inequality

The Republicans passed a terrible budget

PNRJ current events, inequality, politics, public policy , , , , , , , , ,

May 4 JDN 2460800

On April 10, the US House of Representatives passed a truly terrible budget bill. It passed on an almost entirely partisan vote—214 Democrats against, 216 Republicans for, 2 Republicans against. So I think it’s quite fair to say that the Republicans passed this budget—not a single Democrat voted for it, and only 2 Republicans voted against it.

So what’s so bad about it?

Well, first of all, in order to avoid showing just how much it will balloon the national debt, the new budget operates on different accounting rules than normal, using what’s called “current policy baseline” instead of the standard method of assuming that policies will end after 10 years.

In addition to retaining $3.8 trillion in tax cuts that were supposed to expire, this budget will cut taxes by $1.5 trillion over 10 years, with the vast majority of those cuts going to the top 1%—thus the real increase in the deficit is a staggering $5.3 trillion over 10 years. This is absolutely not what we need, given that unemployment is actually pretty good right now and we still have a deficit of $1.8 trillion per year. (Yes, really.) That kind of deficit is good in response to a severe recession—I was all in favor of it during COVID, and it worked. But when the economy is good, you’re supposed to balance the budget, and they haven’t.

The richest 1% stand to gain about 4% more income from these tax cuts (which adds up to about $240 billion per year), while the combination of tax cuts and spending cuts would most likely reduce the income of 40% of the population.

They aren’t even cutting spending to offset these tax cuts. This budget only includes a paltry $4 billion in spending cuts—less than 0.1% of the budget. (I mean, sure, $4 billion is a lot of money for a person; but for a whole country as rich and large as ours? It’s a rounding error.) And then it includes $521 billion in spending increases, over 100 times as much.

They are talking about making more cuts, but they’ve been cagey as to where, probably because the only plausible ways to save this much money are the military, Medicaid, Medicare, or Social Security. Obviously Republicans will never cut the military, but the other three programs are also enormously popular, even in deep-red states. It would be not only very harmful to millions of people to cut these programs—it would also be harmful to the Republicans’ re-election chances. They could also get some savings by cutting income security programs like SNAP and TANF, which would probably be less unpopular—but it would also cause enormous suffering.

This new budget is estimated to add some $6.9 trillion to the national debt over 10 years—and even more after that, if the policies actually continue.

I am not exactly a “deficit hawk”; I don’t think the budget should always be balanced. But this is not the time to be increasing the deficit. When times are good, we should balance the budget, so that when we have to go into debt during bad times, we can afford to do so.

And bad times are probably on the horizon, since Trump’s tariff policy is already such a disaster. So are we going to borrow even more then? While bond yields are rising? We’re going to end up spending most of our budget on debt payments! And all this injection of money into the system won’t be good for inflation either (and on top of the tariffs!).

The only sensible thing to do right now is raise taxes on the rich. We need that revenue. We can’t just keep going deeper into debt. And the rich are the ones who would be least harmed by raising taxes—indeed, if you focused the hikes on billionaires, they would barely feel anything at all.

But the Republicans don’t care about what’s in the interest of ordinary Americans. They only care about the interests of the rich. And that’s why they passed this budget.

An interview with Claude

PNRJ cognitive science, current events, ethics, futurism, inequality , , , , , , , , ,

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.

Extrapolating the INE

PNRJ critique of neoclassical economics, current events, inequality, public policy , , , , , , , , , , ,

Apr 6 JDN 2460772

I was only able to find sufficient data to calculate the Index of Necessary Expenditure back to 1990. But I found a fairly consistent pattern that the INE grew at a rate about 20% faster than the CPI over that period, so I decided to take a look at what longer-term income growth looks like if we extrapolate that pattern back further in time.

The result is this graph:

Using the CPI, real per-capita GDP in the US (in 2024 dollars) has grown from $25,760 in 1950 to $85,779 today—increasing by a factor of 3.33. Even accounting for increased inequality and the fact that more families have two income earners, that’s still a substantial increase.

But using the extrapolated INE, real per-capita GDP has only grown from $43,622 in 1950 to $85,779 today—increasing by only a factor of 1.97. This is a much smaller increase, especially when we adjusted for increased inequality and increased employment for women.

Even without the extrapolation, it’s still clear that real INE-adjusted incomes have were basically stagnant in the 2000s, increased rather slowly in the 2020s, and then actually dropped in 2022 after a bunch of government assistance ended. What looked, under the CPI, like steadily increasing real income was actually more like treading water.

Should we trust this extrapolation? It’s a pretty simplistic approach, I admit. But I think it is plausible when we consider this graph of the ratio between median income and median housing price:

This ratio was around 6 in the 1950s, then began to fall until in the 1970s it stabilized around 4. It began to slowly creep back up, but then absolutely skyrocketed in the 2000s before the 2008 crash. Now it has been rising again, and is now above 7, the highest it has been since the Second World War. (Does this mean we’re due for another crash? I’d bet as much.)

What does this mean? It means that a typical family used to be able to afford a typical house with only four years of their total income—and now would require seven. In that sense, homes are now 75% more expensive today than they were in the 1970s.

Similar arguments can be made for the rising costs of education and healthcare; while many prices have not grown much (gasoline) or even fallen (jewelry and technology), these necessities have continued to grow more and more expensive, not simply in nominal terms, but even compared to the median income.

This is further evidence that our standard measures of “inflation” and “real income” are fundamentally inadequate. They simply aren’t accurately reflecting the real cost of living for most American families. Even in many times when it seemed “inflation” was low and “real income” was growing, in fact it was growing harder and harder to afford vital necessities such as housing, education, and healthcare.

This economic malaise may have been what contributed to the widespread low opinion of Biden’s economy. While the official figures looked good, people’s lives weren’t actually getting better.

Yet this is still no excuse for those who voted for Trump; even the policies he proudly announced he would do—like tariffs and deportations—have clearly made these problems worse, and this was not only foreseeable but actually foreseen by the vast majority of the world’s economists. Then there are all the things he didn’t even say he would do but is now doing, like cozying up to Putin, alienating our closest allies, and discussing “methods” for achieving an unconstitutional third term.

Indeed, it honestly feels quite futile to even reflect upon what was wrong with our economy even when things seemed to be running smoothly, because now things are rapidly getting worse, and showing no sign of getting better in any way any time soon.

A new theoretical model of co-ops

PNRJ critique of neoclassical economics, inequality, market failure, mathematical models, public policy , , , , , , , , ,

Mar 30 JDN 2460765

A lot of economists seem puzzled by the fact that co-ops are just as efficient as corporate firms, since they have this idea that profit-sharing inevitably results in lower efficiency due to perverse incentives.

I think they’ve been modeling co-ops wrong. Here I present a new model, a very simple one, with linear supply and demand curves. Of course one could make a more sophisticated model, but this should be enough to make the point (and this is just a blog post, not a research paper, after all).

Demand curve is p = a – b q

Marginal cost is f q

There are n workers, who would hold equal shares of the co-op.

Competitive market

First, let’s start with the traditional corporate firm in a competitive market.

Since the market is competitive, price would equal marginal cost would equal wage:

a – b q = d q

q = a/(b+f)

w = d (a/(b+f)) = (a d)/(b+f)

Total profit will be

(p – w)q = 0.

Monopoly firm

In a monopoly, marginal revenue would equal marginal cost:
d[pq]/dq = a – 2 b q

If they are also a monopsonist in the labor market, this marginal cost would be marginal cost of labor, not wage:

d[d q2]/dq = 2 f q

a – 2 b q = 2 f q

q = a/(2b + 2f)

p = a – b q = a (1 – b/(2b + 2f)) = (a (b + 2f))/(2b + 2f)

w = d q = (a f)/(2b + 2f)

Total profit will be

(p – w) q = ((a (b + 2f))/(2b + 2f) – (a f)/(2b + 2f))a/(2b + 2f) = a2/(4b + 2f)

Now consider the co-op.

First, suppose that instead of working for a wage, I work for profit sharing.

If our product market is competitive, we’ll be price-takers, and we will produce until price equals marginal cost:

p = f q

a – b q = f q

q = a/(a+b)

But will we, really? I only get 1/n share of the profits. So let’s see here. My marginal cost of production is still f q, but the marginal benefit I get from more sales may only be p/n.

In that case I would work until:

p/n = f q

(a – b q)/n = fq

a – b q = n f q

q = (a/(b+nf))

Thus I would under-produce. This is the usual argument against co-ops and similar shared ownership.

Co-ops with wages

But that’s not actually how co-ops work. They pay wages. Why do they do that? Well, consider what happens if I am offered a wage as a worker-owner of the co-op.

Is there any reason for the co-op to vote on a wage that is less than the competitive market? No, because owners are workers, so any additional profit from a lower wage would simply be taken from their own wages.

If there any reason for the co-op to vote on a wage that is more than the competitive market? No, because workers are owners, and any surplus lost by paying higher wages would simply be taken from their own profits.

So if the product market is competitive, the co-op will produce the same amount and charge the same price as a firm in perfect competition, even if they have market power over their own wages.

Monopoly co-ops

The argument above doesn’t assume that the co-op has no market power in the labor market. Thus if they are a monopoly in the product market and a monopsony in the labor market, they still pay a competitive wage.

Thus they would set marginal revenue equal to marginal cost:

a – 2 b q = f q

q = a/(2b + f)

The co-op will produce more than the monopoly firm..

This is the new price:

p = a – b q = a(1 – b/(2b+f)) = a(b+f)/(2b + f)

It’s not obvious that this is lower than the price charged by the monopoly firm, but it is.

(a (b + 2f))/(2b + 2f) – a(b+f)/(2b + f) = (a (2b + f)(b + 2f) – 2 a(b+f)2)/(2(b+f)(2b+f))

This is proportional to:

(2b + f)(b + 2f) – 2(b+f)2

2b2 + 5bf + 2f2 – (2b2 + 4bf + 2f2) = bf

So it’s not a large difference, but it’s there. In the presence of market power in the labor market, the co-op is better for consumers, because they get more goods and pay a lower price.

Thus, there is actually no lost efficiency from being a co-op. There is simply much lower inequality, and potentially higher efficiency.

But that’s just in theory.

What do we see in practice?

Exactly that.

Co-ops have the same productivity and efficiency as corporate firms, but they pay higher wages, provide better benefits, and offer collateral benefits to their communities. In fact, they are sometimes more efficient than corporate firms.

Since they’re just as efficient—if not more so—and produce much lower inequality, switching more firms over to co-ops would clearly be a good thing.

Why, then, aren’t co-ops more common?

Because the people who have the money don’t like them.

The biggest barrier facing co-ops is their inability to get financing, because they don’t pay shareholders (so no IPOs) and banks don’t like to lend to them. They tend to make less profit than corporate firms, which offers investors a lower return—instead that money goes to the worker-owners. This lower return isn’t due to inefficiency; it’s just a different distribution of income, more to labor and less to capital.

We will need new financial institutions to support co-ops, such as the Cooperative Fund of New England. And general redistribution of wealth would also help, because if middle class people had more wealth they could afford to finance co-ops. (It would also be good for many other reasons, of course.)

Reflections on the Index of Necessary Expenditure

PNRJ inequality, macroeconomics, public policy, statistics , , , , , , , , , , , ,

Mar 16 JDN 2460751

In last week’s post I constructed an Index of National Expenditure (INE), attempting to estimate the total cost of all of the things a family needs and can’t do without, like housing, food, clothing, cars, healthcare, and education. What I found shocked me: The median family cannot afford all necessary expenditures.

I have a couple more thoughts about that.

I still don’t understand why people care so much about gas prices.

Gasoline was a relatively small contribution to INE. It was more than clothing but less than utilities, and absolutely dwarfed by housing, food, or college. I thought maybe since I only counted a 15-mile commute, maybe I didn’t actually include enoughgasoline usage, but based on this estimate of about $2000 per driver, I was in about the right range; my estimate for the same year was $3350 for a 2-car family.

I think I still have to go with my salience hypothesis: Gasoline is the only price that we plaster in real-time on signs on the side of the road. So people are constantly aware of it, even though it isn’t actually that important.

The price surge that should be upsetting people is housing.

If the price of homes had only risen with the rate of CPI inflation instead of what it actually did, the median home price in 2024 would be only $234,000 instead of the $396,000 it actually is; and by my estimation that would save a typical family $11,000 per year—a whopping 15% of their income, and nearly enough to make the INE affordable by itself.

Now, I’ll consider some possible objections to my findings.

Objection 1: A typical family doesn’t actually spend this much on these things.

You’re right, they don’t! Because they couldn’t possibly. Even with substantial debt, you just can’t sustainably spend 125% of your after-tax household income.

My goal here was not to estimate how much families actually spend; it was to estimate how much they need to spend in order to live a good life and not feel deprived.


What I have found is that most American families feel deprived. They are forced to sacrifice something really important—like healthcare, or education, or owning a home—because they simply can’t afford it.

What I’m trying to do here is find the price of the American Dream; and what I’ve found is that the American Dream has a price that most Americans cannot afford.

Objection 2: You should use median healthcare spending, not mean.

I did in fact use mean figures instead of median for healthcare expenditures, mainly because only the mean was readily available. Mean income is higher than median income, so you might say that I’ve overestimated healthcare expenditure—and in a sense that’s definitely true. The median family spends less than this on healthcare.

But the reason that the median family spends less than this on healthcare is not that they want to, but that they have to. Healthcare isn’t a luxury that people buy more of because they are richer. People buy either as much as they need or as much as they can afford—whichever is lower, which is typically the latter. Using the mean instead of the median is a crude way to account for that, but I think it’s a defensible one.

But okay, let’s go ahead and cut the estimate of healthcare spending in half; even if you do that, the INE is still larger than after-tax median household income in most years.

Objection 3: A typical family isn’t a family of four, it’s a family of three.

Yes, the mean number of people in a family household in the US is 3.22 (the median is 3).

This is a very bad thing.

Part of what I seem to be finding here is that a family of four is unaffordable—literally impossible to afford—on a typical family income.

But a healthy society is one in which typical families have two or three children. That is what we need in order to achieve population replacement. When families get smaller than that, we aren’t having enough children, and our population will decline—which means that we’ll have too many old people relative to young people. This puts enormous pressure on healthcare and pension systems, which rely upon the fact that young people produce more, in order to pay for the fact that old people cost more.

The ideal average number of births per woman is about 2.1; this is what would give us a steady population. No US state has fertility above this level. The only reason the US population is growing rather than shrinking is that we are taking in immigrants.

This is bad. This is not sustainable. If the reason families aren’t having enough kids is that they can’t afford them—and this fits with other research on the subject—then this economic failure damages our entire society, and it needs to be fixed.

Objection 4: Many families buy their cars used.

Perhaps 1/10 of a new car every year isn’t an ideal estimate of how much people spend on their cars, but if anything I think it’s conservative, because if you only buy a car every 10 years, and it was already used when you bought it, you’re going to need to spend a lot on maintaining it—quite possibly more than it would cost to get a new one. Motley Fool actually estimates the ownership cost of just one car at substantially more than I estimated for two cars. So if anything your complaint should be that I’ve underestimated the cost by not adequately including maintenance and insurance.

Objection 5: Not everyone gets a four-year college degree.

Fair enough; a substantial proportion get associate’s degrees, and most people get no college degree at all. But some also get graduate degrees, which is even more expensive (ask me how I know).

Moreover, in today’s labor market, having a college degree makes a huge difference in your future earnings; a bachelor’s degree increases your lifetime earnings by a whopping 84%. In theory it’s okay to have a society where most people don’t go to college; in practice, in our society, not going to college puts you at a tremendous disadvantage for the rest of your life. So we either need to find a way to bring wages up for those who don’t go to college, or find a way to bring the cost of college down.

This is probably one of the things that families actually choose to scrimp on, only sending one kid to college or none at all. But because college is such a huge determinant of earnings, this perpetuates intergenerational inequality: Only rich families can afford to send their kids to college, and only kids who went to college grow up to have rich families.

Objection 6: You don’t actually need to save for college; you can use student loans.

Yes, you can, and in practice, most people who to college do. But while this solves the liquidity problem (having enough money right now), it does not solve the solvency problem (having enough money in the long run). Failing to save for college and relying on student loans just means pushing the cost of college onto your children—and since we’ve been doing that for over a generation, feel free to replace the category “college savings” with “repaying student loans”; it won’t meaningfully change the results.

The Index of Necessary Expenditure

PNRJ core principles, critique of neoclassical economics, current events, inequality, politics, public policy, statistics , , , , , , , , , ,

Mar 16 JDN 2460751

I’m still reeling from the fact that Donald Trump was re-elected President. He seemed obviously horrible at the time, and he still seems horrible now, for many of the same reasons as before (we all knew the tariffs were coming, and I think deep down we knew he would sell out Ukraine because he loves Putin), as well as some brand new ones (I did not predict DOGE would gain access to all the government payment systems, nor that Trump would want to start a “crypto fund”). Kamala Harris was not an ideal candidate, but she was a good candidate, and the comparison between the two could not have been starker.

Now that the dust has cleared and we have good data on voting patterns, I am now less convinced than I was that racism and sexism were decisive against Harris. I think they probably hurt her some, but given that she actually lost the most ground among men of color, racism seems like it really couldn’t have been a big factor. Sexism seems more likely to be a significant factor, but the fact that Harris greatly underperformed Hillary Clinton among Latina women at least complicates that view.

A lot of voters insisted that they voted on “inflation” or “the economy”. Setting aside for a moment how absurd it was—even at the time—to think that Trump (he of the tariffs and mass deportations!) was going to do anything beneficial for the economy, I would like to better understand how people could be so insistent that the economy was bad even though standard statistical measures said it was doing fine.

Krugman believes it was a “vibecession”, where people thought the economy was bad even though it wasn’t. I think there may be some truth to this.


But today I’d like to evaluate another possibility, that what people were really reacting against was not inflation per se but necessitization.

I first wrote about necessitization in 2020; as far as I know, the term is my own coinage. The basic notion is that while prices overall may not have risen all that much, prices of necessities have risen much faster, and the result is that people feel squeezed by the economy even as CPI growth remains low.

In this post I’d like to more directly evaluate that notion, by constructing an index of necessary expenditure (INE).

The core idea here is this:

What would you continue to buy, in roughly the same amounts, even if it doubled in price, because you simply can’t do without it?

For example, this is clearly true of housing: You can rent or you can own, but can’t not have a house. And nor are most families going to buy multiple houses—and they can’t buy partial houses.

It’s also true of healthcare: You need whatever healthcare you need. Yes, depending on your conditions, you maybe could go without, but not without suffering, potentially greatly. Nor are you going to go out and buy a bunch of extra healthcare just because it’s cheap. You need what you need.

I think it’s largely true of education as well: You want your kids to go to college. If college gets more expensive, you might—of necessity—send them to a worse school or not allow them to complete their degree, but this would feel like a great hardship for your family. And in today’s economy you can’t not send your kids to college.

But this is not true of technology: While there is a case to be made that in today’s society you need a laptop in the house, the fact is that people didn’t used to have those not that long ago, and if they suddenly got a lot cheaper you very well might buy another one.

Well, it just so happens that housing, healthcare, and education have all gotten radically more expensive over time, while technology has gotten radically cheaper. So prima facie, this is looking pretty plausible.

But I wanted to get more precise about it. So here is the index I have constructed. I consider a family of four, two adults, two kids, making the median household income.

To get the median income, I’ll use this FRED series for median household income, then use this table of median federal tax burden to get an after-tax wage. (State taxes vary too much for me to usefully include them.) Since the tax table ends in 2020 which was anomalous, I’m going to extrapolate that 2021-2024 should be about the same as 2019.

I assume the kids go to public school, but the parents are saving up for college; to make the math simple, I’ll assume the family is saving enough for each kid to graduate from with a four-year degree from a public university, and that saving is spread over 16 years of the child’s life. 2*4/16 = 0.5; this means that each year the family needs to come up with 0.5 years of cost of attendance. (I had to get the last few years from here, but the numbers are comparable.)

I assume the family owns two cars—both working full time, they kinda have to—which I amortize over 10 year lifetimes; 2*1/10 = 0.2, so each year the family pays 0.2 times the value of an average midsize car. (The current average new car price is $33226; I then use the CPI for cars to figure out what it was in previous years.)

I assume they pay a 30-year mortgage on the median home; they would pay interest on this mortgage, so I need to factor that in. I’ll assume they pay the average mortgage rate in that year, but I don’t want to have to do a full mortgage calculation (including PMI, points, down payment etc.) for each year, so I’ll say that they amount they pay is (1/30 + 0.5 (interest rate))*(home value) per year, which seems to be a reasonable approximation over the relevant range.

I assume that both adults have a 15-mile commute (this seems roughly commensurate with the current mean commute time of 26 minutes), both adults work 5 days per week, 50 weeks per year, and their cars get the median level of gas mileage. This means that they consume 2*15*2*5*50/(median MPG) = 15000/(median MPG) gallons of gasoline per year. I’ll use this BTS data for gas mileage. I’m intentionally not using median gasoline consumption, because when gas is cheap, people might take more road trips, which is consumption that could be avoided without great hardship when gas gets expensive. I will also assume that the kids take the bus to school, so that doesn’t contribute to the gasoline cost.

That I will multiply by the average price of gasoline in June of that year, which I have from the EIA since 1993. (I’ll extrapolate 1990-1992 as the same as 1993, which is conservative.)

I will assume that the family owns 2 cell phones, 1 computer, and 1 television. This is tricky, because the quality of these tech items has dramatically increased over time.

If you try to measure with equivalent buying power (e.g. a 1 MHz computer, a 20-inch CRT TV), then you’ll find that these items have gotten radically cheaper; $1000 in 1950 would only buy as much TV as $7 today, and a $50 Raspberry Pi‘s 2.4 GHz processor is 150 times faster than the 16 MHz offered by an Apple Powerbook in 1991—despite the latter selling for $2500 nominally. So in dollars per gigahertz, the price of computers has fallen by an astonishing 7,500 times just since 1990.

But I think that’s an unrealistic comparison. The standards for what was considered necessary have also increased over time. I actually think it’s quite fair to assume that people have spent a roughly constant nominal amount on these items: about $500 for a TV, $1000 for a computer, and $500 for a cell phone. I’ll also assume that the TV and phones are good for 5 years while the computer is good for 2 years, which makes the total annual expenditure for 2 phones, a TV, and a computer equal to 2/5*500 + 1/5*500 + 1/2*1000 = 800. This is about what a family must spend every year to feel like they have an adequate amount of digital technology.

I will also assume that the family buys clothes with this equivalent purchasing power, with an index that goes from 166 in 1990 to 177 in 2024—also nearly constant in nominal terms. I’ll multiply that index by $10 because the average annual household spending on clothes is about $1700 today.

I will assume that the family buys the equivalent of five months of infant care per year; they surely spend more than this (in either time or money) when they have actual infants, but less as the kids grow. This amounts to about $5000 today, but was only $1600 in 1990—a 214% increase, or 3.42% per year.

For food expenditure, I’m going to use the USDA’s thrifty plan for June of that year. I’ll use the figures assuming that one child is 6 and the other is 9. I don’t have data before 1994, so I’ll extrapolate that with the average growth rate of 3.2%.

Food expenditures have been at a fairly consistent 11% of disposable income since 1990; so I’m going to include them as 2*11%*40*50*(after-tax median wage) = 440*(after-tax median wage).

The figures I had the hardest time getting were for utilities. It’s also difficult to know what to include: Is Internet access a necessity? Probably, nowadays—but not in 1990. Should I separate electric and natural gas, even though they are partial substitutes? But using these figures I estimate that utility costs rise at about 0.8% per year in CPI-adjusted terms, so what I’ll do is benchmark to $3800 in 2016 and assume that utility costs have risen by (0.8% + inflation rate) per year each year.

Healthcare is also a tough one; pardon the heteronormativity, but for simplicity I’m going to use the mean personal healthcare expenditures for one man and woman (aged 19-44) and one boy and one girl (aged 0-18). Unfortunately I was only able to find that for two-year intervals in the range from 2002 to 2020, so I interpolated and extrapolated both directions assuming the same average growth rate of 3.5%.

So let’s summarize what all is included here:

  • Estimated payment on a mortgage
  • 0.5 years of college tuition
  • amortized cost of 2 cars
  • 7500/(median MPG) gallons of gasoline
  • amortized cost of 2 phones, 1 computer, and 1 television
  • average spending on clothes
  • 11% of income on food
  • Estimated utilities spending
  • Estimated childcare equivalent to five months of infant care
  • Healthcare for one man, one woman, one boy, one girl

There are obviously many criticisms you could make of these choices. If I were writing a proper paper, I would search harder for better data and run robustness checks over the various estimation and extrapolation assumptions. But for these purposes I really just want a ballpark figure, something that will give me a sense of what rising cost of living feels like to most people.

What I found absolutely floored me. Over the range from 1990 to 2024:

  1. The Index of Necessary Expenditure rose by an average of 3.45% per year, almost a full percentage point higher than the average CPI inflation of 2.62% per year.
  2. Over the same period, after-tax income rose at a rate of 3.31%, faster than CPI inflation, but slightly slower than the growth rate of INE.
  3. The Index of Necessary Expenditure was over 100% of median after-tax household income every year except 2020.
  4. Since 2021, the Index of Necessary Expenditure has risen at an average rate of 5.74%, compared to CPI inflation of only 2.66%. In that same time, after-tax income has only grown at a rate of 4.94%.

Point 3 is the one that really stunned me. The only time in the last 34 years that a family of four has been able to actually pay for all necessities—just necessities—on a typical household income was during the COVID pandemic, and that in turn was only because the federal tax burden had been radically reduced in response to the crisis. This means that every single year, a typical American family has been either going further and further into debt, or scrimping on something really important—like healthcare or education.

No wonder people feel like the economy is failing them! It is!

In fact, I can even make sense now of how Trump could convince people with “Are you better off than you were four years ago?” in 2024 looking back at 2020—while the pandemic was horrific and the disruption to the economy was massive, thanks to the US government finally actually being generous to its citizens for once, people could just about actually make ends meet. That one year. In my entire life.

This is why people felt betrayed by Biden’s economy. For the first time most of us could remember, we actually had this brief moment when we could pay for everything we needed and still have money left over. And then, when things went back to “normal”, it was taken away from us. We were back to no longer making ends meet.

When I went into this, I expected to see that the INE had risen faster than both inflation and income, which was indeed the case. But I expected to find that INE was a large but manageable proportion of household income—maybe 70% or 80%—and slowly growing. Instead, I found that INE was greater than 100% of income in every year but one.

And the truth is, I’m not sure I’ve adequately covered all necessary spending! My figures for childcare and utilities are the most uncertain; those could easily go up or down by quite a bit. But even if I exclude them completely, the reduced INE is still greater than income in most years.

Suddenly the way people feel about the economy makes a lot more sense to me.

On land acknowledgments

PNRJ ethics, inequality, tribal paradigm , , , , , , , , , , , , , ,

Dec 29 JDN 2460674

Noah Smith and Brad DeLong, both of whom I admire, have recently written about the practice of land acknowledgments. Smith is wholeheartedly against them. DeLong has a more nuanced view. Smith in fact goes so far as to argue that there is no moral basis for considering these lands to be ‘Native lands’ at all, which DeLong rightly takes issue with.

I feel like this might be an issue where it would be better to focus on Native American perspectives. (Not that White people aren’t allowed to talk about it; just that we tend to hear from them on everything, and this is something where maybe they’re less likely to know what they’re talking about.)

It turns out that Native views on land acknowledgments are also quite mixed; some see them as a pointless, empty gesture; others see them as a stepping-stone to more serious policy changes that are necessary. There is general agreement that more concrete actions, such as upholding treaties and maintaining tribal sovereignty, are more important.

I have to admit I’m much more in the ’empty gesture’ camp. I’m only one-fourth Native (so I’m Whiter than I am not), but my own view on this is that land acknowledgments aren’t really accomplishing very much, and in fact aren’t even particularly morally defensible.

Now, I know that it’s not realistic to actually “give back” all the land in the United States (or Australia, or anywhere where indigenous people were forced out by colonialism). Many of the tribes that originally lived on the land are gone, scattered to the winds, or now living somewhere else that they were forced to (predominantly Oklahoma). Moreover, there are now more non-Native people living on that land than there ever were Native people living on it, and forcing them all out would be just as violent and horrific as forcing out the Native people was in the first place.

I even appreciate Smith’s point that there is something problematic about assigning ownership of land to bloodlines of people just because they happened to be the first ones living there. Indeed, as he correctly points out, they often weren’t the first ones living there; different tribes have been feuding and warring with each other since time immemorial, and it’s likely that any given plot of land was held by multiple different tribes at different times even before colonization.

Let’s make this a little more concrete.

Consider the Beaver Wars.


The Beaver Wars were a series of conflicts between the Haudenosaunee (that’s what they call themselves; to a non-Native audience they are better known by what the French called them, Iroquois) and several other tribes. Now, that was after colonization, and the French were involved, and part of what they were fighting over was the European fur trade—so the story is a bit complicated by that. But it’s a conflict we have good historical records of, and it’s pretty clear that many of these rivalries long pre-dated the arrival of the French.

The Haudenosaunee were brutal in the Beaver Wars. They slaughtered thousands, including many helpless civilians, and effectively wiped out several entire tribes, including the Erie and Susquehannock, and devastated several others, including the Mohicans and the Wyandot. Many historians consider these to be acts of genocide. Surely any land that the Haundenosaunee claimed as a result of the Beaver Wars is as illegitimate as land claimed by colonial imperialism? Indeed, isn’t it colonial imperialism?

Yet we have no reason to believe that these brutal wars were unique to the Haundenosaunee, or that they only occurred after colonization. Our historical records aren’t as clear going that far back, because many Native tribes didn’t keep written records—in fact, many didn’t even have a written language. But what we do know suggests that a great many tribes warred with a great many other tribes, and land was gained and lost in warfare, going back thousands of years.

Indeed, it seems to be a sad fact of human history that virtually all land, indigenous or colonized, is actually owned by a group that conquered another group (that conquered another group, that conquered another group…). European colonialism was simply the most recent conquest.

But this doesn’t make European colonialism any more justifiable. Rather, it raises a deeper question:

How should we decide who owns what land?

The simplest way, and the way that we actually seem to use most of the time, is to simply take whoever currently owns the land as its legitimate ownership. “Possession is nine-tenths of the law” was always nonsense when it comes to private property (that’s literally what larceny means!), but when it comes to national sovereignty, it is basically correct. Once a group manages to organize itself well enough to enforce control over a territory, we pretty much say that it’s their territory now and they’re allowed to keep it.

Does that mean that anyone is just allowed to take whatever land they can successfully conquer and defend? That the world must simply accept that chaos and warfare are inevitable? Fortunately, there is a solution to this problem.

The Westphalian solution.

The current solution to this problem is what’s called Westphalian sovereignty, after the Peace of Westphalia, two closely-related treaties that were signed in Westphalia (a region of Germany) in 1648. Those treaties established a precedent in international law that nations are entitled to sovereignty over their own territory; other nations are not allowed to invade and conquer them, and if anyone tries, the whole international community should fight to resist any such attempt.

Effectively, what Westphalia did was establish that whoever controlled a given territory right now (where “right now” means 1648) now gets the right to hold it forever—and everyone else not only has to accept that, they are expected to defend it. Now, clearly this has not been followed precisely; new nations have gained independence from their empires (like the United States), nations have separated into pieces (like India and Pakistan, the Balkans, and most recently South Sudan), and sometimes even nations have successfully conquered each other and retained control—but the latter has been considerably rarer than it was before the establishment of Westphalian sovereignty. (Indeed, part of what makes the Ukraine War such an aberration is that it is a brazen violation of Westphalian sovereignty the likes of which we haven’t seen since the Second World War.)

This was, as far as I can tell, a completely pragmatic solution, with absolutely no moral basis whatsoever. We knew in 1648, and we know today, that virtually every nation on Earth was founded in bloodshed, its land taken from others (who took it from others, who took it from others…). And it was timed in such a way that European colonialism became etched in stone—no European power was allowed to take over another European power’s colonies anymore, but they were all allowed to keep all the colonies they already had, and the people living in those colonies didn’t get any say in the matter.

Since then, most (but by no means all) of those colonies have revolted and gained their own independence. But by the time it happened, there were large populations of former colonists, and the indigenous populations were often driven out, dramatically reduced, or even outright exterminated. There is something unsettling about founding a new democracy like the United States or Australia after centuries of injustice and oppression have allowed a White population to establish a majority over the indigenous population; had indigenous people been democratically represented all along, things would probably have gone a lot differently.

What do land acknowledgments accomplish?

I think that the intent behind land acknowledgments is to recognize and commemorate this history of injustice, in the hopes of somehow gaining some kind of at least partial restitution. The intentions here are good, and the injustices are real.

But there is something fundamentally wrong with the way most land acknowledgments are done, because they basically just push the sovereignty back one step: They assert that whoever held the land before Europeans came along is the land’s legitimate owner. But what about the people before them (and the people before them, and the people before them)? How far back in the chain of violence are we supposed to go before we declare a given group’s conquests legitimate?

How far back can we go?

Most of these events happened many centuries ago and were never written down, and all we have now is vague oral histories that may or may not even be accurate. Particularly when one tribe forces out another, it rather behooves the conquering tribe to tell the story in their own favor, as one of “reclaiming” land that was rightfully theirs all along, whether or not that was actually true—as they say, history is written by the victors. (I think it’s actually more true when the history is never actually written.) And in some cases it’s probably even true! In others, that land may have been contested between the two tribes for so long that nobody honestly knows who owned it first.

It feels wrong to legitimate the conquests of colonial imperialism, but it feels just as wrong to simply push it back one step—or three steps, or seven steps.

I think that ultimately what we must do is acknowledge this entire history.

We must acknowledge that this land was stolen by force from Native Americans, and also that most of those Native Americans acquired their land by stealing it by force from other Native Americans, and the chain goes back farther than we have records. We must acknowledge that this is by no means unique to the United States but in fact a universal feature of almost all land held by anyone anywhere in the world. We must acknowledge that this chain of violence and conquest has been a part of human existence since time immemorial—and affirm our commitment to end it, once and for all.

That doesn’t simply mean accepting the current allocation of land; land, like many other resources, is clearly distributed unequally and unfairly. But it does mean that however we choose to allocate land, we must do so by a fair and peaceful process, not by force and conquest. The chain of violence that has driven human history for thousands of years must finally be brought to an end.

More on Free Will

PNRJ cognitive science, core principles, ethics, inequality, Logic of Kindness, public policy , , , , , , , , ,


Oct 27 JDN 2460611

In a previous post, I defended the existence of compatibilism and free will. There are a few subtler issues with free will that I’d now like to deal with in this week’s post.

The ability to do otherwise

One subtler problem for free will comes from the idea of doing otherwise—what some philosophers call “genuinely open alternatives”. The question is simple to ask, but surprisingly difficult to answer: “When I make a choice, could I have chosen otherwise?”

On one hand, the answer seems obviously “yes” because, when I make a choice, I consider a set of alternatives and select the one that seems best. If I’d wanted to, I’d have chosen something else. On the other hand, the answer seems obviously “no”, because the laws of nature compelled my body and brain to move in exactly the way that it did. So which answer is right?

I think the key lies in understanding specifically how the laws of nature cause my behavior. It’s not as if my arms are on puppet strings, and no matter what I do, they will be moved in a particular way; if I choose to do something, I will do it; if I choose not to, I won’t do it. The laws of nature constrain my behavior by constraining my desires; they don’t constrain what I do in spite of what I want—instead, they constrain what I do through what I want. I am still free to do what I choose to do.

So, while my actions may be predetermined, they are determined by who I am, what I want, what experiences I have. These are precisely the right kind of determinants for free will to make sense; my actions spring not from random chance or external forces, but instead from my own character.

If we really mean to ask, “Could I (exactly as I was, in the situation I was in) have done otherwise (as free choice, not random chance)?” the answer is “No”. Something would have to be different. But one of the things that could be different is me! If I’d had different genes, or a different upbringing, or exposure to different ideas during my life, I might have acted differently. Most importantly, if I had wanted a different outcome, I could have chosen it. So if all we mean by the question is “Could I (if I wanted to) have done otherwise?” the answer is a resounding “Yes”. What I have done in my life speaks to my character—who I am, what I want. It doesn’t merely involve luck (though it may involve some luck), and it isn’t reducible to factors external to me. I am part of the causal structure of the universe; my will is a force. Though the world is made of pushes and pulls, I am among the things pushing and pulling.

As Daniel Dennett pointed out, this kind of freedom admits of degrees: It is entirely possible for a deterministic agent to be more or less effective at altering its circumstances to suit its goals. In fact, we have more options today than we did a few short centuries ago, and this means that in a very real sense we have more free will.

Empirically observing free will

What is really at stake, when we ask whether a person has free will? It seems to me that the question we really want to answer is this: “Are we morally justified in rewarding or punishing this person?” If you were to conclude, “No, they do not have free will, but we are justified in punishing them.”, I would think that you meant something different than I do by “free will”. If instead your ruling was “Yes, they have free will, but we may not reward or punish them.”, I would be similarly confused. Moreover, the concern that without free will, our moral and legal discourse collapses, seems to be founded upon this general notion—that reward and punishment, crucial to ethics and law (not to mention economics!) as they are, are dependent upon free will.

Yet, consider this as a scientific question. What kind of organism can respond to reward and punishment? What sort of thing will change its behavior based upon rewards, punishments, and the prospect thereof? Certainly you must agree that there is no point punishing a thing that will not be affected by the punishment in any way—banging your fist on the rocks will not make the rocks less likely to crush your loved ones. Conversely, I think you’d be hard-pressed to say it’s pointless to punish if the punishment would result in some useful effect. Maybe it’s not morally relevant—but then, why not? If you can make the world better by some action, doesn’t that, other things equal, give you a moral reason to perform that action?

We know exactly what sort of thing responds to reward and punishment: Animals. Specifically, animals that are operant-conditionable, for operant conditioning consists precisely in the orchestrated use of reward and punishment. Humans are of course supremely operant-conditionable; indeed, we can be trained to do incredibly complex things—like play a piano, pilot a space shuttle, hit a fastball, or write a book—and, even more impressively, we can learn to train ourselves to do such things. In fact, clearly something more than operant conditioning is at work here, because certain human behaviors (like language) are far too complex to learn by simple reward and punishment. There is a lot of innate cognition going on in the human brain—but over that layer of innate cognition we can add a virtually endless range of possible learned behaviors.

That is to say, learning—the capacity to change future behavior based upon past experience—is precisely in alignment with our common intuitions about free will—that humans have the most, animals have somewhat less, computers might have some, and rocks have none. Yes, there are staunch anthropocentrist dualists who would insist that animals and computers have no “free will”. But if you ask someone, “Did that dog dig that hole on purpose?” their immediate response will not include such theological considerations; it will attribute free choice to Canis lupus familiaris. Indeed, I think if you ask, “Did the chess program make that move on purpose?” the natural answer attributes some sort of will even to the machine. (Maybe just its programmer? I’m not so sure.)

Yet, if the capacity to respond to reward and punishment is all we need to justify reward and punishment, then the problem of free will collapses. We should punish criminals if, and only if, punishing them will reform them to better behavior, or set an example to deter others from similar crimes. Did we lose some deep sense of moral desert and retribution? Maybe, but I think we can probably work it back in, and if we can’t, we can probably do without it. Either way, we can still have a justice system and moral discourse.

Indeed, we can do better than that; we can now determine empirically whether a given entity is a moral agent. The insane psychopathic serial killer who utterly fails to understand empathy may indeed fail to qualify, in which case we should kill them and be done with it, the same way we would kill a virus or destroy an oncoming asteroid. Or they may turn out to qualify, in which case we should punish them as we would other moral agents. The point is, this is a decidable question, at least in principle; all we need are a few behavioral and psychological experiments to determine the answer.

The power of circumstances

There is another problem with classical accounts of free will, which comes from the results of psychology experiments. Perhaps the most seminal was the (in)famous experiment by Stanley Milgram, in which verbal commands caused ordinary people to administer what they thought were agonizing and life-threatening shocks to innocent people for no good reason. Simply by being put in particular circumstances, people found themselves compelled to engage in actions they would never have done otherwise. This experiment was replicated in 2009 under more rigorous controls, with virtually identical results.

This shows that free will is much more complicated than we previously imagined. Even if we acknowledge that human beings are capable of making rational, volitional decisions that reflect their character, we must be careful not to presume that everything people do is based upon character. As Hannah Arendt has pointed out, even the Nazis, though they perpetrated almost unimaginable evils, nonetheless were for the most part biologically and psychologically normal human beings. Perhaps Hitler and Himmler were maniacal psychopaths (and more recently Arendt’s specific example of Eichmann has also been challenged.), but the vast majority of foot soldiers of the German Army who burned villages or gassed children were completely ordinary men in extraordinarily terrible circumstances. This forces us to reflect upon the dire fact that in their place, most of us would have done exactly the same things.

This doesn’t undermine free will entirely, but it does force us to reconsider many of our preconceptions about it. Court systems around the world are based around the presumption that criminal acts are committed by people who are defective in character, making them deserving of punishment; in some cases this is probably right (e.g. Jeffrey Dahmer, Charles Manson), but in many cases, it is clearly wrong. Crime is much more prevalent in impoverished areas; why? Not because poor people are inherently more criminal, but because poverty itself makes people more likely to commit crimes. In a longitudinal study in Georgia, socioeconomic factors strongly predicted crime, especially property crime. An experiment at MIT suggests that letting people move to wealthier neighborhoods actually makes their children less likely to commit crimes. A 2007 report from the Government Accountability Office explicitly endorsed the hypothesis that poverty causes crime.

Really, all of this makes perfect sense: Poor people are precisely those who have the least to lose and the most to gain by breaking the rules. If you are starving, theft may literally save your life. Even if you’re not at the verge of starvation, the poorer you are, the worse your life prospects are, and the more unfairly the system has treated you. Most people who are rich today inherited much of their wealth from ancestors who violently stole it from other people. Why should anyone respect the rules of a system that robbed their ancestors and leaves them forsaken? Compound this with the fact that it is harder to be law-abiding when you are surrounded by thieves, and the high crime rates of inner cities hardly seem surprising.

Does this mean we should abandon criminal justice? Clearly not, for the consequences of doing so would be predictably horrendous. Temporary collapses in civil government typically lead to violent anarchy; this continued for several years in Somalia, and has happened more briefly even in Louisiana (it was not as terrible as the media initially reported, but it was still quite bad.) We do need to hold people responsible for their crimes. But what this sort of research shows is that we also need to consider situational factors when we set policy. The United States has the highest after-tax absolute poverty rate and the highest share of income claimed by the top 0.01\% of any First World nation—an astonishing 4%, meaning that the top 30,000 richest Americans have on average 400 times as much income as the average person. (My master’s thesis was actually on the subject of how this high level of inequality is related to increased corruption.) We also have the third-highest rate of murder in the OECD, after Mexico (by far the highest) and Estonia. Our homicide rate is almost three times that of Canada and over four times that of England. Even worse, the US has the highest incarceration rate in the world. Yes, that’s right; we in the US imprison a larger portion of our population than any other nation on Earth—including Iran, China, and Saudi Arabia.

Social science suggests this is no coincidence; it is our economic inequality that leads to our crime and incarceration. Nor is our poverty a result of insufficient wealth. By the standard measure Gross Domestic Product (GDP), an estimate of the total economic output a nation produces each year, the United States has the second-highest total GDP at purchasing power parity (China recently surpassed us), and the sixth-highest GDP per person in the world. We do not lack wealth; instead, we funnel wealth to the rich and deny it from the poor. If we stopped doing this, we would see a reduction in poverty and inequality, and there is reason to think that a corresponding reduction in crime would follow. We could make people act morally better simply by redistributing wealth.

Such knowledge of situational factors forces us to reconsider our ethical judgments on many subjects. It forces us to examine the ways that social, political, and economic systems influence our behavior in powerful ways. But we still have free will, and we still need to use it; in fact, in order to apply this research to our daily lives and public policies, we will need to exercise our free will very carefully.

Why is America so bad at public transit?

PNRJ development economics, inequality, politics, public policy , , , , , , , , , , , , , , , , ,

Sep 8 JDN 2460562

In most of Europe, 20-30% of the population commutes daily by public transit. In the US, only 13% do.

Even countries much poorer than the US have more widespread use of public transit; Kenya, Russia, and Venezuela all have very high rates of public transit use.

Cities around the world are rapidly expanding and improving their subway systems; but we are not here in the US.

Germany, France, Spain, Italy, and Japan are all building huge high-speed rail networks. We have essentially none.

Even Canada has better public transit than we do, and their population is just as spread out as ours.

Why are we so bad at this?

Surprisingly, it isn’t really that we are lacking in rail network. We actually have more kilometers of rail than China or the EU—though shockingly little of it is electrified, and we had nearly twice as many kilometers of rail a century ago. But we use this rail network almost entirely for freight, not passengers.

Is it that we aren’t spending enough government funds? Sort of. But it’s worth noting that we cover a higher proportion of public transit costs with government funds than most other countries. How can this be? It’s because transit systems get more efficient as they get larger, and attract more passengers as they provide better service. So when you provide really bad service, you end up spending more per passenger, and you need more government subsidies to stay afloat.

Cost is definitely part of it: It costs between two and seven times as much to build the same amount of light rail network in the US as it does in most EU countries. But that just raises another question: Why is it so much more expensive here?

This isn’t comparing with China—of course China is cheaper; they have a dictatorship, they abuse their workers, they pay peanuts. None of that is true of France or Germany, democracies where wages are just as high and worker protections are actually a good deal stronger than here. Yet it still costs two to seven times as much to build the same amount of rail in the US as it does in France or Germany.

Another part of the problem seems to be that public transit in the US is viewed as a social welfare program, rather than an infrastructure program: Rather than seeing it as a vital function of government that supports a strong economy, we see it as a last resort for people too poor to buy cars. And then it becomes politicized, because the right wing in the US hates social welfare programs and will do anything to make sure that they are cut down as much as possible.

It wasn’t always this way.

As recently as 1970, most US major cities had strong public transit systems. But now it’s really only the coastal cities that have them; cities throughout the South and Midwest have massively divested from their public transit. This goes along with a pattern of deindustrialization and suburbanization: These cities are stagnating economically and their citizens are moving out to the suburbs, so there’s no money for public transit and there’s more need for roads.

But the decline of US public transit goes back even further than that. Average transit trips per person in the US fell from 115 per year in 1950 to 36 per year in 1970.

This long, slow decline has only gotten worse as a result of the COVID pandemic; with more and more people working remotely, there’s just less need for commuting in general. (Then again, that also means fewer car miles, so it’s probably a good thing from an environmental perspective.)

Once public transit starts failing, it becomes a vicious cycle: They lose revenue, so they cut back on service, so they become more inconvenient, so they lose more revenue. Really successful public transit systems require very heavy investment in order to maintain fast, convenient service across an entire city. Any less than that, and people will just turn to cars instead.

Currently, the public transit systems in most US cities are suffering severe financial problems, largely as a result of the pandemic; they are facing massive shortfalls in their budgets. The federal government often helps with the capital costs of buying vehicles and laying down new lines, but not with the operating costs of actually running the system.

There seems to be some kind of systemic failure in the US in particular; something about our politics, or our economy, or our culture just makes us uniquely bad at building and maintaining public transit.

What should we do about this?

One option would be to do nothing—laissez faire. Maybe cars are just a more efficient mode of transportation, or better for what Americans want, and we should accept that.

But when you look at the externalities involved, it becomes clear that this is not the right approach. While cars produce enormous amounts of pollution and carbon emissions, public transit is much, much cleaner. (Electric cars are better than diesel buses, but still worse than trams and light rail—and besides, the vast majority of cars use gasoline.) Just for clean air and climate change alone, we have strong reasons to want fewer cars and more public transit.

And there are positive externalities of public transit too; it’s been estimated that for every $1 spent on public transit, a city gains $5 in economic activity. We’re leaving a lot of money on the table by failing to invest in something so productive.

We need a fundamental shift in how Americans think about public transit. Not as a last resort for the poor, but as a default option for everyone. Not as a left-wing social welfare program, but as a vital component of our nation’s infrastructure.

Whenever people get stuck in traffic, instead of resenting other drivers (who are in exactly the same boat!), they should resent that the government hasn’t supported more robust public transit systems—and then they should go out and vote for candidates and policies that will change that.

Of course, with everything else that’s wrong with our economy and our political system, I can understand why this might not be a priority right now. But sooner or later we are going to need to fix this, or it’s just going to keep getting worse and worse.

Housing should be cheap

PNRJ core principles, development economics, inequality, macroeconomics, market failure, public policy , , ,

Sep 1 JDN 2460555

We are of two minds about housing in our society. On the one hand, we recognize that shelter is a necessity, and we want it to be affordable for all. On the other hand, we see real estate as an asset, and we want it to appreciate in value and thereby provide a store of wealth. So on the one hand we want it to be cheap, but on the other hand we want it to be expensive. And of course it can’t be both.

This is not a uniquely American phenomenon. As Noah Smith points out, it seems to be how things are done in almost every country in the world. It may be foolish for me to try to turn such a tide. But I’m going to try anyway.

Housing should be cheap.

For some reason, inflation is seen as a bad thing for every other good, necessity and luxury alike; but when it comes to housing in particular—the single biggest expense for almost everyone—suddenly we are conflicted about it, and think that maybe inflation is a good thing actually.

This is because owning a home that appreciates in value provides the illusion of increasing wealth.

Yes, I said illusion. In some particular circumstances it can sometimes increase real wealth, but when housing is getting more expensive everywhere at once (which is basically true), it doesn’t actually increase real wealth—because you still need to have a home. So while you’d get more money if you sold your current home, you’d have to go buy another home that would be just as expensive. That extra wealth is largely imaginary.

In fact, what isn’t an illusion is your increased property tax bill. If you aren’t planning on selling your home any time soon, you should really see its appreciation as a bad thing; now you suddenly owe more in taxes.

Home equity lines of credit complicate this a bit; for some reason we let people collateralize part of the home—even though the whole home is already collateralized with a mortgage to someone else—and thereby turn that largely-imaginary wealth into actual liquid cash. This is just one more way that our financial system is broken; we shouldn’t be offering these lines of credit, just as we shouldn’t be creating mortgage-backed securities. Cleverness is not a virtue in finance; banking should be boring.

But you’re probably still not convinced. So I’d like you to consider a simple thought experiment, where we take either view to the extreme: Make housing 100 times cheaper or 100 times more expensive.

Currently, houses cost about $400,000. So in Cheap World, houses cost $4,000. In Expensive World, they cost $40 million.

In Cheap World, there is no homelessness. Seriously, zero. It would make no sense at all for the government not to simply buy everyone a house. If you want to also buy your own house—or a dozen—go ahead, that’s fine; but you get one for free, paid for by tax dollars, because that’s cheaper than a year of schooling for a high-school student; it’s in fact not much more than what we’d currently spend to house someone in a homeless shelter for a year. So given the choice of offering someone two years at a shelter versus never homeless ever again, it’s pretty obvious we should choose the latter. Thus, in Cheap World, we all have a roof over our heads. And instead of storing their wealth in their homes in Cheap World, people store their wealth in stocks and bonds, which have better returns anyway.

In Expensive World, the top 1% are multi-millionaires who own homes, maybe the top 10% can afford rent, and the remaining 89% of the population are homeless. There’s simply no way to allocate the wealth of our society such that a typical middle class household has $40 million. We’re just not that rich. We probably never will be that rich. It may not even be possible to make a society that rich. In Expensive World, most people live in tents on the streets, because housing has been priced out of reach for all but the richest families.

Cheap World sounds like an amazing place to live. Expensive World is a horrific dystopia. The only thing I changed was the price of housing.


Yes, I changed it a lot; but that was to make the example as clear as possible, and it’s not even as extreme as it probably sounds. At 10% annual growth, 100 times more expensive only takes 49 years. At the current growth rate of housing prices of about 5% per year, it would take 95 years. A century from now, if we don’t fix our housing market, we will live in Expensive World. (Yes, we’ll most likely be richer then too; but will we be that much richer? Median income has not been rising nearly as fast as median housing price. If current trends continue, median income will be 5 times bigger and housing prices will be 100 times bigger—that’s still terrible.)

We’re already seeing something that feels a lot like Expensive World in some of our most expensive cities. San Francisco has ludicrously expensive housing and also a massive homelessness crisis—this is not a coincidence. Homelessness does still exist in more affordable cities, but clearly not at the same crisis level.

I think part of the problem is that people don’t really understand what wealth is. They see the number go up, and they think that means there is more wealth. Real wealth consists in goods, not in prices. The wealth we have is made of real things, not monetary prices. Prices merely decide how wealth is allocated.

A home is wealth, yes. But it’s the same amount of real wealth regardless of what price it has, because what matters is what it’s good for. If you become genuinely richer by selling an appreciated home, you gained that extra wealth from somewhere else; it was not contained within your home. You have appropriated wealth that someone else used to have. You haven’t created wealth; you’ve merely obtained it.

For you as an individual, that may not make a difference; you still get richer. But as a society, it makes all the difference: Moving wealth around doesn’t make our society richer, and all higher prices can do is move wealth around.

This means that rising housing prices simply cannot make our whole society richer. Better houses could do that. More houses could do that. But simply raising the price tag isn’t making our society richer. If it makes anyone richer—which, again, typically it does not—it does so by moving wealth from somewhere else. And since homeowners are generally richer than non-homeowners (even aside from their housing wealth!), more expensive homes means moving wealth from poorer people to richer people—increased inequality.

We used to have affordable housing, just a couple of generations ago. But we may never have truly affordable housing again, because people really don’t like to see that number go down, and they vote for policies accordingly—especially at the local level. Our best hope right now seems to be to keep it from going up faster than the growth rate of income, so that homes don’t become any more unaffordable than they already are.

But frankly I’m not optimistic. I think part of the cyberpunk dystopia we’re careening towards is Expensive World.