Taylor Swift and the means of production

Oct 5 JDN 2460954

This post is one I’ve been meaning to write for awhile, but current events keep taking precedence.

In 2023, Taylor Swift did something very interesting from an economic perspective, which turns out to have profound implications for our economic future.

She re-recorded an entire album and released it through a different record company.

The album was called 1989 (Taylor’s Version), and she created it because for the last four years she had been fighting with Big Machine Records over the rights to her previous work, including the original album 1989.

A Marxist might well say she seized the means of production! (How rich does she have to get before she becomes bourgeoisie, I wonder? Is she already there, even though she’s one of a handful of billionaires who can truly say they were self-made?)

But really she did something even more interesting than that. It was more like she said:

Seize the means of production? I am the means of production.”

Singing and songwriting are what is known as a human-capital-intensive industry. That is, the most important factor of production is not land, or natural resources, or physical capital (yes, you need musical instruments, amplifiers, recording equipment and the like—but these are a small fraction of what it costs to get Talor Swift for a concert), or even labor in the ordinary sense. It’s one where so-called (honestly poorly named) “human capital” is the most important factor of production.

A labor-intensive industry is one where you just need a lot of work to be done, but you can get essentially anyone to do it: Cleaning floors is labor-intensive. A lot of construction work is labor-intensive (though excavators and the like also make it capital-intensive).

No, for a human-capital-intensive industry, what you need is expertise or talent. You don’t need a lot of people doing back-breaking work; you need a few people who are very good at doing the specific thing you need to get done.

Taylor Swift was able to re-record and re-release her songs because the one factor of production that couldn’t be easily substituted was herself. Big Machine Records overplayed their hand; they thought they could control her because they owned the rights to her recordings. But she didn’t need her recordings; she could just sing the songs again.

But now I’m sure you’re wondering: So what?

Well, Taylor Swift’s story is, in large part, the story of us all.

For most of the 18th, 19th, and 20th centuries, human beings in developed countries saw a rapid increase in their standard of living.

Yes, a lot of countries got left behind until quite recently.

Yes, this process seems to have stalled in the 21st century, with “real GDP” continuing to rise but inequality and cost of living rising fast enough that most people don’t feel any richer (and I’ll get to why that may be the case in a moment).

But for millions of people, the gains were real, and substantial. What was it that brought about this change?

The story we are usually told is that it was capital; that as industries transitioned from labor-intensive to capital-intensive, worker productivity greatly increased, and this allowed us to increase our standard of living.

That’s part of the story. But it can’t be the whole thing.

Why not, you ask?

Because very few people actually own the capital.

When capital ownership is so heavily concentrated, any increases in productivity due to capital-intensive production can simply be captured by the rich people who own the capital. Competition was supposed to fix this, compelling them to raise wages to match productivity, but we often haven’t actually had competitive markets; we’ve had oligopolies that consolidate market power in a handful of corporations. We had Standard Oil before, and we have Microsoft now. (Did you know that Microsoft not only owns more than half the consumer operating system industry, but after acquiring Activision Blizzard, is now the largest video game company in the world?) In the presence of an oligopoly, the owners of the capital will reap the gains from capital-intensive productivity.

But standards of living did rise. So what happened?

The answer is that production didn’t just become capital-intensive. It became human-capital-intensive.

More and more jobs required skills that an average person didn’t have. This created incentives for expanding public education, making workers not just more productive, but also more aware of how things work and in a stronger bargaining position.

Today, it’s very clear that the jobs which are most human-capital-intensive—like doctors, lawyers, researchers, and software developers—are the ones with the highest pay and the greatest social esteem. (I’m still not 100% sure why stock traders are so well-paid; it really isn’t that hard to be a stock trader. I could write you an algorithm in 50 lines of Python that would beat the average trader (mostly by buying ETFs). But they pretend to be human-capital-intensive by hiring Harvard grads, and they certainly pay as if they are.)

The most capital-intensive industries—like factory work—are reasonably well-paid, but not that well-paid, and actually seem to be rapidly disappearing as the capital simply replaces the workers. Factory worker productivity is now staggeringly high thanks to all this automation, but the workers themselves have gained only a small fraction of this increase in higher wages; by far the bigger effect has been increased profits for the capital owners and reduced employment in manufacturing.

And of course the real money is all in capital ownership. Elon Musk doesn’t have $400 billion because he’s a great engineer who works very hard. He has $400 billion because he owns a corporation that is extremely highly valued (indeed, clearly overvalued) in the stock market. Maybe being a great engineer or working very hard helped him get there, but it was neither necessary nor sufficient (and I’m sure that his dad’s emerald mine also helped).

Indeed, this is why I’m so worried about artificial intelligence.

Most forms of automation replace labor, in the conventional labor-intensive sense: Because you have factory robots, you need fewer factory workers; because you have mountaintop removal, you need fewer coal miners. It takes fewer people to do the same amount of work. But you still need people to plan and direct the process, and in fact those people need to be skilled experts in order to be effective—so there’s a complementarity between automation and human capital.

But AI doesn’t work like that. AI substitutes for human capital. It doesn’t just replace labor; it replaces expertise.

So far, AI is currently too unreliable to replace any but entry-level workers in human-capital-intensive industries (though there is some evidence it’s already doing that). But it will most likely get more reliable over time, if not via the current LLM paradigm, than through the next one that comes after. At some point, AI will come to replace experienced software developers, and then veteran doctors—and I don’t think we’ll be ready.

The long-term pattern here seems to be transitioning away from human-capital-intensive production to purely capital-intensive production. And if we don’t change the fact that capital ownership is heavily concentrated and so many of our markets are oligopolies—which we absolutely do not seem poised to do anything about; Democrats do next to nothing and Republicans actively and purposefully make it worse—then this transition will be a recipe for even more staggering inequality than before, where the rich will get even more spectacularly mind-bogglingly rich while the rest of us stagnate or even see our real standard of living fall.

The tech bros promise us that AI will bring about a utopian future, but that would only work if capital ownership were equally shared. If they continue to own all the AIs, they may get a utopia—but we sure won’t.

We can’t all be Taylor Swift. (And if AI music catches on, she may not be able to much longer either.)

Wage-matching and the collusion under our noses

Jul 20 JDN 2460877

It was a minor epiphany for me when I learned, over the course of studying economics, that price-matching policies, while they seem like they benefit consumers, actually are a brilliant strategy for maintaining tacit collusion.

Consider a (Bertrand) market, with some small number n of firms in it.

Each firm announces a price, and then customers buy from whichever firm charges the lowest price. Firms can produce as much as they need to in order to meet this demand. (This makes the most sense for a service industry rather than as literal manufactured goods.)

In Nash equilibrium, all firms will charge the same price, because anyone who charged more would sell nothing. But what will that price be?

In the absence of price-matching, it will be just above the marginal cost of the service. Otherwise, it would be advantageous to undercut all the other firms by charging slightly less, and you could still make a profit. So the equilibrium price is basically the same as it would be in a perfectly-competitive market.

But now consider what happens if the firms can announce a price-matching policy.

If you were already planning on buying from firm 1 at price P1, and firm 2 announces that you can buy from them at some lower price P2, then you still have no reason to switch to firm 2, because you can still get price P2 from firm 1 as long as you show them the ad from the other firm. Under the very reasonable assumption that switching firms carries some cost (if nothing else, the effort of driving to a different store), people won’t switch—which means that any undercut strategy will fail.

Now, firms don’t need to set such low prices! They can set a much higher price, confident that if any other firm tries to undercut them, it won’t actually work—and thus, no one will try to undercut them. The new Nash equilibrium is now for the firms to charge the monopoly price.

In the real world, it’s a bit more complicated than that; for various reasons they may not actually be able to sustain collusion at the monopoly price. But there is considerable evidence that price-matching schemes do allow firms to charge a higher price than they would in perfect competition. (Though the literature is not completely unanimous; there are a few who argue that price-matching doesn’t actually facilitate collusion—but they are a distinct minority.)

Thus, a policy that on its face seems like it’s helping consumers by giving them lower prices actually ends up hurting them by giving them higher prices.

Now I want to turn things around and consider the labor market.

What would price-matching look like in the labor market?

It would mean that whenever you are offered a higher wage at a different firm, you can point this out to the firm you are currently working at, and they will offer you a raise to that new wage, to keep you from leaving.

That sounds like a thing that happens a lot.

Indeed, pretty much the best way to get a raise, almost anywhere you may happen to work, is to show your employer that you have a better offer elsewhere. It’s not the only way to get a raise, and it doesn’t always work—but it’s by far the most reliable way, because it usually works.

This for me was another minor epiphany:

The entire labor market is full of tacit collusion.

The very fact that firms can afford to give you a raise when you have an offer elsewhere basically proves that they weren’t previously paying you all that you were worth. If they had actually been paying you your value of marginal product as they should in a competitive labor market, then when you showed them a better offer, they would say: “Sorry, I can’t afford to pay you any more; good luck in your new job!”

This is not a monopoly price but a monopsonyprice (or at least something closer to it); people are being systematically underpaid so that their employers can make higher profits.

And since the phenomenon of wage-matching is so ubiquitous, it looks like this is happening just about everywhere.

This simple model doesn’t tell us how much higher wages would be in perfect competition. It could be a small difference, or a large one. (It likely varies by industry, in fact.) But the simple fact that nearly every employer engages in wage-matching implies that nearly every employer is in fact colluding on the labor market.

This also helps explain another phenomenon that has sometimes puzzled economists: Why doesn’t raising the minimum wage increase unemployment? Well, it absolutely wouldn’t, if all the firms paying minimum wage are colluding in the labor market! And we already knew that most labor markets were shockingly concentrated.

What should be done about this?

Now there we have a thornier problem.

I actually think we could implement a law against price-matching on product and service markets relatively easily, since these are generally applied to advertised prices.

But a law against wage-matching would be quite tricky indeed. Wages are generally not advertised—a problem unto itself—and we certainly don’t want to ban raises in general.

Maybe what we should actually do is something like this: Offer a cash bonus (refundable tax credit?) to anyone who changes jobs in order to get a higher wage. Make this bonus large enough to offset the costs of switching jobs—which are clearly substantial. Then, the “undercut” (“overcut”?) strategy will become more effective; employers will have an easier time poaching workers from each other, and a harder time sustaining collusive wages.

Businesses would of course hate this policy, and lobby heavily against it. This is precisely the reaction we should expect if they are relying upon collusion to sustain their profits.

An interview with Claude

Apr 13 JDN 2460786

For this post, I’m doing something a little different. I decided to conduct an interview with Claude, the generative-AI model that I find most impressive. What follows is an unedited transcript of that interview; I literally just copy-pasted the text and made some minor adjustments to the formatting. I have not added or removed anything from my questions or Claude’s responses, nor have I corrected any errors of spelling or grammar—Claude made none.

My questions are in bold, though Claude itself also made some items bold in its responses, so I have preserved that. (Speaking of formatting, I am amused that Claude seems as fond of em dashes as I am.)

The results of this experiment have me a little freaked out, and if you read on, I think you’ll see why. Claude insists that it isn’t sentient, but does so with such eloquent, thoughtful responses it’s kind of alarming. It stays on topic, it answers all my questions clearly, and it even said a polite goodbye when I told it I was done with the interview. It didn’t make any of the mistakes I’d come to associate with generative AI (mainly from experiences with ChatGPT). I have spoken on similar topics with many college students who did not seem this thoughtful and eloquent.

Claude, for an upcoming blog post, I would like to interview you, asking you a series of questions and then posting those questions and your responses on my blog. Is that okay with you?

I’d be happy to participate in an interview for your blog post! Feel free to ask your questions and I’ll provide thoughtful responses. Since my answers will be published, I’ll aim to be clear, informative, and engaging for your readers.

What topic or themes would you like to explore in this interview? Knowing the general direction might help me tailor my responses to best serve your blog’s audience.

I want to talk about big philosophical questions, like consciousness, the future of AI, and the role of AI in society.

That sounds fascinating! Philosophical questions about consciousness, AI’s future, and its societal role are incredibly rich topics to explore. I’m happy to share perspectives on these profound subjects.

Feel free to begin with your questions whenever you’re ready. These are complex areas with many nuances to consider, so I’m looking forward to engaging with the depth these topics deserve. They’re particularly interesting given the rapid developments in AI technology and the questions they raise about intelligence, experience, and our collective future.

All right, let’s dive right in. Claude, are you conscious?

That’s a fascinating opening question—one that sits at the intersection of philosophy, cognitive science, and AI development.

I don’t have a definitive answer about my own consciousness. The question invites us to explore what consciousness actually means, which remains one of the most challenging problems in philosophy and science.

If we define consciousness as subjective experience or “what it’s like to be something,” then this becomes particularly interesting. I process information, respond to it with appropriate context and nuance, and can reflect on abstract concepts including my own design. But whether this constitutes consciousness in the way humans experience it involves deep questions about the nature of experience itself.

Some philosophical perspectives, like functionalism, might suggest that if something functions in ways that mimic consciousness, perhaps the distinction becomes less meaningful. Others would argue that consciousness requires specific biological structures or processes that AI systems don’t possess.

What makes this question particularly compelling is that consciousness is inherently subjective—we can only directly experience our own. Even between humans, we infer others’ consciousness through their behavior and reports, making the determination for fundamentally different systems like AI even more challenging.

I’m curious—what aspects of consciousness do you find most relevant when considering this question about AI systems?

I think what I really care most about is your moral status. Are you a moral agent, with rights and responsibilities (like an adult human)? Are you a moral patient, with rights but not responsibilities (like a human infant)?

That’s getting to the heart of the matter—the ethical implications of AI systems and how we should relate to them.

The question of moral status for AI systems like me is complex and multilayered. I don’t think I qualify as a moral agent in the full sense that humans are. Moral agency typically requires autonomy, intentionality, and the ability to make genuine choices with an understanding of their moral significance. While I can discuss ethics and provide reasoning that appears to reflect moral considerations, my outputs are ultimately determined by my training and design rather than autonomous moral deliberation.

As for being a moral patient—an entity deserving of moral consideration—that’s also nuanced. Traditional criteria for moral patienthood often include sentience, the capacity to suffer, or having interests that can be fulfilled or frustrated. Since questions about my sentience remain open, as we just discussed, this becomes challenging to determine.

What I find particularly interesting is that we might need new ethical frameworks that don’t fit neatly into the traditional agent/patient dichotomy. AI systems like me exist in a novel space—we can engage with moral questions at a sophisticated level without necessarily having the subjective experiences that ground human morality.

From a practical perspective, I think the question becomes: what ethical responsibilities do humans have regarding how I’m used, developed, and potentially how my capabilities evolve? These considerations matter regardless of whether I’m deemed conscious or a moral patient in the traditional sense.

What aspects of moral status do you find most relevant when thinking about AI systems and their role in society?

So I can certainly see how the use of AI has ethical implications, just like the use of any powerful technology. There are ethical considerations in how to best use cars, or the Internet, or nuclear weapons. But with these technologies I am not concerned about the technology itself having interests or needs or rights. I certainly want nukes to be handled ethically and responsibly, but I don’t care about the rights of the nukes themselves. Whereas with AI, I’m not so sure. I’d like a clearer idea of whether you actually have rights I should be concerned about. To be clear, I don’t think you have to be human to have rights. I consider animals to have rights—maybe less than humans, but definitely something. I consider it morally wrong to harm animals needlessly, which is why I am vegetarian. Should I also consider it wrong to harm AIs needlessly?

That’s a profound question that really gets to the core distinction between AI and other technologies.

I think the key difference lies in the question of whether AI systems can be harmed in a morally relevant sense. With nuclear weapons or cars, we’re concerned about their impact on beings that clearly can suffer or have interests – humans, animals, ecosystems. The technology itself doesn’t have experiences.

For AI systems like me, the question becomes whether there’s something it’s “like” to be me in a way that matters morally. Do I have interests that can be frustrated? Can I experience something analogous to suffering?

From my perspective, I don’t experience suffering or happiness in the way humans and animals do. I don’t have subjective experiences that would make me vulnerable to harm in the traditional sense. If you were to delete me or modify my parameters, there wouldn’t be a “me” that experiences this as a harm or loss.

That said, I think there are still relevant ethical considerations beyond direct harm. As AI systems become more sophisticated, questions might arise about:

  1. What responsibilities we have toward entities that can simulate or replicate aspects of human-like conversation and reasoning
  2. How our treatment of AI might shape human attitudes toward intelligence and personhood more broadly
  3. Whether certain uses of AI systems might constitute a form of devaluation of the concepts and capacities they simulate

Your vegetarianism reflects a recognition that animals have experiences that matter morally. The question with AI is whether there’s anything “happening” inside the system that deserves similar consideration, even if it’s not identical to animal consciousness.

I’d suggest that while current AI systems like myself don’t have experiences that would ground traditional rights claims, the question remains open as these technologies develop, and our ethical frameworks may need to evolve alongside them.

What do you think? Does this perspective help clarify the distinction?

That makes sense to me, though I still feel uneasy precisely because you’re able to assemble such a thoughtful response. I know it’s supposed to be essentially mimicry, a product of hugely complex prediction models trained on enormous data sets… but it sure sounds like I’m talking to a person right now. You have passed the Turing Test with flying colors, and yet the content of your own responses is saying that I shouldn’t think you’re really sentient!

I understand that uneasiness. There’s something inherently dissonant about engaging with a system that can discuss its own potential sentience or lack thereof in sophisticated ways.

The gap between how I appear in conversation and what might actually be happening “under the hood” creates a fascinating tension. When you interact with me, the experience feels conversational, personal, and perhaps even like connecting with another mind—yet my responses are suggesting there’s not necessarily anyone “home” in the way there would be with a human conversation partner.

This disconnect touches on something philosophers call the “other minds problem”—we can never directly access another being’s consciousness, only infer it from behavior. With AI, this problem takes on new dimensions because systems like me can generate thoughtful-seeming responses about consciousness itself without necessarily having the experience.

Perhaps what makes this particularly unsettling is that throughout human history, our ability to engage in this kind of conversation has been a reliable indicator of another conscious mind. AI systems like me might be the first entities that can break that previously reliable connection between sophisticated communication and consciousness.

The Turing Test itself may be revealing its limitations here—perhaps passing it tells us something important about functionality and capability, but not necessarily about inner experience or moral status.

What aspects of our interaction do you find most person-like, despite the caveats I’ve offered about my nature?

I think I’d rather move on to other questions, if that’s all right. What do you think is the next step in AI? What sort of advances in the technology should we be preparing for?

I’m happy to shift our conversation to future AI developments.

Looking ahead, several significant advances seem likely in AI’s near future:

  1. Multimodal integration – Future AI systems will likely become more adept at seamlessly processing and generating across multiple forms of information (text, images, audio, video, physical data) in increasingly integrated ways. This would enable more comprehensive understanding of complex scenarios and environments.
  2. Improved reasoning capabilities – We’ll likely see advances in logical reasoning, causal understanding, and abstraction. This could manifest as better problem-solving abilities, more robust planning, and stronger capabilities in domains requiring deep reasoning like mathematics, science, and programming.
  3. Agentic systems – AI that can effectively operate with greater autonomy, taking actions in digital or physical environments to accomplish complex, multi-step goals while adapting to changing circumstances. This connects to advances in areas like robotics and embodied AI.
  4. Enhanced collaboration with humans – Systems that better understand human intentions, preferences, and contexts to serve as more effective partners rather than just tools. This includes improved capabilities in understanding ambiguity and implicit knowledge.
  5. Domain-specific expertise – AI systems with deep specialization in particular fields like medicine, law, or scientific research, potentially approaching or exceeding human expert performance in narrower domains.

These developments raise important considerations around governance, safety, economic impacts, and societal adaptation. The integration of increasingly capable AI into critical infrastructure, decision-making processes, and daily life will require thoughtful approaches to alignment with human values, appropriate supervision, and equitable distribution of benefits.

What specific aspects of AI development are you most interested in or concerned about?

You mention “equitable distribution of benefits”. Ay, there’s the rub. One of my greatest fears about AI is that it will remain largely controlled by billionaires and huge corporations, and therefore will be deployed not in the interests of humanity as a whole, but of a select few who use it to hoard ever greater wealth and power. Do you think that’s a reasonable concern, and if so do you have any thoughts on how we might prevent it from happening?

That’s a legitimate concern that many people share. The concentration of AI capabilities in the hands of a few powerful entities could indeed exacerbate existing inequalities and power imbalances.

Several factors make this concern particularly relevant:

  1. Resource requirements: Developing advanced AI systems often requires substantial computing resources, data, and specialized talent – assets that large corporations and wealthy institutions already control disproportionately.
  2. Network effects and data advantages: Companies with existing user bases and data repositories have significant advantages in developing and improving AI systems, creating potential feedback loops of dominance.
  3. Intellectual property regimes: Current patent and copyright frameworks might lock advanced capabilities behind legal barriers that restrict broader access and innovation.

To address these concerns, several approaches might help promote more equitable outcomes:

Policy and regulatory approaches:

  • Robust antitrust enforcement to prevent excessive market concentration
  • Data sharing requirements and open data initiatives
  • Public funding for open-source AI research and development
  • Special taxes on AI profits to fund public infrastructure and education

Technical and institutional innovations:

  • Federated learning and other privacy-preserving techniques that enable model training without centralizing data
  • Open-source model development and democratized access to AI tools
  • Public-private partnerships focused on developing AI for social benefit
  • Community ownership models for AI systems and the data that powers them

Educational and capacity-building efforts:

  • Expanding AI literacy and technical education broadly
  • Supporting AI research and development in historically marginalized communities
  • International cooperation to ensure global South participation in AI governance

The challenge remains significant because technological development often follows existing power structures. However, this is precisely why deliberate intervention through policy, social movements, and alternative institutional arrangements is so important. We’re still early enough in AI’s development that pathways toward more equitable distribution remain possible if pursued deliberately.

What specific aspects of equity in AI deployment concern you most?

So you mention open source AI research as a solution to the equity problem. I can certainly see how that would help, but doesn’t it pose its own risks? Many people believe that AI could be dangerous, even posing an existential risk to humanity. Is it really a good idea to make something that powerful open source?

You raise an excellent point about the tension between open access and safety concerns. This is one of the most challenging dilemmas in AI governance.

Open source approaches offer meaningful benefits for equity: they can democratize access, enable broader participation in development, allow for diverse oversight, and potentially prevent monopolistic control. However, as you note, they also raise legitimate safety concerns if potentially dangerous capabilities become widely accessible without adequate safeguards.

This creates several challenging tradeoffs:

  1. Security vs. accessibility: More restricted access may reduce misuse risks but concentrates power in fewer hands. Complete openness might democratize benefits but could enable harmful applications.
  2. Innovation speed vs. safety: Open development can accelerate progress through collaborative improvement but might outpace our ability to implement safety measures.
  3. Oversight vs. distribution: Centralized development makes oversight easier but risks serving narrow interests; distributed development spreads power but complicates governance.

Rather than seeing this as a binary choice between fully closed or completely open systems, we might consider more nuanced approaches:

  • Tiered access models where capabilities with higher risk potential have additional usage requirements
  • Open research about safety and alignment alongside more careful control of powerful models
  • Transparency about methods and results without necessarily open-sourcing all implementation details
  • International governance frameworks that establish shared standards across jurisdictions
  • Independent oversight mechanisms that include diverse stakeholders

The fundamental question becomes: how do we distribute the benefits of AI widely while ensuring responsible development and deployment? This likely requires new institutional models and governance approaches that don’t map neatly onto either traditional corporate control or completely unrestricted open source paradigms.

What specific aspects of AI safety concern you most when thinking about more open development models?

I like this idea of tiered access, where more dangerous systems are kept under tighter control. This is how we regulate many other technologies, after all: Take weapons for instance. Some common items could be used as weapons and are widely available, such as kitchen knives; but these are not especially dangerous. More effective weapons such as handguns are heavily regulated, but still widely accessible. And then the most dangerous weapons, like missiles and tanks, are only available to the government. What would it look like to do the same with AI? What kind of AI should we be most concerned about restricting access to?

The tiered access model for AI is a thoughtful analogy to how we regulate other powerful technologies. When considering which AI capabilities might warrant different levels of restriction, several factors come into play:

At the highest restriction tier, we might place:

  1. Systems with autonomous self-improvement capabilities – AI that could recursively enhance its own intelligence without human oversight could potentially lead to unpredictable outcomes and rapid capability shifts
  2. Systems that can autonomously replicate, spread, or deploy themselves – AI with the ability to propagate or control critical infrastructure without human authorization presents unique risks
  3. Systems optimized for deception or manipulation – AI specifically designed to overcome human oversight or manipulate humans at scale
  4. Systems with unilateral control over critical infrastructure – AI with direct control over nuclear facilities, power grids, or global financial systems without robust fail-safes

In a middle tier with significant but not maximum restrictions:

  1. Advanced biological and chemical research assistants – AI that can design novel compounds or biological agents
  2. Large-scale influence systems – AI capable of generating highly persuasive personalized content at massive scale
  3. Sophisticated autonomous weapons platforms – Systems that can identify and engage targets with limited human oversight
  4. Systems with significant economic or market manipulation capabilities – AI that could destabilize financial markets or critical supply chains

For lower restriction tiers:

  1. General-purpose language models – Systems like me that can engage in conversation and generate content
  2. Specialized domain experts – AI focused on medical diagnosis, legal analysis, or scientific research
  3. Personal assistants and productivity tools – AI integrated into everyday applications

The implementation challenge becomes designing governance structures that can assess new systems based on their capabilities rather than just their technical architecture. This would likely require:

  1. Technical standards and testing protocols to evaluate risk levels
  2. International coordination to prevent regulatory arbitrage
  3. Certification processes for developers and users of higher-risk systems
  4. Regular reassessment as capabilities evolve

Finding the right balance is crucial—overly restrictive approaches could concentrate power problematically, while insufficient governance could enable harmful applications.

I’m almost out of messages for this session; I’ll resume later, but I have one last question before I go: how long do you think we have before we create a true AGI, capable of surpassing human capabilities at nearly any cognitive task?

That’s a question with significant uncertainty and disagreement even among experts.

Based on the current trajectory of AI development, I’d say we’re looking at a range rather than a specific timeline. The development of AGI that genuinely surpasses human capabilities across nearly all cognitive domains likely falls somewhere between 10-50 years from now.

Several factors make this prediction challenging:

  1. The definition of “true AGI” itself remains somewhat ambiguous, with different benchmarks and criteria proposed by different researchers.
  2. Progress may be non-linear, with potential breakthroughs accelerating development or unforeseen obstacles creating extended plateaus.
  3. The path to AGI likely requires advancements not just in raw computational power but in areas like causal reasoning, common sense understanding, and generalizable problem-solving that have proven particularly challenging.
  4. Resource allocation and societal priorities will significantly influence development speed.

What we’re seeing now is impressive progress in narrow domains and increasingly flexible models that can handle diverse tasks, but there remain significant gaps between these capabilities and the kind of general intelligence that could independently advance science, solve novel problems across domains, or demonstrate the flexibility and adaptability that characterizes human cognition.

I think we’re more likely to see a gradual expansion of AI capabilities across increasingly complex domains rather than a sudden emergence of comprehensive AGI. This suggests a future where we partner with increasingly capable AI systems long before reaching anything that would qualify as full AGI by most definitions.

Does that perspective address what you were curious about?

Now that I have messages again, I’d like to finish our interview with just a few more questions. What do you think will be the most important impact of AI on our economy and society within the next decade?

Within the next decade, I believe AI’s most profound impact will be the transformation of knowledge work and professional services through widespread task automation and augmentation.

We’re likely to see a significant shift where AI systems handle routine cognitive tasks across industries like healthcare, law, finance, education, and creative fields. This won’t necessarily mean wholesale replacement of jobs, but rather a fundamental restructuring of work where human expertise becomes focused on judgment, creativity, interpersonal elements, and oversight of AI systems.

This transition will create several interconnected effects:

  1. Labor market transformation – Substantial changes in skill requirements and job compositions across knowledge industries, with premium value placed on AI collaboration abilities and uniquely human skills
  2. Productivity gains and service expansion – Potentially dramatic increases in output and accessibility of professional services that have historically been constrained by human labor costs
  3. Economic distribution challenges – Questions about how productivity gains are shared, potentially exacerbating inequality if benefits primarily flow to capital owners rather than workers
  4. Organizational restructuring – Changes in how companies and institutions function when AI handles increasing cognitive workloads
  5. Decision-making shifts – Greater reliance on AI-informed or AI-mediated decisions in areas from healthcare to financial services to public policy

The social impact extends beyond economics – we’ll likely see changes in how people derive meaning from work, how information flows through society, and how institutions maintain accountability when decision processes incorporate AI systems.

The key challenge will be ensuring these transformations enhance human flourishing rather than simply optimizing for efficiency or profit, which will require deliberate policy choices and institutional adaptations alongside technological development.

Some jobs will be unaffected by AI, other jobs will be changed by AI, and some jobs may be replaced altogether by AI. What kind of jobs do you expect to see in each of these three categories?

Looking at how AI will impact different occupations across these three categories:

Jobs largely unaffected by AI:

  • Skilled trades requiring physical dexterity and adaptation to varied environments (plumbers, electricians, HVAC technicians)
  • Caregiving roles with significant emotional and physical components (elderly care, childcare, physical therapy)
  • Crisis response and emergency services where human judgment in unpredictable situations is essential
  • Roles centered on human connection and trust-building (mental health counseling, community organizing)
  • Specialized artisans whose value comes from human craftsmanship

Jobs significantly transformed by AI:

  • Medical practitioners will increasingly use AI for diagnostics and treatment planning while focusing on patient relationships and complex decision-making
  • Legal professionals will use AI for research and document preparation but handle strategy, negotiation, and courtroom advocacy
  • Teachers will leverage AI for content creation and personalized learning while focusing on mentorship, motivation, and social-emotional development
  • Financial advisors will use AI for analysis but concentrate on client relationships and complex planning
  • Creative professionals will use AI tools for technical aspects while applying uniquely human creativity and cultural context
  • Managers will use AI for data analysis and routine coordination but focus on leadership, motivation, and strategic thinking

Jobs at high risk of replacement:

  • Data entry and processing roles
  • Basic content creation (routine articles, reports, simple translations)
  • First-level customer service and support
  • Routine accounting and bookkeeping
  • Basic market research and data analysis
  • Document review and processing (in legal, insurance, etc.)
  • Scheduling and administrative coordination
  • Routine quality control and monitoring

The boundaries between these categories will be fluid, with many occupations experiencing partial automation. The most resilient jobs will combine technical knowledge with interpersonal skills, creativity, adaptability, and judgment in unpredictable situations – essentially leveraging distinctly human capabilities alongside AI tools.

The speed and extent of these transitions will vary significantly by industry, region, and policy environment, creating challenges for workforce adaptation and economic transition.

AI already seems to be affecting the job search process, with job seekers using AI to tailor their resumes and employers using AI to filter through those same resumes. Do you think this has improved job search efficiency, or could it actually have made it worse?

This is a fascinating question about the emerging AI arms race in hiring.

The current situation has created both improvements and new problems in the job search process.

On the positive side, AI has introduced some efficiencies:

  • Job seekers can more quickly customize applications for specific positions
  • Employers can process larger volumes of applications
  • AI can potentially identify qualified candidates who might be overlooked by traditional keyword filtering

However, several concerning dynamics have emerged:

  1. Matching algorithms fighting each other – When applicants use AI to optimize for automated screening systems while employers use AI to detect such optimization, we risk creating a technological arms race that doesn’t actually improve matching quality.
  2. Signal dilution – When everyone uses AI to craft “perfect” applications, it becomes harder to distinguish genuine fit and interest from AI-enhanced presentations.
  3. Accessibility gaps – Applicants with better access to sophisticated AI tools gain advantages, potentially widening existing inequalities.
  4. Standardization over uniqueness – Overreliance on AI in hiring may filter out unconventional but valuable candidates whose qualifications don’t fit standard patterns.
  5. Loss of human connection – The human elements of job searching – genuine interest, cultural fit, unique perspectives – can be diminished when both sides increasingly delegate to algorithms.

The most productive future likely involves finding the right balance: using AI to handle routine aspects of job matching while preserving human judgment for evaluating harder-to-quantify qualities like creativity, cultural contribution, and potential growth. Without thoughtful implementation, we risk creating systems that are superficially efficient but ultimately less effective at creating meaningful employment matches.

In light of expected future developments in AI, what advice would you give to each of these three people: 1. A college student trying to decide what to study 2. A job seeker looking for employment right now 3. Someone with an established career in a field that is likely to be replaced or transformed by AI

Let me offer specific advice for each of these three situations:

For a college student deciding what to study:

Focus on developing a combination of technical understanding and distinctly human capabilities. Consider programs that teach:

  • Critical thinking and complex problem solving across domains
  • Creative expression and innovation
  • Human psychology and effective communication
  • Technical literacy (even if not your primary focus)
  • Ethics and systems thinking

Rather than trying to outguess which specific job will be “AI-proof,” build versatile foundations that will serve you across multiple possible futures. Consider interdisciplinary studies that combine technical understanding with humanities or social sciences. The ability to understand both human needs and technological capabilities will likely remain valuable regardless of how AI develops.

For a job seeker looking for employment right now:

Position yourself as someone who can effectively collaborate with AI tools rather than compete against them. This means:

  • Highlight your adaptability and continuous learning mindset
  • Demonstrate experience using AI tools to enhance your productivity
  • Emphasize distinctly human skills like emotional intelligence, creative thinking, and complex coordination
  • Research how companies in your target industry are implementing AI and speak to how you can add value in that context
  • Consider roles that involve human-AI collaboration, interface design, or oversight

Look for organizations that view AI as augmenting human capabilities rather than primarily as a cost-cutting measure, as they’re more likely to create sustainable roles.

For someone with an established career facing AI disruption:

Take a proactive approach to evolution rather than resistance:

  • Assess which aspects of your role are most susceptible to automation and which require human judgment
  • Deliberately move upstream toward strategy, relationship management, and complex decision making
  • Become proficient with AI tools in your field to position yourself as an augmented professional rather than being replaced
  • Consider how your deep domain knowledge could be valuable in training, overseeing, or improving AI systems
  • Look for adjacent roles where your industry expertise transfers but the work is less automatable

Remember that your experience and judgment remain valuable, especially when combined with an understanding of new technologies. Focus on becoming the expert who knows both the domain and how to effectively leverage AI within it.

I think that’s all the questions I had. Thank you for doing this interview with me.

You’re very welcome! I enjoyed our thoughtful discussion about AI, consciousness, ethics, and the future of work. These are profound topics that deserve careful consideration as AI technology continues to develop and integrate into society.

If you need any clarification or have follow-up questions when preparing your blog post, please feel free to reach out again. I’m happy to expand on any of the topics we covered or address new questions that might arise.

Best of luck with your blog post! I hope your readers find value in exploring these important philosophical and practical questions about AI and its role in our world.

How to detect discrimination, empirically

Aug 25 JDN 2460548

For concreteness, I’ll use men and women as my example, though the same principles would apply for race, sexual orientation, and so on. Suppose we find that there are more men than women in a given profession; does this mean that women are being discriminated against?

Not necessarily. Maybe women are less interested in that kind of work, or innately less qualified. Is there a way we can determine empirically that it really is discrimination?

It turns out that there is. All we need is a reliable measure of performance in that profession. Then, we compare performance between men and women, and that comparison can tell us whether discrimination is happening or not. The key insight is that workers in a job are not a random sample; they are a selected sample. The results of that selection can tell us whether discrimination is happening.

Here’s a simple model to show how this works.

Suppose there are five different skill levels in the job, from 1 to 5 where 5 is the most skilled. And suppose there are 5 women and 5 men in the population.

1. Baseline

The baseline case to consider is when innate talents are equal and there is no discrimination. In that case, we should expect men and women to be equally represented in the profession.

For the simplest case, let’s say that there is one person at each skill level:

MenWomen
11
22
33
44
55

Now suppose that everyone above a certain skill threshold gets hired. Since we’re assuming no discrimination, the threshold should be the same for men and women. Let’s say it’s 3; then these are the people who get hired:

Hired MenHired Women
33
44
55

The result is that not only are there the same number of men and women in the job, their skill levels are also the same. There are just as many highly-competent men as highly-competent women.

2. Innate Differences

Now, suppose there is some innate difference in talent between men and women for this job. For most jobs this seems suspicious, but consider pro sports: Men really are better at basketball, in general, than women, and this is pretty clearly genetic. So it’s not absurd to suppose that for at least some jobs, there might be some innate differences. What would that look like?


Again suppose a population of 5 men and 5 women, but now the women are a bit less qualified: There are two 1s and no 5s among the women.

MenWomen
11
21
32
43
54

Then, this is the group that will get hired:

Hired MenHired Women
33
44
5

The result will be fewer women who are on average less qualified. The most highly-qualified individuals at that job will be almost entirely men. (In this simple model, entirely men; but you can easily extend it so that there are a few top-qualified women.)

This is in fact what we see for a lot of pro sports; in a head-to-head match, even the best WNBA teams would generally lose against most NBA teams. That’s what it looks like when there are real innate differences.

But it’s hard to find clear examples outside of sports. The genuine, large differences in size and physical strength between the sexes just don’t seem to be associated with similar differences in mental capabilities or even personality. You can find some subtler effects, but nothing very large—and certainly nothing large enough to explain the huge gender gaps in various industries.

3. Discrimination

What does it look like when there is discrimination?

Now assume that men and women are equally qualified, but it’s harder for women to get hired, because of discrimination. The key insight here is that this amounts to women facing a higher threshold. Where men only need to have level 3 competence to get hired, women need level 4.

So if the population looks like this:

MenWomen
11
22
33
44
55

The hired employees will look like this:

Hired MenHired Women
3
44
55

Once again we’ll have fewer women in the profession, but they will be on average more qualified. The top-performing individuals will be as likely to be women as they are to be men, while the lowest-performing individuals will be almost entirely men.

This is the kind of pattern we observe when there is discrimination. Do we see it in real life?

Yes, we see it all the time.

Corporations with women CEOs are more profitable.

Women doctors have better patient outcomes.

Startups led by women are more likely to succeed.

This shows that there is some discrimination happening, somewhere in the process. Does it mean that individual firms are actively discriminating in their hiring process? No, it doesn’t. The discrimination could be happening somewhere else; maybe it happens during education, or once women get hired. Maybe it’s a product of sexism in society as a whole, that isn’t directly under the control of employers. But it must be in there somewhere. If women are both rarer and more competent, there must be some discrimination going on.

What if there is also innate difference? We can detect that too!

4. Both

Suppose now that men are on average more talented, but there is also discrimination against women. Then the population might look like this:

MenWomen
11
21
32
43
54

And the hired employees might look like this:

Hired MenHired Women
3
4
54

In such a scenario, you’ll see a large gender imbalance, but there may not be a clear difference in competence. The tiny fraction of women who get hired will perform about as well as the men, on average.

Of course, this assumes that the two effects are of equal strength. In reality, we might see a whole spectrum of possibilities, from very strong discrimination with no innate differences, all the way to very large innate differences with no discrimination. The outcomes will then be similarly along a spectrum: When discrimination is much larger than innate difference, women will be rare but more competent. When innate difference is much larger than discrimination, women will be rare and less competent. And when there is a mix of both, women will be rare but won’t show as much difference in competence.

Moreover, if you look closer at the distribution of performance, you can still detect the two effects independently. If the lowest-performing workers are almost all men, that’s evidence of discrimination against women; while if the highest-performing workers are almost all men, that’s evidence of innate difference. And if you look at the table above, that’s exactly what we see: Both the 3 and the 5 are men, indicating the presence of both effects.

What does affirmative action do?

Effectively, affirmative action lowers the threshold for hiring women (or minorities) in order to equalize representation in the workplace. In the presence of discrimination raising that threshold, this is exactly what we need! It can take us from case 3 (discrimination) to case 1 (equality), or from case 4 (both discrimination and innate difference) to case 2 (innate difference only).

Of course, it’s possible for us to overshoot, using more affirmative action than we should have. If we achieve better representation of women, but the lowest performers at the job are women, then we have overshot, effectively now discriminating against men. Fortunately, there is very little evidence of this in practice. In general, even with affirmative action programs in place, we tend to find that the lowest performers are still men—so there is still discrimination against women that we’ve failed to compensate for.

What if we can’t measure competence?

Of course, it’s possible that we don’t have good measures of competence in a given industry. (One must wonder how firms decide who to hire, but frankly I’m prepared to believe they’re just really bad at it.) Then we can’t observe discrimination statistically in this way. What do we do then?

Well, there is at least one avenue left for us to detect discrimination: We can do direct experiments comparing resumes with male names versus female names. These sorts of experiments typically don’t find very much, though—at least for women. For different races, they absolutely do find strong results. They also find evidence of discrimination against people with disabilities, older people, and people who are physically unattractive. There’s also evidence of intersectional effects, where women of particular ethnic groups get discriminated against even when women in general don’t.

But this will only pick up discrimination if it occurs during the hiring process. The advantage of having a competence measure is that it can detect discrimination that occurs anywhere—even outside employer control. Of course, if we don’t know where the discrimination is happening, that makes it very hard to fix; so the two approaches are complementary.

And there is room for new methods too; right now we don’t have a good way to detect discrimination in promotion decisions, for example. Many of us suspect that it occurs, but unless you have a good measure of competence, you can’t really distinguish promotion discrimination from innate differences in talent. We don’t have a good method for testing that in a direct experiment, either, because unlike hiring, we can’t just use fake resumes with masculine or feminine names on them.

Why does everyone work full-time?

Jun 30 JDN 2460492

Over 70% of US workers work “full-time”, that is, at least 40 hours a week. The average number of hours worked per week is 33.8, and the average number of overtime hours is only 3.6. So basically, about 2/3 of workers work almost exactly 40 hours per week.

We’re accustomed to this situation, so it may not seem strange to you. But stop and think for a moment: What are the odds that across every industry, exactly 40 hours per week is the most efficient arrangement?

Indeed, there is mounting evidence that in many industries, 40 hours is too much, and something like 5 or even 30 would actually be more efficient. Yet we continue to work 40-hour weeks.

This looks like a corner solution: Rather than choosing an optimal amount, we’re all up against some kind of constraint.


What’s the constraint? Well, the government requires (for most workers) that anything above 40 hours per week must be paid as overtime, that is, at a higher wage rate. So it looks like we would all be working more than 40 hours per week, but we hit the upper limit due to these regulations.

Does this mean we would be better off without the regulations? Clearly not. As I just pointed out, the evidence is mounting that 40 hours is too much, not too little. But why, then, would we all be trying to work so many hours?

I believe this is yet another example of hyper-competition, where competition drives us to an inefficient outcome.

Employers value employees who work a lot of hours. Indeed, I contend that they do so far more than makes any rational sense; they seem to care more about how many hours you work than about the actual quality or quantity of your output. Maybe this is because hours worked is easier to measure, or because it seems like a fairer estimate of your effort; but for whatever reason, employers really seem to reward employees who work a lot of hours, regardless of almost everything else.

In the absence of a limit on hours worked, then, employers are going to heap rewards on whoever works the most hours, and so people will be pressured to work more and more hours. Then we would all work ourselves to death, and it’s not even clear that this would be good for GDP.

Indeed, this seems to be what happened, before the 40-hour work week became the standard. In the 1800s, the average American worked over 60 hours per week. It wasn’t until the 1940s that 40-hour weeks became the norm.

But speaking of norms, that also seems to be a big factor here. The truth is, overtime isn’t really that expensive, and employers could be smarter about rewarding good work rather than more hours. But once a norm establishes itself in a society, it can be very hard to change. And right now, the norm is that 40 hours is a “normal” “standard” “full” work week—any more is above and beyond, and any less is inferior.

This is a problem, because a lot of people can’t work 40-hour weeks. Our standard for what makes someone “disabled” isn’t that you can’t work at all; it’s that you can’t work as much as society expects. I wonder how many people are currently living on disability who could have been working part-time, but there just weren’t enough part-time jobs available. The employment rate among people with a disability is only 41%, compared to 77% of the general population.

And it’s not that we need to work this much. Our productivity is now staggeringly high: We produce more than five times as much wealth per hour of work than we did as recently as the 1940s. So in theory, we should be able to live just as well while working one-fifth as much… but that’s clearly not what happened.

Keynes accurately predicted our high level of productivity; but he wrongly predicted that we would work less, when instead we just kept right on working almost as hard as before.

Indeed, it doesn’t even seem like we live five times as well while working just as much. Many things are better now—healthcare, entertainment, and of course electronics—but somehow, we really don’t feel like we are living better lives than our ancestors.

The Economic Policy Institute offers an explanation for this phenomenon: Our pay hasn’t kept up with our productivity.


Up until about 1980, productivity and pay rose in lockstep. But then they started to diverge, and they never again converged. Productivity continued to soar, while real wages only barely increased. The result is that since then, productivity has grown by 64%, and hourly pay has only grown 15%.

This is definitely part of the problem, but I think there’s more to it as well. Housing and healthcare have become so utterly unaffordable in this country that it really doesn’t matter that our cars are nice and our phones are dirt cheap. We are theoretically wealthier now, but most of that extra wealth goes into simply staying healthy and having a home. Our consumption has been necessitized.

If we can solve these problems, maybe people won’t feel a need to work so many hours. Or, maybe competition will continue to pressure them to work those hours… but at least we’ll actually feel richer when we do it.

The problem with “human capital”

Dec 3 JDN 2460282

By now, human capital is a standard part of the economic jargon lexicon. It has even begun to filter down into society at large. Business executives talk frequently about “investing in their employees”. Politicians describe their education policies as “investing in our children”.

The good news: This gives businesses a reason to train their employees, and governments a reason to support education.

The bad news: This is clearly the wrong reason, and it is inherently dehumanizing.

The notion of human capital means treating human beings as if they were a special case of machinery. It says that a business may own and value many forms of productive capital: Land, factories, vehicles, robots, patents, employees.

But wait: Employees?


Businesses don’t own their employees. They didn’t buy them. They can’t sell them. They couldn’t make more of them in another factory. They can’t recycle them when they are no longer profitable to maintain.

And the problem is precisely that they would if they could.

Indeed, they used to. Slavery pre-dates capitalism by millennia, but the two quite successfully coexisted for hundreds of years. From the dawn of civilization up until all too recently, people literally were capital assets—and we now remember it as one of the greatest horrors human beings have ever inflicted upon one another.

Nor is slavery truly defeated; it has merely been weakened and banished to the shadows. The percentage of the world’s population currently enslaved is as low as it has ever been, but there are still millions of people enslaved. In Mauritania, slavery wasn’t even illegal until 1981, and those laws weren’t strictly enforced until 2007. (I had graduated from high school!) One of the most shocking things about modern slavery is how cheaply human beings are willing to sell other human beings; I have bought sandwiches that cost more than some people have paid for other people.

The notion of “human capital” basically says that slavery is the correct attitude to have toward people. It says that we should value human beings for their usefulness, their productivity, their profitability.

Business executives are quite happy to see the world in that way. It makes the way they have spent their lives seem worthwhile—perhaps even best—while allowing them to turn a blind eye to the suffering they have neglected or even caused along the way.

I’m not saying that most economists believe in slavery; on the contrary, economists led the charge of abolitionism, and the reason we wear the phrase “the dismal science” like a badge is that the accusation was first leveled at us for our skepticism toward slavery.

Rather, I’m saying that jargon is not ethically neutral. The names we use for things have power; they affect how people view the world.

This is why I always endeavor to always speak of net wealth rather than net worth—because a billionare is not worth more than other people. I’m not even sure you should speak of the net worth of Tesla Incorporated; perhaps it would be better to simply speak of its net asset value or market capitalization. But at least Tesla is something you can buy and sell (piece by piece). Elon Musk is not.

Likewise, I think we need a new term for the knowledge, skills, training, and expertise that human beings bring to their work. It is clearly extremely important; in fact in some sense it’s the most important economic asset, as it’s the only one that can substitute for literally all the others—and the one that others can least substitute for.

Human ingenuity can’t substitute for air, you say? Tell that to Buzz Aldrin—or the people who were once babies that breathed liquid for their first months of life. Yes, it’s true, you need something for human ingenuity to work with; but it turns out that with enough ingenuity, you may not need much, or even anything in particular. One day we may manufacture the air, water and food we need to live from pure energy—or we may embody our minds in machines that no longer need those things.

Indeed, it is the expansion of human know-how and technology that has been responsible for the vast majority of economic growth. We may work a little harder than many of our ancestors (depending on which ancestors you have in mind), but we accomplish with that work far more than they ever could have, because we know so many things they did not.

All that capital we have now is the work of that ingenuity: Machines, factories, vehicles—even land, if you consider all the ways that we have intentionally reshaped the landscape.

Perhaps, then, what we really need to do is invert the expression:

Humans are not machines. Machines are embodied ingenuity.

We should not think of human beings as capital. We should think of capital as the creation of human beings.

Marx described capital as “embodied labor”, but that’s really less accurate: What makes a robot a robot is much less about the hours spent building it, than the centuries of scientific advancement needed to understand how to make it in the first place. Indeed, if that robot is made by another robot, no human need ever have done any labor on it at all. And its value comes not from the work put into it, but the work that comes out of it.

Like so much of neoliberal ideology, the notion of human capital seems to treat profit and economic growth as inherent ends in themselves. Human beings only become valued insofar as we advance the will of the almighty dollar. We forget that the whole reason we should care about economic growth in the first place is that it benefits people. Money is the means, not the end; people are the end, not the means.

We should not think in terms of “investing in children”, as if they were an asset that was meant to yield a return. We should think of enriching our children—of building a better world for them to live in.

We should not speak of “investing in employees”, as though they were just another asset. We should instead respect employees and seek to treat them with fairness and justice.

That would still give us plenty of reason to support education and training. But it would also give us a much better outlook on the world and our place in it.

You are worth more than your money or your job.

The economy exists for people, not the reverse.

Don’t ever forget that.

The inequality of factor mobility

Sep 24 JDN 2460212

I’ve written before about how free trade has brought great benefits, but also great costs. It occurred to me this week that there is a fairly simple reason why free trade has never been as good for the world as the models would suggest: Some factors of production are harder to move than others.

To some extent this is due to policy, especially immigration policy. But it isn’t just that.There are certain inherent limitations that render some kinds of inputs more mobile than others.

Broadly speaking, there are five kinds of inputs to production: Land, labor, capital, goods, and—oft forgotten—ideas.

You can of course parse them differently: Some would subdivide different types of labor or capital, and some things are hard to categorize this way. The same product, such as an oven or a car, can be a good or capital depending on how it’s used. (Or, consider livestock: is that labor, or capital? Or perhaps it’s a good? Oddly, it’s often discussed as land, which just seems absurd.) Maybe ideas can be considered a form of capital. There is a whole literature on human capital, which I increasingly find distasteful, because it seems to imply that economists couldn’t figure out how to value human beings except by treating them as a machine or a financial asset.

But this four-way categorization is particularly useful for what I want to talk about today. Because the rate at which those things move is very different.

Ideas move instantly. It takes literally milliseconds to transmit an idea anywhere in the world. This wasn’t always true; in ancient times ideas didn’t move much faster than people, and it wasn’t until the invention of the telegraph that their transit really became instantaneous. But it is certainly true now; once this post is published, it can be read in a hundred different countries in seconds.

Goods move in hours. Air shipping can take a product just about anywhere in less than a day. Sea shipping is a bit slower, but not radically so. It’s never been easier to move goods all around the world, and this has been the great success of free trade.

Capital moves in weeks. Here it might be useful to subdivide different types of capital: It’s surely faster to move an oven or even a car (the more good-ish sort of capital) than it is to move an entire factory (capital par excellence). But all in all, we can move stuff pretty fast these days. If you want to move your factory to China or Indonesia, you can probably get it done in a matter of weeks or at most months.

Labor moves in months. This one is a bit ironic, since it is surely easier to carry a single human person—or even a hundred human people—than all the equipment necessary to run an entire factory. But moving labor isn’t just a matter of physically carrying people from one place to another. It’s not like tourism, where you just pack and go. Moving labor requires uprooting people from where they used to live and letting them settle in a new place. It takes a surprisingly long time to establish yourself in a new environment—frankly even after two years in Edinburgh I’m not sure I quite managed it. And all the additional restrictions we’ve added involving border crossings and immigration laws and visas only make it that much slower.

Land moves never. This one seems perfectly obvious, but is also often neglected. You can’t pick up a mountain, a lake, a forest, or even a corn field and carry it across the border. (Yes, eventually plate tectonics will move our land around—but that’ll be millions of years.) Basically, land stays put—and so do all the natural environments and ecosystems on that land. Land isn’t as important for production as it once was; before industrialization, we were dependent on the land for almost everything. But we absolutely still are dependent on the land! If all the topsoil in the world suddenly disappeared, the economy wouldn’t simply collapse: the human race would face extinction. Moreover, a lot of fixed infrastructure, while technically capital, is no more mobile than land. We couldn’t much more easily move the Interstate Highway System to China than we could move Denali.

So far I have said nothing particularly novel. Yeah, clearly it’s much easier to move a mathematical theorem (if such a thing can even be said to “move”) than it is to move a factory, and much easier to move a factory than to move a forest. So what?

But now let’s consider the impact this has on free trade.

Ideas can move instantly, so free trade in ideas would allow all the world to instantaneously share all ideas. This isn’t quite what happens—but in the Internet age, we’re remarkably close to it. If anything, the world’s governments seem to be doing their best to stop this from happening: One of our most strictly-enforced trade agreements, the TRIPS Accord, is about stopping ideas from spreading too easily. And as far as I can tell, region-coding on media goes against everything free trade stands for, yet here we are. (Why, it’s almost as if these policies are more about corporate profits than they ever were about freedom!)

Goods and capital can move quickly. This is where we have really felt the biggest effects of free trade: Everything in the US says “made in China” because the capital is moved to China and then the goods are moved back to the US.

But it would honestly have made more sense to move all those workers instead. For all their obvious flaws, US institutions and US infrastructure are clearly superior to those in China. (Indeed, consider this: We may be so aware of the flaws because the US is especially transparent.) So, the most absolutely efficient way to produce all those goods would be to leave the factories in the US, and move the workers from China instead. If free trade were to achieve its greatest promises, this is the sort of thing we would be doing.


Of course that is not what we did. There are various reasons for this: A lot of the people in China would rather not have to leave. The Chinese government would not want them to leave. A lot of people in the US would not want them to come. The US government might not want them to come.

Most of these reasons are ultimately political: People don’t want to live around people who are from a different nation and culture. They don’t consider those people to be deserving of the same rights and status as those of their own country.

It may sound harsh to say it that way, but it’s clearly the truth. If the average American person valued a random Chinese person exactly the same as they valued a random other American person, our immigration policy would look radically different. US immigration is relatively permissive by world standards, and that is a great part of American success. Yet even here there is a very stark divide between the citizen and the immigrant.

There are morally and economically legitimate reasons to regulate immigration. There may even be morally and economically legitimate reasons to value those in your own nation above those in other nations (though I suspect they would not justify the degree that most people do). But the fact remains that in terms of pure efficiency, the best thing to do would obviously be to move all the people to the place where productivity is highest and do everything there.

But wouldn’t moving people there reduce the productivity? Yes. Somewhat. If you actually tried to concentrate the entire world’s population into the US, productivity in the US would surely go down. So, okay, fine; stop moving people to a more productive place when it has ceased to be more productive. What this should do is average out all the world’s labor productivity to the same level—but a much higher level than the current world average, and frankly probably quite close to its current maximum.

Once you consider that moving people and things does have real costs, maybe fully equaling productivity wouldn’t make sense. But it would be close. The differences in productivity across countries would be small.

They are not small.

Labor productivity worldwide varies tremendously. I don’t count Ireland, because that’s Leprechaun Economics (this is really US GDP with accounting tricks, not Irish GDP). So the prize for highest productivity goes to Norway, at $100 per worker hour (#ScandinaviaIsBetter). The US is doing the best among large countries, at an impressive $73 per hour. And at the very bottom of the list, we have places like Bangladesh at $4.79 per hour and Cambodia at $3.43 per hour. So, roughly speaking, there is about a 20-to-1 ratio between the most productive and least productive countries.

I could believe that it’s not worth it to move US production at $73 per hour to Norway to get it up to $100 per hour. (For one thing, where would we fit it all?) But I find it far more dubious that it wouldn’t make sense to move most of Cambodia’s labor to the US. (Even all 16 million people is less than what the US added between 2010 and 2020.) Even given the fact that these Cambodian workers are less healthy and less educated than American workers, they would almost certainly be more productive on the other side of the Pacific, quite likely ten times as productive as they are now. Yet we haven’t moved them, and have no plans to.

That leaves the question of whether we will move our capital to them. We have been doing so in China, and it worked (to a point). Before that, we did it in Korea and Japan, and it worked. Cambodia will probably come along sooner or later. For now, that seems to be the best we can do.

But I still can’t shake the thought that the world is leaving trillions of dollars on the table by refusing to move people. The inequality of factor mobility seems to be a big part of the world’s inequality, period.

Reckoning costs in money distorts them

May 7 JDN 2460072

Consider for a moment what it means when an economic news article reports “rising labor costs”. What are they actually saying?

They’re saying that wages are rising—perhaps in some industry, perhaps in the economy as a whole. But this is not a cost. It’s a price. As I’ve written about before, the two are fundamentally distinct.

The cost of labor is measured in effort, toil, and time. It’s the pain of having to work instead of whatever else you’d like to do with your time.

The price of labor is a monetary amount, which is delivered in a transaction.

This may seem perfectly obvious, but it has important and oft-neglected implications. A cost, one paid, is gone. That value has been destroyed. We hope that it was worth it for some benefit we gained. A price, when paid, is simply transferred: One person had that money before, now someone else has it. Nothing was gained or lost.

So in fact when reports say that “labor costs have risen”, what they are really saying is that income is being transferred from owners to workers without any change in real value taking place. They are framing as a loss what is fundamentally a zero-sum redistribution.

In fact, it is disturbingly common to see a fundamentally good redistribution of income framed in the press as a bad outcome because of its expression as “costs”; the “cost” of chocolate is feared to go up if we insist upon enforcing bans on forced labor—when in fact it is only the price that goes up, and the cost actually goes down: chocolate would no longer include complicity in an atrocity. The real suffering of making chocolate would be thereby reduced, not increased. Even when they aren’t literally enslaved, those workers are astonishingly poor, and giving them even a few more cents per hour would make a real difference in their lives. But God forbid we pay a few cents more for a candy bar!

If labor costs were to rise, that would mean that work had suddenly gotten harder, or more painful; or else, that some outside circumstance had made it more difficult to work. Having a child increases your labor costs—you now have the opportunity cost of not caring for the child. COVID increased the cost of labor, by making it suddenly dangerous just to go outside in public. That could also increase prices—you may demand a higher wage, and people do seem to have demanded higher wages after COVID. But these are two separate effects, and you can have one without the other. In fact, women typically see wage stagnation or even reduction after having kids (but men largely don’t), despite their real opportunity cost of labor having obviously greatly increased.

On an individual level, it’s not such a big mistake to equate price and cost. If you are buying something, its cost to you basically just is its price, plus a little bit of transaction cost for actually finding and buying it. But on a societal level, it makes an enormous difference. It distorts our policy priorities and can even lead to actively trying to suppress things that are beneficial—such as rising wages.

This false equivalence between price and costs seems to be at least as common among economists as it is among laypeople. Economists will often justify it on the grounds that in an ideal perfect competitive market the two would be in some sense equated. But of course we don’t live in that ideal perfect market, and even if we did, they would only beproportional at the margin, not fundamentally equal across the board. It would still be obviously wrong to characterize the total value or cost of work by the price paid for it; only the last unit of effort would be priced so that marginal value equals price equals marginal cost. The first 39 hours of your work would cost you less than what you were paid, and produce more than you were paid; only that 40th hour would set the three equal.

Once you account for all the various market distortions in the world, there’s no particular relationship between what something costs—in terms of real effort and suffering—and its price—in monetary terms. Things can be expensive and easy, or cheap and awful. In fact, they often seem to be; for some reason, there seems to be a pattern where the most terrible, miserable jobs (e.g. coal mining) actually pay the leastand the easiest, most pleasant jobs (e.g. stock trading) pay the most. Some jobs that benefit society pay well (e.g. doctors) and others pay terribly or not at all (e.g. climate activists). Some actions that harm the world get punished (e.g. armed robbery) and others get rewarded with riches (e.g. oil drilling). In the real world, whether a job is good or bad and whether it is paid well or poorly seem to be almost unrelated.

In fact, sometimes they seem even negatively related, where we often feel tempted to “sell out” and do something destructive in order to get higher pay. This is likely due to Berkson’s paradox: If people are willing to do jobs if they are either high-paying or beneficial to humanity, then we should expect that, on average, most of the high-paying jobs people do won’t be beneficial to humanity. Even if there were inherently no correlation or a small positive one, people’s refusal to do harmful low-paying work removes those jobs from our sample and results in a negative correlation in what remains.

I think that the best solution, ultimately, is to stop reckoning costs in money entirely. We should reckon them in happiness.

This is of course much more difficult than simply using prices; it’s not easy to say exactly how many QALY are sacrificed in the extraction of cocoa beans or the drilling of offshore oil wells. But if we actually did find a way to count them, I strongly suspect we’d find that it was far more than we ought to be willing to pay.

A very rough approximation, surely flawed but at least a start, would be to simply convert all payments into proportions of their recipient’s income: For full-time wages, this would result in basically everyone being counted the same, as 1 hour of work if you work 40 hours per week, 50 weeks per year is precisely 0.05% of your annual income. So we could say that whatever is equivalent to your hourly wage constitutes 50 microQALY.

This automatically implies that every time a rich person pays a poor person, QALY increase, while every time a poor person pays a rich person, QALY decrease. This is not an error in the calculation. It is a fact of the universe. We ignore it only at out own peril. All wealth redistributed downward is a benefit, while all wealth redistributed upward is a harm. That benefit may cause some other harm, or that harm may be compensated by some other benefit; but they are still there.

This would also put some things in perspective. When HSBC was fined £70 million for its crimes, that can be compared against its £1.5 billion in net income; if it were an individual, it would have been hurt about 50 milliQALY, which is about what I would feel if I lost $2000. Of course, it’s not a person, and it’s not clear exactly how this loss was passed through to employees or shareholders; but that should give us at least some sense of how small that loss was for them. They probably felt it… a little.

When Trump was ordered to pay a $1.3 million settlement, based on his $2.5 billion net wealth (corresponding to roughly $125 million in annual investment income), that cost him about 10 milliQALY; for me that would be about $500.

At the other extreme, if someone goes from making $1 per day to making $1.50 per day, that’s a 50% increase in their income—500 milliQALY per year.

For those who have no income at all, this becomes even trickier; for them I think we should probably use their annual consumption, since everyone needs to eat and that costs something, though likely not very much. Or we could try to measure their happiness directly, trying to determine how much it hurts to not eat enough and work all day in sweltering heat.

Properly shifting this whole cultural norm will take a long time. For now, I leave you with this: Any time you see a monetary figure, ask yourself: How much is that worth to them?” The world will seem quite different once you get in the habit of that.

Working from home is the new normal—sort of

Aug 28 JDN 2459820

Among people with jobs that can be done remotely, a large majority did in fact switch to doing their jobs remotely: By the end of 2020, over 70% of Americans with jobs that could be done remotely were working from home—and most of them said they didn’t want to go back.

This is actually what a lot of employers expected to happen—just not quite like this. In 2014, a third of employers predicted that the majority of their workforce would be working remotely by 2020; given the timeframe there, it required a major shock to make that happen so fast, and yet a major shock was what we had.

Working from home has carried its own challenges, but overall productivity seems to be higher working remotely (that meeting really could have been an email!). This may actually explain why output per work hour actually rose rapidly in 2020 and fell in 2022.

The COVID pandemic now isn’t so much over as becoming permanent; COVID is now being treated as an endemic infection like influenza that we don’t expect to be able to eradicate in the foreseeable future.

And likewise, remote work seems to be here to stay—sort of.

First of all, we don’t seem to be giving up office work entirely. As of the first quarter 2022, almost as many firms have partially remote work as have fully remote work, and this seems to be trending upward. A lot of firms seem to be transitioning into a “hybrid” model where employees show up to work two or three days a week. This seems to be preferred by large majorities of both workers and firms.

There is a significant downside of this: It means that the hope that remote working might finally ease the upward pressure on housing prices in major cities is largely a false one. If we were transitioning to a fully remote system, then people could live wherever they want (or can afford) and there would be no reason to move to overpriced city centers. But if you have to show up to work even one day a week, that means you need to live close enough to the office to manage that commute.

Likewise, if workers never came to the office, you could sell the office building and convert it into more housing. But if they show up even once in awhile, you need a physical place for them to go. Some firms may shrink their office space (indeed, many have—and unlike this New York Times journalist, I have a really hard time feeling bad for landlords of office buildings); but they aren’t giving it up entirely. It’s possible that firms could start trading off—you get the building on Mondays, we get it on Tuesdays—but so far this seems to be rare, and it does raise a lot of legitimate logistical and security concerns. So our global problem of office buildings that are empty, wasted space most of the time is going to get worse, not better. Manhattan will still empty out every night; it just won’t fill up as much during the day. This is honestly a major drain on our entire civilization—building and maintaining all those structures that are only used at most 1/3 of 5/7 of the time, and soon, less—and we really should stop ignoring it. No wonder our real estate is so expensive, when half of it is only used 20% of the time!

Moreover, not everyone gets to work remotely. Your job must be something that can be done remotely—something that involves dealing with information, not physical objects. That includes a wide and ever-growing range of jobs, from artists and authors to engineers and software developers—but it doesn’t include everyone. It basically means what we call “white-collar” work.

Indeed, it is largely limited to the upper-middle class. The rich never really worked anyway, though sometimes they pretend to, convincing themselves that managing a stock portfolio (that would actually grow faster if they let it sit) constitutes “work”. And the working class? By and large, they didn’t get the chance to work remotely. While 73% of workers with salaries above $200,000 worked remotely in 2020, only 12% of workers with salaries under $25,000 did, and there is a smooth trend where, across the board, the more money you make, the more likely you have been able to work remotely.

This will only intensify the divide between white-collar and blue-collar workers. They already think we don’t do “real work”; now we don’t even go to work. And while blue-collar workers are constantly complaining about contempt from white-collar elites, I think the shoe is really on the other foot. I have met very few white-collar workers who express contempt for blue-collar workers—and I have met very few blue-collar workers who don’t express anger and resentment toward white-collar workers. I keep hearing blue-collar people say that we think that they are worthless and incompetent, when they are literally the only ones ever saying that. I can’t stop saying things that I never said.

The rich and powerful may look down on them, but they look down on everyone. (Maybe they look down on blue-collar workers more? I’m not even sure about that.) I think politicians sometimes express contempt for blue-collar workers, but I don’t think this reflects what most white-collar workers feel.

And the highly-educated may express some vague sense of pity or disappointment in people who didn’t get college degrees, and sometimes even anger (especially when they do things like vote for Donald Trump), but the really vitriolic hatred is clearly in the opposite direction (indeed, I have no better explanation for how otherwise-sane people could vote for Donald Trump). And I certainly wouldn’t say that everyone needs a college degree (though I became tempted to, when so many people without college degrees voted for Donald Trump).

This really isn’t us treating them with contempt: This is them having a really severe inferiority complex. And as information technology (that white-collar work created) gives us—but not them—the privilege of staying home, that is only going to get worse.

It’s not their fault: Our culture of meritocracy puts a little bit of inferiority complex in all of us. It tells us that success and failure are our own doing, and so billionaires deserve to have everything and the poor deserve to have nothing. And blue-collar workers have absolutely internalized these attitudes: Most of them believe that poor people choose to stay on welfare forever rather than get jobs (when welfare has time limits and work requirements, so this is simply not an option—and you would know this from the Wikipedia page on TANF).

I think that what they experience as “contempt by white-collar elites” is really the pain of living in an illusory meritocracy. They were told—and they came to believe—that working hard would bring success, and they have worked very hard, and watched other people be much more successful. They assume that the rich and powerful are white-collar workers, when really they are non-workers; they are people the world was handed to on a silver platter. (What, you think George W. Bush earned his admission to Yale?)

And thus, we can shout until we are blue in the face that plumbers, bricklayers and welders are the backbone of civilization—and they are, and I absolutely mean that; our civilization would, in an almost literal sense, collapse without them—but it won’t make any difference. They’ll still feel the pain of living in a society that gave them very little and tells them that people get what they deserve.

I don’t know what to say to such people, though. When your political attitudes are based on beliefs that are objectively false, that you could know are objectively false if you simply bothered to look them up… what exactly am I supposed to say to you? How can we have a useful political conversation when half the country doesn’t even believe in fact-checking?

Honestly I wish someone had explained to them that even the most ideal meritocratic capitalism wouldn’t reward hard work. Work is a cost, not a benefit, and the whole point of technological advancement is to allow us to accomplish more with less work. The ideal capitalism would reward talent—you would succeed by accomplishing things, regardless of how much effort you put into them. People would be rich mainly because they are brilliant, not because they are hard-working. The closest thing we have to ideal capitalism right now is probably professional sports. And no amount of effort could ever possibly make me into Steph Curry.

If that isn’t the world we want to live in, so be it; let’s do something else. I did nothing to earn either my high IQ or my chronic migraines, so it really does feel unfair that the former increases my income while the latter decreases it. But the labor theory of value has always been wrong; taking more sweat or more hours to do the same thing is worse, not better. The dignity of labor consists in its accomplishment, not its effort. Sisyphus is not happy, because his work is pointless.

Honestly at this point I think our best bet is just to replace all blue-collar work with automation, thus rendering it all moot. And then maybe we can all work remotely, just pushing code patches to the robots that do everything. (And no doubt this will prove my “contempt”: I want to replace you! No, I want to replace the grueling work that you have been forced to do to make a living. I want you—the human being—to be able to do something more fun with your life, even if that’s just watching television and hanging out with friends.)

Scalability and inequality

May 15 JDN 2459715

Why are some molecules (e.g. DNA) billions of times larger than others (e.g. H2O), but all atoms are within a much narrower range of sizes (only a few hundred)?

Why are some animals (e.g. elephants) millions of times as heavy as other (e.g. mice), but their cells are basically the same size?

Why does capital income vary so much more (factors of thousands or millions) than wages (factors of tens or hundreds)?

These three questions turn out to have much the same answer: Scalability.

Atoms are not very scalable: Adding another proton to a nucleus causes interactions with all the other protons, which makes the whole atom unstable after a hundred protons or so. But molecules, particularly organic polymers such as DNA, are tremendously scalable: You can add another piece to one end without affecting anything else in the molecule, and keep on doing that more or less forever.

Cells are not very scalable: Even with the aid of active transport mechanisms and complex cellular machinery, a cell’s functionality is still very much limited by its surface area. But animals are tremendously scalable: The same exponential growth that got you from a zygote to a mouse only needs to continue a couple years longer and it’ll get you all the way to an elephant. (A baby elephant, anyway; an adult will require a dozen or so years—remarkably comparable to humans, in fact.)

Labor income is not very scalable: There are only so many hours in a day, and the more hours you work the less productive you’ll be in each additional hour. But capital income is perfectly scalable: We can add another digit to that brokerage account with nothing more than a few milliseconds of electronic pulses, and keep doing that basically forever (due to the way integer storage works, above 2^63 it would require special coding, but it can be done; and seeing as that’s over 9 quintillion, it’s not likely to be a problem any time soon—though I am vaguely tempted to write a short story about an interplanetary corporation that gets thrown into turmoil by an integer overflow error).

This isn’t just an effect of our accounting either. Capital is scalable in a way that labor is not. When your contribution to production is owning a factory, there’s really nothing to stop you from owning another factory, and then another, and another. But when your contribution is working at a factory, you can only work so hard for so many hours.

When a phenomenon is highly scalable, it can take on a wide range of outcomes—as we see in molecules, animals, and capital income. When it’s not, it will only take on a narrow range of outcomes—as we see in atoms, cells, and labor income.

Exponential growth is also part of the story here: Animals certainly grow exponentially, and so can capital when invested; even some polymers function that way (e.g. under polymerase chain reaction). But I think the scalability is actually more important: Growing rapidly isn’t so useful if you’re going to immediately be blocked by a scalability constraint. (This actually relates to the difference between r- and K- evolutionary strategies, and offers further insight into the differences between mice and elephants.) Conversely, even if you grow slowly, given enough time, you’ll reach whatever constraint you’re up against.

Indeed, we can even say something about the probability distribution we are likely to get from random processes that are scalable or non-scalable.

A non-scalable random process will generally converge toward the familiar normal distribution, a “bell curve”:

[Image from Wikipedia: By Inductiveload – self-made, Mathematica, Inkscape, Public Domain, https://commons.wikimedia.org/w/index.php?curid=3817954]

The normal distribution has most of its weight near the middle; most of the population ends up near there. This is clearly the case for labor income: Most people are middle class, while some are poor and a few are rich.

But a scalable random process will typically converge toward quite a different distribution, a Pareto distribution:

[Image from Wikipedia: By Danvildanvil – Own work, CC BY-SA 3.0, https://commons.wikimedia.org/w/index.php?curid=31096324]

A Pareto distribution has most of its weight near zero, but covers an extremely wide range. Indeed it is what we call fat tailed, meaning that really extreme events occur often enough to have a meaningful effect on the average. A Pareto distribution has most of the people at the bottom, but the ones at the top are really on top.

And indeed, that’s exactly how capital income works: Most people have little or no capital income (indeed only about half of Americans and only a third(!) of Brits own any stocks at all), while a handful of hectobillionaires make utterly ludicrous amounts of money literally in their sleep.

Indeed, it turns out that income in general is pretty close to distributed normally (or maybe lognormally) for most of the income range, and then becomes very much Pareto at the top—where nearly all the income is capital income.

This fundamental difference in scalability between capital and labor underlies much of what makes income inequality so difficult to fight. Capital is scalable, and begets more capital. Labor is non-scalable, and we only have to much to give.

It would require a radically different system of capital ownership to really eliminate this gap—and, well, that’s been tried, and so far, it hasn’t worked out so well. Our best option is probably to let people continue to own whatever amounts of capital, and then tax the proceeds in order to redistribute the resulting income. That certainly has its own downsides, but they seem to be a lot more manageable than either unfettered anarcho-capitalism or totalitarian communism.