly resistant to automation. These are not consolation prizes nor are they sexy but they are parallel wealth tracks that don’t depend on winner-take-all dynamics.

That critique stands. But there is another omission that matters just as much.

The Missing Third Option

What the essay leaves out is that AI does not only destroy ladders, it reshuffles where leverage lives.

The choice is not simply between grinding obsolete roles and betting your future on high-variance speculation. There is a third option: positioning oneself at the system level rather than the task level.

AI collapses the value of many individual tasks, but in doing so it raises the value of roles that define goals, set constraints, integrate outputs, arbitrate tradeoffs, and absorb responsibility when systems fail. These are not “AI-proof” jobs in the traditional sense. They are AI-adjacent leverage points, places where human judgment, accountability, and synthesis still matter precisely because the system has become more automated.

(Also, a friendly reminder that there is such a thing as the Jevons Paradox: while AI automates tasks, humans still orchestrate workflows, pushing expectations higher. There are legible, logical arguments that we should expect more work, not less, much of it entirely new)

The core of the argument here is not necessarily about learning the next hot skill or chasing “prompt engineering” as a credential. It is about understanding how AI reorganizes workflows and placing yourself where coordination, interpretation, and consequence still concentrate. That path does not necessarily promise the dopamine hit of a moonshot, but it preserves agency without requiring existential bets.

Gambling, But With a Seatbelt

On “gambling” itself, the sane position lies between moral panic and evangelism.

There is a categorical difference between capped, asymmetric optionality and full-blown, identity-level risk. Holding casino-styled financial assets as a speculative hedge is not the same thing as staking one’s future on memecoins or perpetuals. The essay claims to be descriptive, but its tone risks normalizing behavior that is, at scale, financially and psychologically ruinous.

The deeper problem is not ignorance of odds. Most participants understand the house edge. What they lack is a credible alternative path that feels agentic. When the baseline is “treading water indefinitely”, perpetual movement without motion, even a slim chance of escape starts to look rational.

The Inflation of What Feels Necessary

Another blind spot is excessive upside-seeking masquerading as inevitability. Not everyone is merely seeking dignity or stability; many are seeking extraordinary outcomes in a world where most outcomes are, by definition, ordinary.

Even venture capital is structurally a form of gambling. Most startups fail. A tiny fraction generate outsized returns. The difference is that good VC-style bets often leave participants with something even when they fail: skills, networks, judgment, and optionality (conditioned on who the participant is, of course)

Pure gambling leaves none of this behind.

That distinction points to the strongest corrective insight.

The Only Bets Worth Making

The best bets are those whose failure modes still resemble success.

Learning can compound even when companies die. Reputation can survive even when products don’t. Skills can transfer. Networks persist. Optionality expands. These are antifragile payoffs. Lose the bet, and you are still better positioned than before.

Pure gambling offers no such cushion. Lose, and you are strictly worse off. Win, and you may still be worse off psychologically.

All of these begs the question: what is even gambling in the context of these various assets that I am, admittedly, not terribly familiar with?

One way to answer this via negativa is, it is not pure gambling if the failure modes still resemble some form of success (and I know the devil is in the details, but I’m not ready to spill more ink here; reasonable people can fill in the gaps as they see fit.)

But of course, there are more straightforward(?) way of thinking about it - does it involve creation of real value? and is it merely a game of chance?

A Better Framework

All of these invites better questions:

• Where does agency still exist in this system?

• Where does effort still map to outcomes?

• What paths offer convex upside without existential downside?

• What roles become more valuable because AI moves through the economy?

To conclude, we should address the cynicism embedded in the “Long the Platforms” thesis. The proposal is not to escape the prison of financial mediocrity by breaking the bars, but by repositioning oneself as the warden. To “own the casino” is to place a levered bet on the continued desperation of one’s peers; it presumes a steady population that remains desperate enough to gamble, yet solvent enough to pay the rake. Structurally, this is a short on broad-based human flourishing. True agency shouldn’t be found in collecting tolls on the road to ruin, but in building the off-ramps.

Subscribe now

I saw someone online the other day who claimed to be a “polymath.” And of course, the last person who would ever use that word to describe themselves is a genuine one—at least to the extent that such a thing is even possible these days. It struck me as a kind of Dunning–Kruger variant, or maybe just the plain old vanilla version.

It reminded me of when I first began reading fine books. When I came to the United States, and suddenly buying books wasn’t a luxury, I realized I couldn’t even come up with a list of ten really interesting titles to read.

Today, if you locked me in a room for five years and threw away the key, I wonder if I will be able to finish the books on my reading list, including those in my anti-library (see below).

There’s a certain irony to all of this. The more one learns, about the nature of things, about how the world works in its elastic, interwoven way, the clearer it becomes that the well is too deep. Knowledge doesn’t expand into mastery; there is a sense in which it dissolves into mystery. The horizon keeps receding.

Related: On Antilibrary

Nassim Taleb via Black Swan:

“The library should contain as much of what you do not know as your financial means … allow you to put there. You will accumulate more knowledge and more books as you grow older, and the growing number of unread books on the shelves will look at you menacingly. Indeed, the more you know, the larger the rows of unread books. Let us call this collection of unread books an Antilibrary.”

Subscribe now

There was once talk about AI as a leveler. I’m not sure how common that claim is anymore, but I’ve always thought it was off the mark. (I recently heard the idea parroted on some podcasts lately prompting me to write this.)

Think of intelligence in two forms: “raw” and “cooked.” Raw intelligence is what an AI model embodies, sheer pattern recognition at scale. Cooked intelligence, however, is different. It’s the lived context, the subtle navigation of a messy world.

AI struggles with that second kind. It doesn’t arrive with context baked in. Over time, context can be layered on, through careful prompt design, by building agents, or by extending memory systems (the kind I’m certain Meta is betting on, and OpenAI is aggressively implementing). Even then, the problem isn’t solved.

Because context is only half the story. What about the quality of your questions? What about the blind spots (what you don’t know that you don’t know?) Those edges define the limits of any intelligence, human or machine. And they’re exactly where the myth of AI as a leveler collapses.

There’s another dimension to this. It’s true that in many domains of knowledge work — particularly in task-centric contexts — the gap between expert and beginner has narrowed, and will continue to be. Yet one could also speak of a “greener field” hypothesis, where precisely because everyone has gotten a leg up, the advanced knowledge worker now holds the magic wand, the ability to do what was previously unthinkable (my go to analogy here is often the parable of the talents in the gospels).

But the real fracture appears on the economic front (which flows directly from the prior argument). This is where the “leveler” myth truly shatters.

AI is less a leveler and more a lever, dramatically amplifying the force of those who already know where to push (capital, know-how, etc.). The technology creates a dynamic where markets disproportionately reward those with sophisticated direction (and those who invest in them.)

A small class will thus guide AI toward novel, high-value creation, effectively setting the agenda for entire industries. The majority will find themselves executing more commoditized tasks, using powerful tools they don’t control, to fulfill objectives set by others.

This hierarchy will become self-reinforcing, as leading players reinvest their outsized gains into better models and proprietary data, solidifying their advantage and making the upper rungs of the economic ladder increasingly hard to reach.

There is precedent for this, of course, as such, I am unsure if many people, or anyone for that matter, would disagree with what we all think is coming.

Subscribe now

There is a sense in which by saying the things we are supposed to show, we are professing that we have lost the plot, either as an individual, or more importantly, as a culture. This applies specially if you can detect a tautological motif, or a kind of forced appendage in language use. It is worth noting that they can be hard to see as many are already normalized; and the normalization is really the point here.

For example, the obligatory use of the word “prompt” after a time is clearly stated, in some communities and culture goes a long way to show a broken culture of timeliness, or take deep work (I use this often myself), but what is wrong with just work? The modifier clearly betrays a landscape saturated with too much noise.

The pattern is everywhere once you tune your ear. Some can speak of “authentic cuisine.” Job ads promise “true ownership.” Even the truth sometimes can be insufficient, when one speaks of “honest truth.” I think social media birthed “real connection.” There is passion, and then there is “true passion.” And then there are the “active listening” workshops all over the place. And here is my ‘favorite’: “lived experience.”

Each redundant label is a linguistic tell, a nervous tick revealing the anxiety of its age. When substance fades, language rushes in to erect elaborate signposts, frantically assuring us that the thing still stands. But the very insistence is the confession.

And the normalization, like I intimated earlier, is really the key point, as it signals the silent triumph of the change.

The more syllables we stack, the clearer it becomes that we are circling an empty center, or that something is simply not right, trying to name back into existence what we can no longer, or struggling to, embody.

Subscribe now

Video Essay:

Text:

I.

When I was planning to visit Harvard to give a talk last fall, I looked up events I could attend while in Boston. I saw that Alan Lightman was going to give a talk at the Harvard Science Book Talk about his new book, and I quickly reserved a spot to attend. I hadn't read any of Lightman’s book at the time, but of course, I had heard a lot about him. I believe I first heard about him about a decade ago when, spurred by my intellectual interests, I began researching professors who had modeled their careers to encompass a wide variety of pursuits. He was the first professor at MIT to receive a joint appointment in both the sciences and the humanities. I recalled reading about him and reassured myself that I wasn’t that crazy after all (or may be I was).

When I got to the venue of the talk, he sat beside me outside the lecture hall for a while, I didn’t realize he was the one until someone yelled “Prof Lightman” or something to that effect. After the talk, I bought a signed copy of the book.

Alan Lightman's "The Miraculous from the Material" is a captivating exploration of the wonders of the natural world, viewed through the lens of a self-proclaimed "spiritual materialist" (I will come to this materialist bit in a minute). In this book, Lightman examines various natural phenomena, from the mundane to the spectacular (mostly spectacular than mudane), and elucidates how the material world, with its rules and laws, is capable of extraordinary displays of beauty and wonder.

Lightman's journey as a materialist, he says, began in his youth, where he meticulously constructed a laboratory in his bedroom closet. It was there that he embarked on his investigations of the material world, building pendulums and even a light-borne communication device. Through these experiments, he discovered that the physical world, or at least his little corner of it, obeyed reliable, logical, quantitative laws.

Lightman's fascination with the material world did not diminish his awe and amazement of natural phenomena. From the microscopic world of Paramecia to the rings of Saturn, Lightman found beauty and wonder in the material world and its laws.

One of the parts of the book I enjoyed the most is the way Lightman weaves together science and personal experiences. He recounts his first encounter with bioluminescence while returning to his island house in Maine, where he noticed the wake of his boat glowing. He writes about the science behind this phenomenon, explaining how it is caused by a chemical reaction in organisms like fireflies and algae.

Lightman's fascination with the natural world extends to the intricate structures created by living organisms. He writes about the spider web, considering it the most beautiful structure created by any living being other than Homo sapiens. Spiders utilize different types of silk for various purposes, including trapping prey and wrapping victims in a deathly cocoon-like structure. Lightman also elucidates the remarkable ability of spider webs to spring out and capture flying insects, a feat achieved through electrical attraction.

His curiosity extends to the skies, where he explores the physics of bird flight. He explains how birds generate lift through the shape of their wings and their forward motion, enabling them to seemingly defy gravity. There is also this intriguing phenomenon of birds flying in V formations, revealing how each bird, except the leader, conserves energy by taking advantage of the uplifting pockets of air produced by the bird in front.

I wish I had read books like this when I was much younger, it would have saved me the horror of memorizing some of my text books. Lightman writes so well about things you might otherwise think are impossible to explain. I probably wouldn’t have read the book if I hadn’t attended the talk, so I’m glad I did.

Subscribe now

II.

In addition to a general review of the book, I'd like to add a few commentaries. While this book is not about philosophy (I should state this very clearly), a few important, opinionated statements were made that I think warrant a full-fledged philosophical commentary. And those statements essentially can be summarized in what Lightman called spiritual materialism, which seeks to harmonize transcendent experiences with materialism.

I believe this framework faces a foundational challenge from Alvin Plantinga’s Evolutionary Argument Against Naturalism. Plantinga argues that if naturalism and evolution are true, our cognitive faculties—including those generating spiritual feelings—evolved for survival, not truth, rendering even materialist explanations of spirituality epistemically unreliable. For instance, sensations of cosmic connection or awe might be adaptive illusions fostering social cohesion or resilience, not genuine insights into reality. This creates a paradox I think: Lightman’s framework depends on neuroscience and evolution to explain spirituality, yet naturalism undermines trust in all cognitive outputs, including the scientific reasoning used to validate such spiritual materialism. And one could respond and say that spiritual experiences require no truth-claims beyond their material origins, sidestepping the argument’s focus on belief reliability.

But there is more to be said on this topic: the mysterious alignment between abstract mathematical truths and physical reality (as seen in Eugene Wigner’s popular paper: “unreasonable effectiveness of mathematics”) poses a dual challenge to materialism. Materialism struggles to explain why accidental cosmic processes would conform to elegant, discoverable mathematical laws or why survival-driven cognitive faculties could reliably uncover these laws. The latter intersects with Plantinga’s Evolutionary Argument Against Naturalism: if naturalism undermines trust in cognition’s truth-aimedness, even science’s reliance on mathematics becomes suspect, as evolved brains might prioritize adaptive fictions over truth. Thus, materialism cannot coherently account for mathematics’ predictive power or the reliability of the minds that wield it.

And there is this scientific antirealism angle too but it’s doesn’t look like a crisp argument to me, but I will still flesh it out anyways. When I first read about scientific anti-realism, I didn't quite get it. But now I'm beginning to think that I might be able to make sense of scientific anti-realism on the grounds of materialism. In brief, (some) scientific antirealist challenges the notion that there are mind-independent truths about reality. They suggest that scientific theories are primarily instrumental tools that help us predict, explain and control stuff, they do not necessarily provide a true picture of how the world actually is. Granting the Evolutionary Argument Against Naturalism - and I am now back to my initial point - it appears to me that materialism paradoxically supports antirealism: if our minds are products of blind evolutionary processes, we lack justification for believing they can grasp fundamental truths about the universe.

We can also go through the route of accounting for information in the evolutionary landscape: Darwinian accounts of how complex biological information arises rely on a "displacement fallacy." In brief, instead of explaining where the information originally comes from, the Darwinian account simply shift the burden onto natural selection or specially designed fitness landscapes, effectively assuming the very information they're supposed to explain.

I suppose this will do for now. I should also add that my philosophical commentary should not be taken as a response to Professor Lightman's complete philosophical framework, as I have not read him beyond this book. It's just a commentary to a few comments that actually popped at me while reading this particular book.

In summary, The Miraculous from the Material is an enjoyable read that invites us to marvel at the wonders of the natural world regardless of our philosophical leanings. That being said, if I were to give the book a title, I will keep things as it is, except to swap the positions of “Material” and “Miraculous.”

This essay was previously published a few years ago. If you want to read the text, see the first version here.

Share

Link to Waitlist: https://tally.so/r/wgOJvM

Missing Pages is my latest app project— an app prototype to solve a personal habituated pain point.

To stop reading in a circle, find knowledge gaps, read on-demand, and dig in.

If you are interested in trying this out, here is the Waitlist: https://tally.so/r/wgOJvM

(h/t to Michael Judge for the apt name)

Subscribe now

Video essay:

If you will rather read the vanilla essay:

Essay

Preamble – Steel: tough as hell – Concrete: as hard as these things get – Plastics: The Versatile and Troubling Material – The Unsung Hero: Ammonia – Fossil Fuel Run Our World – Hidden Cost of Progress

Preamble

The modern world is complex. Yet, beneath the surface of our interconnected, information-driven society lie the physical realities that underpin our very existence.

In a world where everyone is on their phones, and God knows what else, it is not surprising that the physical realities are often blurred out. But, yet, these physical entities are the fundamental elements that enable us to produce the food we eat, generate energy, and build the structures that house us.

Vaclav Smil, a distinguished scholar of Energy Studies, in his fascinating book, "How the World Really Works," isolates four materials as the so-called "four pillars of modern civilization": steel, concrete, plastics, and ammonia.

And I was sold. They are not just merely components of our built environment, but they represent the very backbone of our civilization.

Steel: Tough as Hell

At its core, steel is mostly made of iron, with a few other elements mixed in to give it all kinds of special properties. This journey begins with pig iron (also called crude iron), a product of blast furnaces that contains 95 to 97% iron. However, pig iron has a high carbon content, making it very brittle and less ductile (meaning it is not very stretchy). It also has lower tensile strength, which is the ability to withstand stress, compared to bronze or brass.

To turn pig iron into the strong, versatile steel we use every day, the carbon content is reduced. This process makes steel incredibly strong and durable. In fact, steel is much stronger than some of the hardest stones and most common metals. For instance, steel beams can bear loads 15-30 times heavier than granite. It is seven times stronger than aluminum and nearly four times stronger than copper. Steel is also much harder— about four times harder than aluminum and eight times harder than copper. Plus, it can withstand very high temperatures, only melting at about 1,425°C, compared to aluminum at 660°C and copper's 1,085°C.

There are four main types of steel, each with its unique qualities: we have carbon steels, alloy steels, stainless steel, and tool steels. Carbon steels are the most common, and they are used in buildings, bridges, and cars. Alloy steels have other elements added to them to improve certain characteristics. Stainless steel, which doesn't rust by the way, is often used in kitchen appliances and medical equipment. Tool steels are so incredibly hard that they are often used to make tools that are used to cut other kinds of steels, for example. They are used for hand tools like chisels, hammers, wrenches, et cetera.

Understanding these different types of steel and their properties helps us appreciate how this remarkable material shapes our world, making everything from skyscrapers to kitchen sinks possible.

So, now, let’s Imagine a world without steel.

The towering skyscrapers that define city skylines are absent, replaced by shorter, bulkier buildings made from weaker materials. Bridges that span vast rivers and connect cities are now unreliable and fragile. Cars, trains, and airplanes, which rely heavily on steel for their frames and engines, are either significantly less efficient or just non-existent all together, making travel slow and cumbersome.

Everyday life would feel drastically different. Your kitchen appliances, which are typically sleek and durable, are now clunky and prone to rust or wear. Tools and utensils made from less sturdy materials break easily, leading to frustration in accomplishing even simple tasks. The safety and efficiency of our infrastructure— be it roads, railways, and pipelines—are compromised, which will inevitably lead to frequent maintenance and accidents.

Even the medical field would face its own challenges. Stainless steel instruments and equipment are crucial for surgeries and patient care.

The reality is, without steel, our world would be much less advanced, much less connected, and much less efficient.

Concrete: As Hard as These Things Get

Cement is the magic ingredient that makes concrete possible. This fine powder is produced by heating ground limestone and clay, shale, or even waste materials in massive kilns at temperatures of at least 1450°C. The intense heat transforms these raw materials into a substance called clinker, which is then ground into the fine powder that we all know as cement. When mixed with aggregates like sand and gravel, along with water, cement acts as the binding agent to form concrete.

Concrete is everywhere—it's in the roads we drive on, the bridges we cross, our dams, and the buildings we live and work in. Modern cities, in essence, are built from concrete, and without cement, creating concrete on the scale needed to support our societies would be simply impossible.

Back to our exercise, now briefly, imagine a world without cement. Our cities would look drastically different, with less durable and more costly alternatives struggling to meet the demands of modern construction. The convenience and safety we often take for granted in our built environment would simply be compromised.

Plastics: The Versatile and Troubling Material

Plastics are everywhere. The versatility of plastics stem from their ability to be molded into virtually any shape you can think of, making them integral to countless aspects of modern life.

The journey of plastics begins with hydrocarbon feedstocks, found in crude oil and natural gas. Through a process called steam cracking, these hydrocarbons are heated to extremely high temperatures, breaking them down into simpler molecules such as ethylene and propylene. These primary monomers are then synthesized into the diverse array of plastics we use every day.

There are two main types of plastics, each with unique properties and uses. Thermoplastics, which soften when heated and harden when cooled, make up the majority of global plastic production. Examples of thermoplastics include low- and high-density polyethylene (PE), commonly used in packaging and plastic bags; polypropylene (PP), found in car parts and bottle caps; and polyvinyl chloride (PVC), used in healthcare products like catheters, IV tubings, oxygen masks, PVC coated mattress cover, to name but a few. On the other hand, thermoset plastics do not soften upon reheating and are used in products requiring high durability, such as electronics and furniture.

How did we even get to plastics, anyways? We can go from 1600 BCE, when Mesoamericans crafted objects from natural rubber, to the 19th century where we had the discovery of polystyrene and the invention of Parkesine, which is a celluloid that marked the dawn of artificial plastics. The early 20th century saw breakthroughs with Bakelite (the first fully synthetic thermoset, again thermoset are plastics that do not soften upon reheating) and flexible PVC, propelling plastics into widespread use. The mid-century introduced nylon, Teflon, and PET (that is Polyethylene terephthalate), completely transforming consumer goods and packaging. By the late 20th century, plastic bottles had largely replaced glass, and polymer banknotes emerged.

Okay, so that’s quite a ride. An abridged one, I suppose.

But before I move on, I will leave you with this stat: global production of plastics increased from a mere 20,000 tons in 1925 to an astonishing 370 million tons by 2019. If you are about to bring out your calculator there is no need for that, that’s over 18,000 times increase.

Let’s proceed.

Subscribe now

The Unsung Hero: Ammonia

Okay, maybe we cut to the chase with this one. Without ammonia, about 50% of people alive today wouldn’t be here.

So, what’s up with Ammonia?

I suppose we all know this, but you can’t assume much of anything these days. Ammonia is the primary ingredient in nitrogen fertilizers, which are essential for high-yield agriculture.

Nitrogen is a must-have nutrient for plants. It’s a key component of chlorophyll, the molecule plants use to convert sunlight into energy through photosynthesis. Nitrogen also plays a critical role in the biosynthesis of DNA and RNA, the molecules responsible for storing and transferring genetic information, and in building proteins.

Although nitrogen is abundant in the atmosphere, plants can’t use the nitrogen gas (N2) found in the air. They need nitrogen in a reactive form, which only a few natural processes, like nitrogen fixation by bacteria, can provide. Certain bacteria, such as Rhizobium species, form nodules on the roots of legume plants. Within these nodules, the bacteria fix atmospheric nitrogen gas into ammonia or ammonium, which the plants can utilize.

However, staple crops like rice and wheat can’t fix nitrogen on their own and they require an external nitrogen source. Before synthetic fertilizers became a thing, more on that in a minute, farmers had limited methods to add reactive nitrogen to the soil: They would do crop rotation with Legumes: farmers would grow a legume crop, such as clover, and then plow it under to enrich the soil with nitrogen. Or they could just use animal manure, which contains reactive nitrogen compounds.

Needless to say, the traditional methods were labor-intensive and could not supply enough nitrogen to support the high-yield agriculture that is needed for a growing world population.

However, as it always happens, there was a revolutionary discovery: In the early 20th century, scientists Fritz Haber and Carl Bosch developed a groundbreaking method to synthesize ammonia. Known as the Haber-Bosch process, this technique uses high pressure and a catalyst to combine nitrogen from the air with hydrogen. This innovation made it possible to produce reactive nitrogen in the quantities necessary for modern agriculture.

The Green Revolution, which began in the 1960s, was a period of significant agricultural advancement. New high-yield varieties of wheat and rice were developed, but these crops required substantial amounts of nitrogen to reach their full potential. The Haber-Bosch process enabled the mass production of nitrogen fertilizers, which in turn supported these high-yield crops and led to a dramatic increase in global food production. So, again, at the risk of repeating myself, if not for ammonia many of us would simply not exist today.

I should also add that while about 80% of the ammonia produced worldwide is used for fertilizers, it has numerous other applications: such as production of nitric acid, used in the manufacturing of explosives, in rocket propellants, dyes, fibers, cleaners, and so on.

Fossil Fuel Run Our World

If you have granted Vaclav Smil that the four pillars of civilizations are as I have mentioned, then it goes without saying that fossil fuels run our world. Let’s reel through the facts.

Steel: The iron ore smelting process, a crucial step in steelmaking, relies heavily on coke, a carbon-rich material derived from coal. The energy used to power blast furnaces and other steelmaking processes also comes primarily from fossil fuels.

Concrete: Cement production, the core component of concrete, requires immense heat generated by burning fossil fuels, primarily coal dust, petroleum coke, and heavy fuel oil.

Plastics: The synthesis of plastics begins with monomers, simple molecules derived from crude oil and natural gas. The process of converting these monomers into polymers also consumes large amounts of energy derived from fossil fuels.

Ammonia: The Haber-Bosch process, mentioned earlier, is a prime example of fossil fuel dependence. Natural gas is both the source of hydrogen and the primary energy source for this synthesis reaction.

There are two commentaries about these analyses that are quite warranted at this point. The first was made by Professor Smil in the book: the importance of reducing dependence on fossil fuel can not be overstated. However, many folks do not simply realize how deep we are in this fossil fuel world.

It appears that decarbonization is going to be a long-term process due to the pervasive use of fossil fuels in modern society. There are significant changes in energy systems and infrastructure that just need to take place. Smil argues that fossil fuels will remain crucial for decades, especially in sectors like transportation and heavy industry, where alternatives are still developing.

The second point is more obvious, and perhaps only tangentially related to the topic at hand. Our success in solving important problems does not diminish their importance. The fact that we have solved issues like building bridges or producing food does not make them any less crucial to our survival. They are worth our attention, even if it means retracing our steps.

Hidden Costs of Progress

In light of all this, it’s clear that the very foundations of our modern civilization—steel, concrete, plastics, and ammonia—are both marvels of human ingenuity and they are also sources of profound dilemmas. We rely on these materials to feed billions, build cities that defy gravity, connect distant lands, and sustain a quality of life that would have been unimaginable mere centuries ago. Yet, as the systems thinker Daniel Schmachtenberger points out, our technological prowess doesn’t exist in a vacuum. Each stride forward can set off a cascade of unintended consequences, rippling outward through the complex webs of ecology, economy, and society.

The approach we ought to take is to understand that our world is not a series of isolated problems and solutions, but rather an interconnected matrix of systems that interact in both predictable and unpredictable ways. When we celebrate the achievements of the Haber-Bosch process and the gift of abundant food it provides us, for instance, we must also acknowledge its role in overtaxing soils, polluting waterways, and creating a high-stakes dependency on fossil fuels. Similarly, as we marvel at the skyscrapers and infrastructure made possible by steel and concrete, we must also contemplate the immense energy inputs and carbon emissions that have become so deeply embedded in their production.

Our tools and processes, once hailed as solutions to scarcity and hardship, are now implicated in creating new forms of vulnerability. Plastics, once a symbol of modern convenience, have now metamorphosed into environmental hazards scattered across the globe, hinting at the fragile nature of our so-called progress. In fact microplastics in recent studies have been found in human kidneys, livers, and even in brain tissues.

The call to action here is not to abandon these materials outright—an impossibility given the scale of global dependence, as I stated earlier—but to re-envision how we produce, use, and recycle them. We need a more integrated form of problem-solving, one that admits the immensely complex world we live in. This approach challenges us to think systemically: to ask how our attempts to solve one issue might generate others; and to design materials that don’t simply end up as pollutants but can re-enter ecological cycles.

Moving toward such a paradigm requires far more than technological fixes. It demands new governance structures that foster transparency, cooperation, and long-term thinking. It necessitates an educational shift that equips future generations to navigate uncertainty, understand trade-offs, and anticipate outcomes over multiple generations rather than electoral cycles. As Daniel Schmachtenberger has written about, on a cultural level, it might mean reassessing our definition of progress itself.

In the final analysis, recognizing the delicate interplay among these pillars of civilization compels us to question the notion that technology alone can deliver salvation.

References

• Parts of this essay draws heavily from Vaclav Smil’s book: How the World Really Works, Chapter 3. Understanding Our Material World.

• The Consilience Project, Development in Progress, July 16, 2024. https://consilienceproject.org/development-in-progress/

• Home Depot. (n.d.). Types of Steel. Retrieved December 5, 2024, from https://www.homedepot.com/c/ab/types-of-steel/9ba683603be9fa5395fab90171fb5f7e

• Thermoset plastics: https://plasticseurope.org/plastics-explained/a-large-family/thermosets/

• Polyvinyl Chloride in biomedical applications:

• https://boydbiomedical.com/articles/using-polyvinyl-chloride-in-biomedical-applications

• Timeline of plastic development: https://en.wikipedia.org/wiki/Timeline_of_plastic_development

My short book, Wander, is now available for sale! I’d love to hear your thoughts and feedback if you get a chance to read it.

Check it out here.

https://epistemeengine.gumroad.com/l/wander

Subscribe now

My memoir-essay on knowledge work, coming out soon on gumroad and other platforms: https://epistemeengine.gumroad.com/l/wander

We don't simply want; we want what others want. This mimetic nature of desire explains our fascination with objects that hold no inherent value beyond our collective agreement of their worth. Think of the allure of a glittering diamond ring, the prestige of an Olympic gold medal, or the reverence for a masterpiece hanging in a museum. These items, devoid of practical utility, become coveted treasures solely because we've imbued them with shared significance.

But Girard doesn't stop at explaining our peculiar obsessions. He takes this concept further, using it as a foundation to explore the darker aspects of human interaction. When desires converge on the same object, conflict inevitably arises. It's not just about possessing the item; it's about the status and recognition that come with it. This competition can escalate, fueling rivalries, violence, and even large-scale conflicts.

Girard's theory offers a compelling explanation for everything from fashion trends to wars. It challenges us to question the authenticity of our desires and the roots of our conflicts. In a world increasingly driven by social media and never-ending comparison, understanding the mimetic nature of desire becomes not just fascinating or merely academic, but essential for navigating our complex social landscape.

There is about one point mutation for every 100 million base pairs in humans. With the technical caveat that mutation rate actually varies across different regions of the genome and between individuals.

While some mutations are harmful in biological organisms, others might provide beneficial traits that help species survive. Consider the mutation that allows some humans to digest lactose into adulthood, or the CCR5-delta32 mutation that provides resistance to HIV. These genetic 'errors' have conferred significant advantages to their bearers.

DNA repair systems work relentlessly, day and night to correct these mistakes. These molecular guardians are like tireless proofreaders, scanning billions of base pairs for errors and fixing them with remarkable precision. Yet, if they were 100% efficient, if they made no mistakes, beneficial mutations wouldn't occur, completely undermining the entire project of adaptive evolution. 

This delicate balance between fidelity and flexibility is a cornerstone of life's resilience. It's nature's way of hedging its bets, ensuring that species can adapt to changing environments while maintaining overall genetic stability.

Similarly, in technological  and scientific enterprise, mistakes are not always setbacks. Unexpected results can be a path to breakthroughs. Sir Alexander Fleming’s popular discovery is a case in point. His accidental contamination of a petri dish led to one of the most significant medical advancements in history - The Penicillin, revolutionizing infection treatments and laying the foundation for modern antibiotics. 

But Fleming's serendipitous find is just one example. There are too many: the discovery of X-rays, the invention of the microwave oven, and the creation of Post-it notes all stem from errors or unexpected outcomes. These examples remind us that innovation often lurks in the shadows of what is unforeseen.

Error could mean progress. 

Create systems that are antifragile - systems that don't merely withstand shocks and disruptions but actually improve precisely because of them. Experiment. Fail Fast. Engineer cultures that view challenges as opportunities for growth. Wander. 

Create systems that are antifragile 

Given that the modern economy is practically built on addiction. The following should be a required ‘lesson’ for all modern humans. 

Many people still think of Dopamine as simply a neurotransmitter that rewards such and such actions with this ‘mysterious’ dose of pleasure. 

But not quite. It is a herald of impending reward, which can be more compelling than the reward itself. Put simply, the pleasure is in the anticipation of the reward. This anticipation initiates a positive feedback loop, reinforcing the connection between stimulus and action. 

If you have experienced the piercing screech of noise during a concert, caused when a microphone picks up its own output from the speakers; then you know what a feedback loop is. If certain conditions present itself,  this loop can escalate, resulting in a noise so intense it could damage the speakers.

But I digress, take a fellow who enjoys perhaps a bit too much alcohol. 

When their alcohol consumption leads to a release of dopamine in anticipation of relief or pleasure, it strengthens the likelihood of the behavior's recurrence, potentially creating a self-sustaining cycle. (This is particularly pernicious in folks with genetic predisposition to alcoholism.)

The cycle is further exacerbated when environmental cues alone suffice to trigger dopamine release, making the craving for the habit extremely difficult to overcome. 

In humans, this translates into the power of contextual cues associated with substance use, such as a specific location or time, which can induce cravings even in the absence of the substance. And in case you are wondering, this dopaminergic mechanism is what underpins fetishes. 

The challenge, then, is to break both the behavioral pattern and the anticipatory loop. Effective intervention must address the triggers that initiate the loop, often stress or environmental cues, and not just the habit they reinforce. 

Subscribe now

Transcript

There is an apparent asymmetry built into our world. One that stares us in the face no matter where you look. And no matter what we do, it appears to be hard to correct for. 

The startup ecosystem is a prime example. A tiny number of companies reap the massive rewards. And a place to find evidence of this, is obviously in the well cited data you can find on the web. 

But even more so in the investing strategies of early stage venture studios - they fund a bunch of companies, and expect  only a few to succeed. (This is why many of these venture firms fund startups with a potential large market base.) 

Moreover, this disproportionate success more often than not comes from unpredictable breakthroughs that reshape industries.

In the financial markets, a similar pattern emerges. A handful of traders and hedge funds achieve record-breaking returns. In scientific research. In music. As I have noted, ‘no matter where you look.’

Here is the gist: Failure is not solely a reflection of individual worth or effort, but rather the natural outcome of a system that rewards the outliers disproportionately. 

But what can society do? It can strive for a more equitable distribution of opportunities. 

Yet, society's reach has limits. It cannot legislate away the randomness of fortune nor the inherent risks of innovation.

And indeed, the unpredictability of success is, paradoxically, a driver of progress. It's the catalyst for ambition, the fuel for big dreams.

In the end, we must accept that we live in an asymmetrical world. 

Our age brings ‘infinite’ technological advances, each one seemly more stunning than the last. 

But one bug persists in humanity's code base, untamed – our defective human nature.

No ingenious innovation can fix this bug; and we ignore this stark reality at our own peril. 

Amnesia about human’s recurrent capacity of using technology for harm, is simply ignoring history.

For all our shiny upgrades, Murphy's Law still rules. 

Subscribe now