Conflict without shared reality

Aug 17 JDN 2460905

Donald Trump has federalized the police in Washington D.C. and deployed the National Guard. He claims he is doing this in response to a public safety emergency and crime that is “out of control”.

Crime rates in Washington, D.C. are declining and overall at their lowest level in 30 years. Its violent crime rate has not been this low since the 1960s.

By any objective standard, there is no emergency here. Crime in D.C. is not by any means out of control.

Indeed, across the United States, homicide rates are as low as they have been in 60 years.

But we do not live in a world where politics is based on objective truth.

We live in a world where the public perception of reality itself is shaped by the political narrative.

One of the first things that authoritarians do to control these narratives is try to make their followers distrust objective sources. I watch in disgust as not simply the Babylon Bee (which is a right-wing satire site that tries really hard to be funny but never quite manages it) but even the Atlantic (a mainstream news outlet generally considered credible) feeds—in multiple articles—into this dangerous lie that crime is increasing and the official statistics are somehow misleading us about that.

Of course the Atlantic‘s take is much more nuanced; but quite frankly, now is not the time for nuance. A fascist is trying to take over our government, and he needs to be resisted at every turn by every means possible. You need to be calling him out on every single lie he makes—yes, every single one, I know there are a lot of them, and that’s kind of the point—rather than trying to find alternative framings on which maybe part of what he said could somehow be construed as reasonable from a certain point of view. Every time you make Trump sound more reasonable than he is—and mainstream news outlets have done this literally hundreds of times—you are pushing America closer to fascism.

I really don’t know what to do here.

It is impossible to resolve conflicts when they are not based on shared reality.

No policy can solve a crime wave that doesn’t exist. No trade agreement can stop unfair trading practices that aren’t happening. Nothing can stop vaccines from causing autism that they already don’t cause. There is no way to fix problems when those problems are completely imaginary.

I used to think that political conflict was about different values which had to be balanced against one another: Liberty versus security, efficiency versus equality, justice versus mercy. I thought that we all agreed on the basic facts and even most of the values, and were just disagreeing about how to weigh certain values over others.

Maybe I was simply naive; maybe it’s never been like that. But it certainly isn’t right now. We aren’t disagreeing about what should be done; we are disagreeing about what is happening in front of our eyes. We don’t simply have different priorities or even different values; it’s like we are living in different worlds.

I have read, e.g. by Jonathan Haidt, that conservatives largely understand what liberals want, but liberals don’t really understand what conservatives want. (I would like to take one of the tests they use in these experiments, see how I actually do; but I’ve never been able to find one.)

Haidt’s particular argument seems to be that liberals don’t “understand” the “moral dimensions” of loyalty, authority, and sanctity, because we only “understand” harm and fairness as the basis of morality. But just because someone says something is morally relevant, that doesn’t mean it is morally relevant! And indeed, based on more or less the entirety of ethical philosophy, I can say that harm and fairness are morality, and the others simply aren’t. They are distortions of morality, they are inherently evil, and we are right to oppose them at every turn. Loyalty, authority, and sanctity are what fed Nazi Germany and the Spanish Inquisition.

This claim that liberals don’t understand conservatives has always seemed very odd to me: I feel like I have a pretty clear idea what conservatives want, it’s just that what they want is terrible: Kick out the immigrants, take money from the poor and give it to the rich, and put rich straight Christian White men back in charge of everything. (I mean, really, if that’s not what they want, why do they keep voting for people who do it? Revealed preferences, people!)

Or, more sympathetically: They want to go back to a nostalgia-tinted vision of the 1950s and 1960s in which it felt like things were going well for our country—because they were blissfully ignorant of all the violence and injustice in the world. No, thank you, Black people and queer people do not want to go back to how we were treated in the 1950s—when segregation was legal and Alan Turing was chemically castrated. (And they also don’t seem to grasp that among the things that did make some things go relatively well in that period were unions, antitrust law and progressive taxes, which conservatives now fight against at every turn.)

But I think maybe part of what’s actually happening here is that a lot of conservatives actually “want” things that literally don’t make sense, because they rest upon assumptions about the world that simply aren’t true.

They want to end “out of control” crime that is the lowest it’s been in decades.

They want to stop schools from teaching things that they already aren’t teaching.

They want the immigrants to stop bringing drugs and crime that they aren’t bringing.

They want LGBT people to stop converting their children, which we already don’t and couldn’t. (And then they want to do their own conversions in the other direction—which also don’t work, but cause tremendous harm.)

They want liberal professors to stop indoctrinating their students in ways we already aren’t and can’t. (If we could indoctrinate our students, don’t you think we’d at least make them read the syllabus?)

They want to cut government spending by eliminating “waste” and “fraud” that are trivial amounts, without cutting the things that are actually expensive, like Social Security, Medicare, and the military. They think we can balance the budget without cutting these things or raising taxes—which is just literally mathematically impossible.

They want to close off trade to bring back jobs that were sent offshore—but those jobs weren’t sent offshore, they were replaced by robots. (US manufacturing output is near its highest ever, even though manufacturing employment is half what it once was.)


And meanwhile, there’s a bunch of real problems that aren’t getting addressed: Soaring inequality, a dysfunctional healthcare system, climate change, the economic upheaval of AI—and they either don’t care about those, aren’t paying attention to them, or don’t even believe they exist.

It feels a bit like this:

You walk into a room and someone points a gun at you, shouting “Drop the weapon!” but you’re not carrying a weapon. And you show your hands, and try to explain that you don’t have a weapon, but they just keep shouting “Drop the weapon!” over and over again. Someone else has already convinced them that you have a weapon, and they expect you to drop that weapon, and nothing you say can change their mind about this.

What exactly should you do in that situation?

How do you avoid getting shot?

Do you drop something else and say it’s the weapon (make some kind of minor concession that looks vaguely like what they asked for)? Do you try to convince them that you have a right to the weapon (accept their false premise but try to negotiate around it)? Do you just run away (leave the country?)? Do you double down and try even harder to convince them that you really, truly, have no weapon?

I’m not saying that everyone on the left has a completely accurate picture of reality; there are clearly a lot of misconceptions on this side of the aisle as well. But at least among the mainstream center left, there seems to be a respect for objective statistics and a generally accurate perception of how the world works—the “reality-based community”. Sometimes liberals make mistakes, have bad ideas, or even tell lies; but I don’t hear a lot of liberals trying to fix problems that don’t exist or asking for the government budget to be changed in ways that violate basic arithmetic.

I really don’t know what do here, though.

How do you change people’s minds when they won’t even agree on the basic facts?

An interview with Claude

Apr 13 JDN 2460786

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Several factors make this concern particularly relevant:

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

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

Policy and regulatory approaches:

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

Technical and institutional innovations:

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

Educational and capacity-building efforts:

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

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

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

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

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

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

This creates several challenging tradeoffs:

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

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

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

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

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

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

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

At the highest restriction tier, we might place:

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

In a middle tier with significant but not maximum restrictions:

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

For lower restriction tiers:

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

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

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

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

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

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

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

Several factors make this prediction challenging:

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

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

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

Does that perspective address what you were curious about?

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

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

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

This transition will create several interconnected effects:

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

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

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

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

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

Jobs largely unaffected by AI:

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

Jobs significantly transformed by AI:

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

Jobs at high risk of replacement:

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

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

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

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

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

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

On the positive side, AI has introduced some efficiencies:

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

However, several concerning dynamics have emerged:

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

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

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

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

For a college student deciding what to study:

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

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

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

For a job seeker looking for employment right now:

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

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

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

For someone with an established career facing AI disruption:

Take a proactive approach to evolution rather than resistance:

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

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

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

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

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

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

How to detect discrimination, empirically

Aug 25 JDN 2460548

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

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

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

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

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

1. Baseline

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

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

MenWomen
11
22
33
44
55

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

Hired MenHired Women
33
44
55

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

2. Innate Differences

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


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

MenWomen
11
21
32
43
54

Then, this is the group that will get hired:

Hired MenHired Women
33
44
5

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

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

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

3. Discrimination

What does it look like when there is discrimination?

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

So if the population looks like this:

MenWomen
11
22
33
44
55

The hired employees will look like this:

Hired MenHired Women
3
44
55

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

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

Yes, we see it all the time.

Corporations with women CEOs are more profitable.

Women doctors have better patient outcomes.

Startups led by women are more likely to succeed.

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

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

4. Both

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

MenWomen
11
21
32
43
54

And the hired employees might look like this:

Hired MenHired Women
3
4
54

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

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

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

What does affirmative action do?

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

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

What if we can’t measure competence?

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

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

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

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

Hyper-competition

Dec13 JDN 2459197

This phenomenon has been particularly salient for me the last few months, but I think it’s a common experience for most people in my generation: Getting a job takes an awful lot of work.

Over the past six months, I’ve applied to over 70 different positions and so far gone through 4 interviews (2 by video, 2 by phone). I’ve done about 10 hours of test work. That so far has gotten me no offers, though I have yet to hear from 50 employers. Ahead of me I probably have about another 10 interviews, then perhaps 4 of what would have been flyouts and in-person presentations but instead will be “comprehensive interviews” and presentations conducted online, likely several more hours of test work, and then finally, maybe, if I’m lucky, I’ll get a good offer or two. If I’m unlucky, I won’t, and I’ll have to stick around for another year and do all this over again next year.

Aside from the limitations imposed by the pandemic, this is basically standard practice for PhD graduates. And this is only the most extreme end of a continuum of intensive job search efforts, for which even applying to be a cashier at Target requires a formal application, references, and a personality test.

This wasn’t how things used to be. Just a couple of generations ago, low-wage employers would more or less hire you on the spot, with perhaps a resume or a cursory interview. More prestigious employers would almost always require a CV with references and an interview, but it more or less stopped there. I discussed in an earlier post how much of the difference actually seems to come from our chronic labor surplus.

Is all of this extra effort worthwhile? Are we actually fitting people to better jobs this way? Even if the matches are better, are they enough better to justify all this effort?

It is a commonly-held notion among economists that competition in markets is good, that it increases efficiency and improves outcomes. I think that this is often, perhaps usually, the case. But the labor market has become so intensely competitive, particularly for high-paying positions, that the costs of this competitive effort likely outweigh the benefits.

How could this happen? Shouldn’t the free market correct for such an imbalance? Not necessarily. Here is a simple formal model of how this sort of intensive competition can result in significant waste.

Note that this post is about a formal mathematical model, so it’s going to use a lot of algebra. If you are uninterested in such things, you can read the next two paragraphs and then skip to the conclusions at the end.

The overall argument is straightforward: If candidates are similar in skill level, a complicated application process can make sense from a firm’s perspective, but be harmful from society’s perspective, due to the great cost to the applicants. This can happen because the difficult application process imposes an externality on the workers who don’t get the job.

All right, here is where the algebra begins.

I’ve included each equation as both formatted text and LaTeX.

Consider a competition between two applicants, X and Z.

They are each asked to complete a series of tasks in an application process. The amount of effort X puts into the application is x, and the amount of effort Z puts into the application is z. Let’s say each additional bit of effort has a fixed cost, normalized to 1.

Let’s say that their skills are similar, but not identical; this seems quite realistic. X has skill level hx, and Z has skill level hz.

Getting hired has a payoff for each worker of V. This includes all the expected benefits of the salary, benefits, and working conditions. I’ll assume that these are essentially the same for both workers, which also seems realistic.

The benefit to the employer is proportional to the worker’s skill, so letting h be the skill level of the actually hired worker, the benefit of hiring that worker is hY. The reason they are requiring this application process is precisely because they want to get the worker with the highest h. Let’s say that this application process has a cost to implement, c.

Who will get hired? Well, presumably whoever does better on the application. The skill level will amplify the quality of their output, let’s say proportionally to the effort they put in; so X’s expected quality will be hxx and Z’s expected output will be hzz.

Let’s also say there’s a certain amount of error in the process; maybe the more-qualified candidate will sleep badly the day of the interview, or make a glaring and embarrassing typo on their CV. And quite likely the quality of application output isn’t perfectly correlated with the quality of actual output once hired. To capture all this, let’s say that having more skill and putting in more effort only increases your probability of getting the job, rather than actually guaranteeing it.

In particular, let’s say that the probability of X getting hired is P[X] = hxx/(hxx + hzz).

\[ P[X] = \frac{h_x}{h_x x + h_z z} \]

This results in a contest function, a type of model that I’ve discussed in some earlier posts in a rather different context.


The expected payoff for worker X is:

E[Ux] = hxx/(hxx + hzz) V – x

\[ E[U_x] = \frac{h_x x}{h_x x + h_z z} V – x \]

Maximizing this with respect to the choice of effort x (which is all that X can control at this point) yields:

hxhzz V = (hxx + hzz)2

\[ h_x h_z x V = (h_x x + h_z z)^2 \]

A similar maximization for worker Z yields:

hxhzx V = (hxx + hzz)2

\[ h_x h_z z V = (h_x x + h_z z)^2 \]

It follows that x=z, i.e. X and Z will exert equal efforts in Nash equilibrium. Their probability of success will then be contingent entirely on their skill levels:

P[X] = hx/(hx + hz).

\[ P[X] = \frac{h_x}{h_x + h_y} \]

Substituting that back in, we can solve for the actual amount of effort:

hxhzx V = (hx + hz)2x2

\[h_x h_z x V = (h_x + h_z)^2 x^2 \]

x = hxhzV/(hx + hz)2

\[ x = \frac{h_x h_z}{h_x + h_z} V \]

Now let’s see what that gives for the expected payoffs of the firm and the workers. This is worker X’s expected payoff:

E[Ux] = hx/(hx + hz) V – hxhzV/(hx + hz)2 = (hx/(hx + hz))2 V

\[ E[U_x] = \frac{h_x}{h_x + h_z} V – \frac{h_x h_z}{(h_x + h_z)^2} V = \left( \frac{h_x}{h_x + h_z}\right)^2 V \]

Worker Z’s expected payoff is the same, with hx and hz exchanged:

E[Uz] = (hz/(hx + hz))2 V

\[ E[U_z] = \left( \frac{h_z}{h_x + h_z}\right)^2 V \]

What about the firm? Their expected payoff is the the probability of hiring X, times the value of hiring X, plus the probability of hiring Z, times the value of hiring Z, all minus the cost c:

E[Uf] = hx/(hx + hz) hx Y + hz/(hx + hz) hz Y – c= (hx2 + hz2)/(hx + hz) Y – c

\[ E[U_f] = \frac{h_x}{h_x + h_z} h_x Y + \frac{h_z}{h_x + h_z} h_z Y – c = \frac{h_x^2 + h_z^2}{h_x + h_z} Y – c\]

To see whether the application process was worthwhile, let’s compare against the alternative of simply flipping a coin and hiring X or Z at random. The probability of getting hired is then 1/2 for each candidate.

Expected payoffs for X and Z are now equal:

E[Ux] = E[Uz] = V/2

\[ E[U_x] = E[U_z] = \frac{V}{2} \]

The expected payoff for the firm can be computed the same as before, but now without the cost c:

E[Uf] = 1/2 hx Y + 1/2 hz Y = (hx + hz)/2 Y

\[ E[U_f] = \frac{1}{2} h_x Y + \frac{1}{2} h_z Y = \frac{h_x + h_z}{2} Y \]

This has a very simple interpretation: The expected value to the firm is just the average quality of the two workers, times the overall value of the job.

Which of these two outcomes is better? Well, that depends on the parameters, of course. But in particular, it depends on the difference between hx and hz.

Consider two extremes: In one case, the two workers are indistinguishable, and hx = hz = h. In that case, the payoffs for the hiring process reduce to the following:

E[Ux] = E[Uz] = V/4

\[ E[U_x] = E[U_z] = \frac{V}{4} \]

E[Uf] = h Y – c

\[ E[U_f] = h Y – c \]

Compare this against the payoffs for hiring randomly:

E[Ux] = E[Uz] = V/2

\[ E[U_x] = E[U_z] = \frac{V}{2} \]

E[Uf] = h Y

\[ E[U_f] = h Y \]

Both the workers and the firm are strictly better off if the firm just hires at random. This makes sense, since the workers have identical skill levels.

Now consider the other extreme, where one worker is far better than the other; in fact, one is nearly worthless, so hz ~ 0. (I can’t do exactly zero because I’d be dividing by zero, but let’s say one is 100 times better or something.)

In that case, the payoffs for the hiring process reduce to the following:

E[Ux] = V

E[Uz] = 0

\[ E[U_x] = V \]

\[ E[U_z] = 0 \]

X will definitely get the job, so X is much better off.

E[Uf] = hx Y – c

\[ E[U_f] = h_x Y – c \]

If the firm had hired randomly, this would have happened instead:

E[Ux] = E[Uz] = V/2

\[ E[U_x] = E[U_z] = \frac{V}{2} \]

E[Uf] = hY/2

\[ E[U_f] = \frac{h}{2} Y \]

As long as c < hY/2, both the firm and the higher-skill worker are better off in this scenario. (The lower-skill worker is worse off, but that’s not surprising.) The total expected benefit for everyone is also higher in this scenario.


Thus, the difference in skill level between the applicants is vital. If candidates are very different in skill level, in a way that the application process can accurately measure, then a long and costly application process can be beneficial, not only for the firm but also for society as a whole.

In these extreme examples, it was either not worth it for the firm, or worth it for everyone. But there is an intermediate case worth looking at, where the long and costly process can be worth it for the firm, but not for society as a whole. I will call this case hyper-competition—a system that is so competitive it makes society overall worse off.

This inefficient result occurs precisely when:
c < (hx2 + hz2)/(hx + hz) Y – (hx + hz)/2 Y < c + (hx/(hx + hz))2 V + (hz/(hx + hz))2 V

\[ c < \frac{h_x^2 + h_z^2}{h_x + h_z} Y – \frac{h_x + h_z}{2} Y < c + \left( \frac{h_x}{h_x + h_z}\right)^2 V + \left( \frac{h_z}{h_x + h_z}\right)^2 V \]

This simplifies to:

c < (hx – hz)2/(2hx + 2hz) Y < c + (hx2 + hz2)/(hx + hz)2 V

\[ c < \frac{(h_x – h_z)^2}{2 (h_x + h_z)} Y < c + \frac{(h_x^2 + h_z^2)}{(h_x+h_z)^2} V \]

If c is small, then we are interested in the case where:

(hx – hz)2 Y/2 < (hx2 + hz2)/(hx + hz) V

\[ \frac{(h_x – h_z)^2}{2} Y < \frac{h_x^2 + h_z^2}{h_x + h_z} V \]

This is true precisely when the difference hx – hz is small compared to the overall size of hx or hz—that is, precisely when candidates are highly skilled but similar. This is pretty clearly the typical case in the real world. If the candidates were obviously different, you wouldn’t need a competitive process.

For instance, suppose that hx = 10 and hz = 8, while V = 180, Y = 20 and c = 1.

Then, if we hire randomly, these are the expected payoffs:

E[Uf] = (hx + hz)/2 Y = 180

E[Ux] = E[Uz] = V/2 = 90

If we use the complicated hiring process, these are the expected payoffs:

E[Ux] = (hx/(hx + hz))2 V = 55.5

E[Uz] = (hz/(hx + hz))2 V = 35.5

E[Uf] = (hx2 + hz2)/(hx + hz) Y – c = 181

The firm gets a net benefit of 1, quite small; while the workers face a far larger total expected loss of 90. And these candidates aren’t that similar: One is 25% better than the other. Yet because the effort expended in applying was so large, even this improvement in quality wasn’t worth it from society’s perspective.

This conclude’s the algebra for today, if you’ve been skipping it.

In this model I’ve only considered the case of exactly two applicants, but this can be generalized to more applicants, and the effect only gets stronger: Seemingly-large differences in each worker’s skill level can be outweighed by the massive cost of making so many people work so hard to apply and get nothing to show for it.

Thus, hyper-competition can exist despite apparently large differences in skill. Indeed, it is precisely the typical real-world scenario with many applicants who are similar that we expect to see the greatest inefficiencies. In the absence of intervention, we should expect markets to get this wrong.

Of course, we don’t actually want employers to hire randomly, right? We want people who are actually qualified for their jobs. Yes, of course; but you can probably assess that with nothing more than a resume and maybe a short interview. Most employers are not actually trying to find qualified candidates; they are trying to sift through a long list of qualified candidates to find the one that they think is best qualified. And my suspicion is that most of them honestly don’t have good methods of determining that.

This means that it could be an improvement for society to simply ban long hiring processes like these—indeed, perhaps ban job interviews altogether, as I can hardly think of a more efficient mechanism for allowing employers to discriminate based on race, gender, age, or disability than a job interview. Just collect a resume from each applicant, remove the ones that are unqualified, and then roll a die to decide which one you hire.

This would probably make the fit of workers to their jobs somewhat worse than the current system. But most jobs are learned primarily through experience anyway, so once someone has been in a job for a few years it may not matter much who was hired originally. And whatever cost we might pay in less efficient job matches could be made up several times over by the much faster, cheaper, easier, and less stressful process of applying for jobs.

Indeed, think for a moment of how much worse it feels being turned down for a job after a lengthy and costly application process that is designed to assess your merit (but may or may not actually do so particularly well), as opposed to simply finding out that you lost a high-stakes die roll. Employers could even send out letters saying one of two things: “You were rejected as unqualifed for this position.” versus “You were qualified, but you did not have the highest die roll.” Applying for jobs already feels like a crapshoot; maybe it should literally be one.

People would still have to apply for a lot of jobs—actually, they’d probably end up applying for more, because the lower cost of applying would attract more applicants. But since the cost is so much lower, it would still almost certainly be easier to do a job search than it is in the current system. In fact, it could largely be automated: simply post your resume on a central server and the system matches you with employers’ requirements and then randomly generates offers. Employers and prospective employees could fill out a series of forms just once indicating what they were looking for, and then the system could do the rest.

What I find most interesting about this policy idea is that it is in an important sense anti-meritocratic. We are in fact reducing the rewards for high levels of skill—at least a little bit—in order to improve society overall and especially for those with less skill. This is exactly the kind of policy proposal that I had hoped to see from a book like The Meritocracy Trap, but never found there. Perhaps it’s too radical? But the book was all about how we need fundamental, radical change—and then its actual suggestions were simple, obvious, and almost uncontroversial.

Note that this simplified process would not eliminate the incentives to get major, verifiable qualifications like college degrees or years of work experience. In fact, it would focus the incentives so that only those things matter, instead of whatever idiosyncratic or even capricious preferences HR agents might have. There would be no more talk of “culture fit” or “feeling right for the job”, just: “What is their highest degree? How many years have they worked in this industry?” I suppose this is credentialism, but in a world of asymmetric information, I think credentialism may be our only viable alternative to nepotism.

Of course, it’s too late for me. But perhaps future generations may benefit from this wisdom.

What would a better job market look like?

Sep 13 JDN 2459106

I probably don’t need to tell you this, but getting a job is really hard. Indeed, much harder than it seems like it ought to be.

Having all but completed my PhD, I am now entering the job market. The job market for economists is quite different from the job market most people deal with, and these differences highlight some potential opportunities for improving job matching in our whole economy—which, since employment is such a large part of our lives, could have wide-ranging benefits for our society.

The most obvious difference is that the job market for economists is centralized: Job postings are made through the American Economic Association listing of Job Openings for Economists (often abbrievated AEA JOE); in a typical year about 4,000 jobs are posted there. All of them have approximately the same application deadline, near the end of the year. Then, after applying to various positions, applicants get interviewed in rapid succession, all at the annual AEA conference. Then there is a matching system, where applicants get to send two “signals” indicating their top choices and then offers are made.

This year of course is different, because of COVID-19. The conference has been canceled, with all of its presentations moved online; interviews will also be conducted online. Perhaps more worrying, the number of postings has been greatly reduced, and based on past trends may be less than half of the usual number. (The number of applicants may also be reduced, but it seems unlikely to drop as much as the number of postings does.)

There are a number of flaws in even this system. First, it’s too focused on academia; very few private-sector positions use the AEA JOE system, and almost no government positions do. So those of us who are not so sure we want to stay in academia forever end up needing to deal with both this system and the conventional system in parallel. Second, I don’t understand why they use this signaling system and not a deferred-acceptance matching algorithm. I should be able to indicate more about my preferences than simply what my top two choices are—particularly when most applicants apply to over 100 positions. Third, it isn’t quite standardized enough—some positions do have earlier deadlines or different application materials, so you can’t simply put together one application packet and send it to everyone at once.

Still, it’s quite obvious that this system is superior to the decentralized job market that most people deal with. Indeed, this becomes particularly obvious when one is participating in both markets at once, as I am. The decentralized market has a wide range of deadlines, where upon seeing an application you may need to submit to it within that week, or you may have several months to respond. Nearly all applications require a resume, but different institutions will expect different content on it. Different applications may require different materials: Cover letters, references, writing samples, and transcripts are all things that some firms will want and others won’t.

Also, this is just my impression from a relatively small sample, but I feel like the AEA JOE listings are more realistic, in the following sense: They don’t all demand huge amounts of prior experience, and those that do ask for prior experience are either high-level positions where that’s totally reasonable, or are willing to substitute education for experience. For private-sector job openings you basically have to subtract three years from whatever amount of experience they say they require, because otherwise you’d never have anywhere you could apply to. (Federal government jobs are a weird case here; they all say they require a lot of experience at a specific government pay grade, but from talking with those who have dealt with the system before, they are apparently willing to make lots of substitutions—private-sector jobs, education, and even hobbies can sometimes substitute.)

I think this may be because the decentralized market has to some extent unraveled. The job market is the epitome of a matching market; unraveling in a matching market occurs when there is fierce competition for a small number of good candidates or, conversely, a small number of good openings. Each firm has the incentive to make a binding offer earlier than the others, with a short deadline so that candidates don’t have time to shop around. As firms compete with each other, they start making deadlines earlier and earlier until candidates feel like they are in a complete crapshoot: An offer made on Monday might be gone by Friday, and you have no way of knowing if you should accept it now or wait for a better one to come along. This is a Tragedy of the Commons: Given what other firms are doing, each firm benefits from making an earlier binding offer. But once they all make early offers, that benefit disappears and the result just makes the whole system less efficient.

The centralization of the AEA JOE market prevents this from happening: Everyone has common deadlines and does their interviews at the same time. Each institution may be tempted to try to break out of the constraints of the centralized market, but they know that if they do, they will be punished by receiving fewer applicants.

The fact that the centralized market is more efficient is likely a large part of why economics PhDs have the lowest unemployment rate of any PhD graduates and nearly the lowest unemployment rate of any job sector whatsoever. In some sense we should expect this: If anyone understands how to make employment work, it should be economists. Noah Smith wrote in 2013 (and I suppose I took it to heart): “If you get a PhD, get an economics PhD.” I think PhD graduates are the right comparison group here: If we looked at the population as a whole, employment rates and salaries for economists look amazing, but that isn’t really fair since it’s so much harder to become an economist than it is to get most other jobs. But I don’t think it’s particularly easier to get a PhD in physics or biochemistry than to get one in economics, and yet economists still have a lower unemployment rate than physicists or biochemists. (Though it’s worth noting that any PhD—yes, even in the humanities—will give you a far lower risk of unemployment than the general population.) The fact that we have AEA JOE and they don’t may be a major factor here.


So, here’s my question: Why don’t we do this in more job markets? It would be straightforward enough to do this for all PhD graduates, at least—actually my understanding is that some other disciplines do have centralized markets similar to the one in economics, but I’m not sure how common this is.

The federal government could relatively easily centralize its own job market as well; maybe not for positions that need to be urgently filled, but anything that can wait several months would be worth putting into a centralized system that has deadlines once or twice a year.

But what about the private sector, which after all is where most people work? Could we centralize that system as well?

It’s worth noting the additional challenges that immediately arise: Many positions need to be filled immediately, and centralization would make that impossible. There are thousands of firms that would need to be coordinated (there are at least 100,000 firms in the US with 100 or more employees). There are millions of different jobs to be filled, requiring a variety of different skills. In an average month over 5 million jobs are filled in the United States.

Most people want a job near where they live, so part of the solution might be to centralize only jobs within a certain region, such as a particular metro area. But if we are limited to open positions of a particular type within a particular city, there might not be enough openings at any given time to be worth centralizing. And what about applicants who don’t care so much about geography? Should they be applying separately to each regional market?

Yet even with all this in mind, I think some degree of centralization would be feasible and worthwhile. If nothing else, I think standardizing deadlines and application materials could make a significant difference—it’s far easier to apply to many places if they all use the same application and accept them at the same time.

Another option would be to institute widespread active labor market policies, which are a big part of why #ScandinaviaIsBetter. Denmark especially invests heavily in such programs, which provide training and job matching for unemployed citizens. It is no coincidence that Denmark has kept their unemployment rate under 7% even through the worst of the Great Recession. The US unemployment rate fluctuates wildly with the business cycle, while most of Europe has steadier but higher unemployment. Indeed, the lowest unemployment rates in France over the last 30 years have exceeded the highest rates in Denmark over the same period. Denmark spends a lot on their active labor market programs, but I think they’re getting their money’s worth.

Such a change would make our labor markets more efficient, matching people to jobs that fit them better, increasing productivity and likely decreasing turnover. Wages probably wouldn’t change much, but working in a better job for the same wage is still a major improvement in your life. Indeed, job satisfaction is one of the strongest predictors of life satisfaction, which isn’t too surprising given how much of our lives we spend at work.

Will robots take our jobs? Not “if” but “when”.

Jan 5 JDN 2458853

The prospect of technological unemploymentin short, robots taking our jobs—is a very controversial one among economists.

For most of human history, technological advances have destroyed some jobs and created others, causing change, instability, conflict—but ultimately, not unemployment. Many economists believe that this trend will continue well into the 21st century.

Yet I am not so sure, ever since I read this chilling paragraph by Gregory Clark, which I first encountered in The Atlantic:

There was a type of employee at the beginning of the Industrial Revolution whose job and livelihood largely vanished in the early twentieth century. This was the horse. The population of working horses actually peaked in England long after the Industrial Revolution, in 1901, when 3.25 million were at work. Though they had been replaced by rail for long-distance haulage and by steam engines for driving machinery, they still plowed fields, hauled wagons and carriages short distances, pulled boats on the canals, toiled in the pits, and carried armies into battle. But the arrival of the internal combustion engine in the late nineteenth century rapidly displaced these workers, so that by 1924 there were fewer than two million. There was always a wage at which all these horses could have remained employed. But that wage was so low that it did not pay for their feed.

Based on the statistics, what actually seems to be happening right now is that automation is bifurcating the workforce: It’s allowing some people with advanced high-tech skills to make mind-boggling amounts of money in engineering and software development, while those who lack such skills get pushed ever further into the margins, forced to take whatever jobs they can get. This skill-biased technical change is far from a complete explanation for our rising inequality, but it’s clearly a contributing factor, and I expect it will become more important over time.

Indeed, in some sense I think the replacement of most human labor with robots is inevitable. It’s not a question of “if”, but only a question of “when”. In a thousand years—if we survive at all, and if we remain recognizable as human—we’re not going to have employment in the same sense we do today. In the best-case scenario, we’ll live in the Culture, all playing games, making art, singing songs, and writing stories while the robots do all the hard labor.

But a thousand years is a very long time; we’ll be dead, and so will our children and our grandchildren. Most of us are thus understandably a lot more concerned about what happens in say 20 or 50 years.

I’m quite certain that not all human work will be replaced within the next 20 years. In fact, I am skeptical even of the estimates that half of all work will be automated within the next 40 years, though some very qualified experts are making such estimates. A lot of jobs are safe for now.

Indeed, my job is probably pretty safe: While there has been a disturbing trend in universities toward adjunct faculty, people are definitely still going to need economists for the foreseeable future. (Indeed, if Asimov is right, behavioral economists will one day rule the galaxy.)

Creative jobs are also quite safe; it’s going to be at least a century, maybe more, before robots can seriously compete with artists, authors, or musicians. (Robot Beethoven is a publicity stunt, not a serious business plan.) Indeed, by the time robots reach that level, I think we’ll have to start treating them as people—so in that sense, people will still be doing those jobs.

Even construction work is also relatively safe—actually projected to grow faster than employment in general for the next decade. This is probably because increased construction productivity tends to lead to more construction, rather than less employment. We can pretty much always use more or bigger houses, as long as we can afford them. Really, we should be hoping for technological advances in construction, which might finally bring down our astronomical housing prices, especially here in California.

But a lot of jobs are clearly going to disappear, sooner than most people seem to grasp.

The one that worries me the most is truck drivers. Truck drivers are a huge number of people. Trucking employs over 1.5 million Americans, accounting for about 1% of all US workers. It’s one of the few remaining jobs that pays a middle-class salary with entry-level skills and doesn’t require an advanced education. It’s also culturally coded as highly masculine, which is advantageous in a world where a large number of men suffer so deeply from fragile masculinity (a major correlate of support for Donald Trump, by the way, as well as a source of a never-ending array of cringeworthy marketing) that they can’t bear to take even the most promising “pink collar” jobs.

And yet, long-haul trucking is probably not going to exist in 20 years. Short-haul and delivery trucking will probably last a bit longer, since it’s helpful to have a human being to drive around complicated city streets and carry deliveries. Automated trucks are already here, and they are just… better. While human drivers need rest, sleep, food, and bathroom breaks, rarely exceeding 11 hours of actual driving per day (which still sounds exhausting!), an automated long-haul truck can stay on the road for over 22 hours per day, even including fuel and maintenance. The capital cost of an automated truck is currently much higher than an ordinary truck, but when that changes, trucking companies aren’t going to keep around a human driver when their robots can deliver twice as fast and don’t expect to be paid wages. Automated vehicles are also safer than human drivers, which will save several thousand lives per year. For this to happen, we don’t even need truly full automation; we just need to get past our current level 3 automation and reach level 4. Prototypes of this level of automation are already under development; in about 10 years they’ll start hitting the road. The shift won’t be instantaneous; once a company has already invested in a truck and a driver, they’ll keep them around for several years. But in 20 years from now, I don’t expect to see a lot of human-driven trucks left.

I’m pleased to see that the government is taking this matter seriously, already trying to develop plans for what to do when long-haul trucks become fully robotic. I hope they can come up with a good plan in time.

Some jobs that will be automated away deserve to be automated away. I can’t shed very many tears for the loss of fast-food workers and grocery cashiers (which we can already see happening around us—been to a Taco Bell lately?); those are terrible jobs that no human being should have to do. And my only concern about automated telemarketing is that it makes telemarketing cheaper and therefore more common; I certainly am not worried about the fact that people won’t be working as telemarketers anymore.

But a lot of good jobs, even white-collar jobs, are at risk of automation. Algorithms are already performing at about the same level as human radiologists, contract reviewers, and insurance underwriters, and once they get substantially better, companies are going to have trouble justifying why they would hire a human who costs more and performs worse. Indeed, the very first job to be automated by information technology was a white-collar job: computer used to be a profession, not a machine.

Technological advancement is inherently difficult to predict: If we knew how future technology will work, we’d make it now. So any such prediction should contain large error bars: “20 years away” could mean we make a breakthrough next year, or it could stay “20 years away” for the next 50 years.

If we had a robust social safety net—a basic income, perhaps?—this would be fine. But our culture decided somewhere along the way that people only deserve to live well if they are currently performing paid services for a corporation, and as robots get better, corporations will find they don’t need so many people performing services. We could face up to this fact and use it as an opportunity for deeper reforms; but I fear that instead we’ll wait to act until the crisis is already upon us.

Unpaid work and the double burden

Apr 16, JDN 2457860

When we say the word “work”, what leaps to mind is usually paid work in the formal sector—the work people do for employers. When you “go to work” each morning, you are going to do your paid work in the formal sector.

But a large quantity of the world’s labor does not take this form. First, there is the informal sectorwork done for cash “under the table”, where there is no formal employment structure and often no reporting or payment of taxes. Many economists estimate that the majority of the world’s workers are employed in the informal sector. The ILO found that informal employment comprises as much as 70% of employment in some countries. However, it depends how you count: A lot of self-employment could be considered either formal or informal. If you base it on whether you do any work outside an employer-employee relationship, informal sector work is highly prevalent around the world. If you base it on not reporting to the government to avoid taxes, informal sector work is less common. If it must be your primary source of income, whether or not you pay taxes, informal sector work is uncommon. And if you only include informal sector work when it is your primary income source and not reported to the government, informal sector work is relatively rare and largely restricted to underdeveloped countries.

But that’s not really my focus for today, because you at least get paid in the informal sector. Nor am I talking about forced laborthat is, slavery, essentially—which is a serious human rights violation that sadly still goes on in many countries.

No, the unpaid work I want to talk about today is work that people willingly do for free.

I’m also excluding internships and student work, where (at least in theory) the idea is that instead of getting paid you are doing the work in order to acquire skills and experience that will be valuable to you later on. I’m talking about work that you do for its own sake.

Such work can be divided into three major categories.
First there is vocation—the artist who would paint even if she never sold a single canvas; the author who is compelled to write day and night and would give the books away for free. Vocation is work that you do for fun, or because it is fulfilling. It doesn’t even feel like “work” in quite the same sense. For me, writing and research are vocation, at least in part; even if I had $5 million in stocks I would still do at least some writing and research as part of what gives my life meaning.

Second there is volunteering—the soup kitchen, the animal shelter, the protest march. Volunteering is work done out of altruism, to help other people or work toward some greater public goal. You don’t do it for yourself, you do it for others.

Third, and really my main focus for this post, is domestic labor—vacuuming the rug, mopping the floor, washing the dishes, fixing the broken faucet, changing the baby’s diapers. This is generally not work that anyone finds particularly meaningful or fulfilling, nor is it done out of any great sense of altruism (perhaps toward your own family, but that’s about the extent of it). But you also don’t get paid to do it. You do it because it must be done.

There is also considerable overlap, of course: Many people find meaning in their activism or charitable work, and part of what motivates artists and authors is a desire to change the world.

Vocation is ultimately what I would like to see the world move towards. One of the great promises of a basic income is that it might finally free us from the grind of conventional employment that has gripped us ever since we first managed to escape the limitations of subsistence farming—which in turn gripped us ever since we escaped the desperation of hunter-gatherer survival. The fourth great stage in human prosperity might finally be a world where we can work not for food or for pay, but for meaning. A world of musicians and painters, of authors and playwrights, of sculptors and woodcutters, yes; but also a world of cinematographers and video remixers, of 3D modelers and holographers, of VR designers and video game modders. If you ever fret that no work would be done without the constant pressure of the wage incentive, spend some time on Stack Overflow or the Steam Workshop. People will spend hundreds of person-hours at extremely high-skill tasks—I’m talking AI programming and 3D modeling here—not for money but for fun.

Volunteering is frankly kind of overrated; as the Effective Altruism community will eagerly explain to you any chance they get, it’s usually more efficient for you to give money rather than time, because money is fungible while giving your time only makes sense if your skills are actually the ones that the project needs. If this criticism of so much well-intentioned work sounds petty, note that literally thousands of lives would be saved each year if instead of volunteering people donated an equivalent amount of money so that charities could hire qualified workers instead. Unskilled volunteers and donations of useless goods after a disaster typically cause what aid professionals call the “second disaster”. Still, people do find meaning in volunteering, and there is value in that; and also there are times when you really are the best one to do it, particularly when it comes to local politics.

But what should we do with domestic labor?

Some of it can and will be automated away—the Parable of the Dishwasher with literal dishwashers. But it will be awhile before it all can, and right now it’s still a bit expensive. Maybe instead of vacuuming I should buy a Roomba—but $500 feels like a lot of money right now.

Much domestic labor we could hire out to someone else, but we simply choose not to. I could always hire someone to fix my computer, unclog my bathtub, or even mop my floors; I just don’t because it seems too expensive.
From the perspective of an economist, it’s actually a bit odd that it seems too expensive. I might have a comparative advantage in fixing my computer—it’s mine, after all, so I know its ins and outs, and while I’m no hotshot Google admin I am a reasonably competent programmer and debugger in my own right. And while for many people auto repair is a household chore, I do actually hire auto mechanics; I don’t even change my own oil, though partly that’s because my little Smart has an extremely compact design that makes it hard to work on. But I surely have no such comparative advantage in cleaning my floors or unclogging my pipes; so why doesn’t it seem worth it to hire someone else to do that?

Maybe I’m being irrational; hiring a cleaning service isn’t that expensive after all. I could hire a cleaning service to do my whole apartment for something like $80, and if I scheduled a regular maid it would probably be something like that per month. That’s what I would charge for two hours of tutoring, so maybe it would behoove me to hire a maid and spend that extra time tutoring or studying.

Or maybe it’s this grad student budget of mine; money is pretty tight at the moment, as I go through this strange societal ritual where young adults go through a period of near-poverty, overwhelming workload and constant anxiety not in spite but because we are so intelligent and hard-working. Perhaps if and when I get that $70,000 job as a professional economist my marginal utility of wealth will decrease and I will feel more inclined to hire maid services.

There are also transaction costs I save on by doing the work myself. A maid would have to commute here, first of all, reducing the efficiency gains from their comparative advantage in the work; but more than that, there’s a lot of effort I’d have to put in just to prepare for the maid and deal with any problems that might arise. There are scheduling issues, and the work probably wouldn’t get done as quickly unless I were to spend enough to hire a maid on a regular basis. There’s also a psychological cost in comfort and privacy to dealing with a stranger in one’s home, and a small but nontrivial risk that the maid might damage or steal something important.

But honestly it might be as simple as social norms (remember: to a first approximation, all human behavior is social norms). Regardless of whether or not it is affordable, it feels strange to hire a maid. That’s the sort of thing only rich, decadent people do. A responsible middle-class adult is supposed to mop their own floors and do their own laundry. Indeed, while hiring a plumber or an auto mechanic feels like paying for a service, hiring a maid crosses a line and feels like hiring a servant. (I honestly always feel a little awkward around the gardeners hired by our housing development for that reason. I’m only paying them indirectly, but there’s still this vague sense that they are somehow subservient—and surely, we are of quite distinct socioeconomic classes. Maybe it would help if I brushed up on my Spanish and got to know them better?)

And then there’s the gender factor. Being in a same-sex couple household changes the domestic labor dynamic quite a bit relative to the conventional opposite-sex couple household. Even in ostensibly liberal, feminist, egalitarian households, and even when both partners are employed full-time, it usually ends up being the woman who does most of the housework. This is true in the US; it is true in the UK; it is true in Europe; indeed it’s true in most if not all countries around the world, and, unsurprisingly, it is worst in India, where women spend a whopping five hours per day more on housework than men. (I was not surprised by the fact that Japan and China also do poorly, given their overall gender norms; but I’m a bit shocked at how badly Ireland and Italy do on this front.) And yes, while #ScandinaviaIsBetter, still in Sweden and Norway women spend half an hour to an hour more on housework on an average day than men.

Which, of course, supports the social norm theory. Any time you see both an overwhelming global trend against women and considerable cross-country variation within that trend, your first hypothesis should be sexism. Without the cross-country variation, maybe it could be biology—the sex differences in height and upper-body strength, for example, are pretty constant across countries. But women doing half an hour more in Norway but five hours more in India looks an awful lot like sexism.

This is called the double burden: To meet the social norms of being responsible middle-class adults, men are merely expected to work full-time at a high-paying job, but women are expected to do both the full effort of maintaining a household and the full effort of working at a full-time job. This is surely an improvement over the time when women were excluded from the formal workforce, not least because of the financial freedom that full-time work affords many women; but it would be very nice if we could also find a way to share some of that domestic burden as well. There has been some trend toward a less unequal share of housework as more women enter the workforce, but it still has a long way to go, even in highly-developed countries.

So, we can start by trying to shift the social norm that housework is gendered: Women clean the floors and change the diapers, while men fix the car and paint the walls. Childcare in particular is something that should be done equally by all parents, and while it’s plausible that one person may be better or worse at mopping or painting, it strains credulity to think that it’s always the woman who is better at mopping and the man who is better at painting.

Yet perhaps this is a good reason to try to shift away from another social norm as well, the one where only rich people hire maids and maids are servants. Unfortunately, it’s likely that most maids will continue to be women for the foreseeable future—cleaning services are gendered in much the same way that nursing and childcare are gendered. But at least by getting paid to clean, one can fulfill the “job” norm and the “housekeeping” norm in one fell swoop; and then women who are in other professions can carry only one burden instead of two. And if we can begin to think of cleaning services as more like plumbing and auto repair—buying a service, not hiring a servant—this is likely to improve the condition and social status of a great many maids. I doubt we’d ever get to the point where mopping floors is as prestigious as performing neurosurgery, but maybe we can at least get to the point where being a maid is as respectable as being a plumber. Cleaning needs done; it shouldn’t be shameful to be someone who is very good at doing it and gets paid to do so. (That is perhaps the most pernicious aspect of socioeconomic class, this idea that some jobs are “shameful” because they are done by workers with less education or involve more physical labor.)
This also makes good sense in terms of economic efficiency: Your comparative advantage is probably not in cleaning services, or if it is then perhaps you should do that as a career. So by selling your labor at whatever you are good at and then buying the services of someone who is especially good at cleaning, you should, at least in theory, be able to get the same cleaning done and maintain the same standard of living for yourself while also accomplishing more at whatever it is you do in your profession and providing income for whomever you hire to do the cleaning.

So, should I go hire a cleaning service after all? I don’t know, that still sounds pretty expensive.

Sometimes people have to lose their jobs. This isn’t a bad thing.

Oct 8, JDN 2457670

Eleizer Yudkowsky (founder of the excellent blog forum Less Wrong) has a term he likes to use to distinguish his economic policy views from either liberal, conservative, or even libertarian: “econoliterate”, meaning the sort of economic policy ideas one comes up with when one actually knows a good deal about economics.

In general I think Yudkowsky overestimates this effect; I’ve known some very knowledgeable economists who disagree quite strongly over economic policy, and often following the conventional political lines of liberal versus conservative: Liberal economists want more progressive taxation and more Keynesian monetary and fiscal policy, while conservative economists want to reduce taxes on capital and remove regulations. Theoretically you can want all these things—as Miles Kimball does—but it’s rare. Conservative economists hate minimum wage, and lean on the theory that says it should be harmful to employment; liberal economists are ambivalent about minimum wage, and lean on the empirical data that shows it has almost no effect on employment. Which is more reliable? The empirical data, obviously—and until more economists start thinking that way, economics is never truly going to be a science as it should be.

But there are a few issues where Yudkowsky’s “econoliterate” concept really does seem to make sense, where there is one view held by most people, and another held by economists, regardless of who is liberal or conservative. One such example is free trade, which almost all economists believe in. A recent poll of prominent economists by the University of Chicago found literally zero who agreed with protectionist tariffs.

Another example is my topic for today: People losing their jobs.

Not unemployment, which both economists and almost everyone else agree is bad; but people losing their jobs. The general consensus among the public seems to be that people losing jobs is always bad, while economists generally consider it a sign of an economy that is run smoothly and efficiently.

To be clear, of course losing your job is bad for you; I don’t mean to imply that if you lose your job you shouldn’t be sad or frustrated or anxious about that, particularly not in our current system. Rather, I mean to say that policy which tries to keep people in their jobs is almost always a bad idea.

I think the problem is that most people don’t quite grasp that losing your job and not having a job are not the same thing. People not having jobs who want to have jobs—unemployment—is a bad thing. But losing your job doesn’t mean you have to stay unemployed; it could simply mean you get a new job. And indeed, that is what it should mean, if the economy is running properly.

Check out this graph, from FRED:

hires_separations

The red line shows hires—people getting jobs. The blue line shows separations—people losing jobs or leaving jobs. During a recession (the most recent two are shown on this graph), people don’t actually leave their jobs faster than usual; if anything, slightly less. Instead what happens is that hiring rates drop dramatically. When the economy is doing well (as it is right now, more or less), both hires and separations are at very high rates.

Why is this? Well, think about what a job is, really: It’s something that needs done, that no one wants to do for free, so someone pays someone else to do it. Once that thing gets done, what should happen? The job should end. It’s done. The purpose of the job was not to provide for your standard of living; it was to achieve the task at hand. Once it doesn’t need done, why keep doing it?

We tend to lose sight of this, for a couple of reasons. First, we don’t have a basic income, and our social welfare system is very minimal; so a job usually is the only way people have to provide for their standard of living, and they come to think of this as the purpose of the job. Second, many jobs don’t really “get done” in any clear sense; individual tasks are completed, but new ones always arise. After every email sent is another received; after every patient treated is another who falls ill.

But even that is really only true in the short run. In the long run, almost all jobs do actually get done, in the sense that no one has to do them anymore. The job of cleaning up after horses is done (with rare exceptions). The job of manufacturing vacuum tubes for computers is done. Indeed, the job of being a computer—that used to be a profession, young women toiling away with slide rules—is very much done. There are no court jesters anymore, no town criers, and very few artisans (and even then, they’re really more like hobbyists). There are more writers now than ever, and occasional stenographers, but there are no scribes—no one powerful but illiterate pays others just to write things down, because no one powerful is illiterate (and even few who are not powerful, and fewer all the time).

When a job “gets done” in this long-run sense, we usually say that it is obsolete, and again think of this as somehow a bad thing, like we are somehow losing the ability to do something. No, we are gaining the ability to do something better. Jobs don’t become obsolete because we can’t do them anymore; they become obsolete because we don’t need to do them anymore. Instead of computers being a profession that toils with slide rules, they are thinking machines that fit in our pockets; and there are plenty of jobs now for software engineers, web developers, network administrators, hardware designers, and so on as a result.

Soon, there will be no coal miners, and very few oil drillers—or at least I hope so, for the sake of our planet’s climate. There will be far fewer auto workers (robots have already done most of that already), but far more construction workers who install rail lines. There will be more nuclear engineers, more photovoltaic researchers, even more miners and roofers, because we need to mine uranium and install solar panels on rooftops.

Yet even by saying that I am falling into the trap: I am making it sound like the benefit of new technology is that it opens up more new jobs. Typically it does do that, but that isn’t what it’s for. The purpose of technology is to get things done.

Remember my parable of the dishwasher. The goal of our economy is not to make people work; it is to provide people with goods and services. If we could invent a machine today that would do the job of everyone in the world and thereby put us all out of work, most people think that would be terrible—but in fact it would be wonderful.

Or at least it could be, if we did it right. See, the problem right now is that while poor people think that the purpose of a job is to provide for their needs, rich people think that the purpose of poor people is to do jobs. If there are no jobs to be done, why bother with them? At that point, they’re just in the way! (Think I’m exaggerating? Why else would anyone put a work requirement on TANF and SNAP? To do that, you must literally think that poor people do not deserve to eat or have homes if they aren’t, right now, working for an employer. You can couch that in cold economic jargon as “maximizing work incentives”, but that’s what you’re doing—you’re threatening people with starvation if they can’t or won’t find jobs.)

What would happen if we tried to stop people from losing their jobs? Typically, inefficiency. When you aren’t allowed to lay people off when they are no longer doing useful work, we end up in a situation where a large segment of the population is being paid but isn’t doing useful work—and unlike the situation with a basic income, those people would lose their income, at least temporarily, if they quit and tried to do something more useful. There is still considerable uncertainty within the empirical literature on just how much “employment protection” (laws that make it hard to lay people off) actually creates inefficiency and reduces productivity and employment, so it could be that this effect is small—but even so, likewise it does not seem to have the desired effect of reducing unemployment either. It may be like minimum wage, where the effect just isn’t all that large. But it’s probably not saving people from being unemployed; it may simply be shifting the distribution of unemployment so that people with protected jobs are almost never unemployed and people without it are unemployed much more frequently. (This doesn’t have to be based in law, either; while it is made by custom rather than law, it’s quite clear that tenure for university professors makes tenured professors vastly more secure, but at the cost of making employment tenuous and underpaid for adjuncts.)

There are other policies we could make that are better than employment protection, active labor market policies like those in Denmark that would make it easier to find a good job. Yet even then, we’re assuming that everyone needs jobs–and increasingly, that just isn’t true.

So, when we invent a new technology that replaces workers, workers are laid off from their jobs—and that is as it should be. What happens next is what we do wrong, and it’s not even anybody in particular; this is something our whole society does wrong: All those displaced workers get nothing. The extra profit from the more efficient production goes entirely to the shareholders of the corporation—and those shareholders are almost entirely members of the top 0.01%. So the poor get poorer and the rich get richer.

The real problem here is not that people lose their jobs; it’s that capital ownership is distributed so unequally. And boy, is it ever! Here are some graphs I made of the distribution of net wealth in the US, using from the US Census.

Here are the quintiles of the population as a whole:

net_wealth_us

And here are the medians by race:

net_wealth_race

Medians by age:

net_wealth_age

Medians by education:

net_wealth_education

And, perhaps most instructively, here are the quintiles of people who own their homes versus renting (The rent is too damn high!)

net_wealth_rent

All that is just within the US, and already they are ranging from the mean net wealth of the lowest quintile of people under 35 (-$45,000, yes negative—student loans) to the mean net wealth of the highest quintile of people with graduate degrees ($3.8 million). All but the top quintile of renters are poorer than all but the bottom quintile of homeowners. And the median Black or Hispanic person has less than one-tenth the wealth of the median White or Asian person.

If we look worldwide, wealth inequality is even starker. Based on UN University figures, 40% of world wealth is owned by the top 1%; 70% by the top 5%; and 80% by the top 10%. There is less total wealth in the bottom 80% than in the 80-90% decile alone. According to Oxfam, the richest 85 individuals own as much net wealth as the poorest 3.7 billion. They are the 0.000,001%.

If we had an equal distribution of capital ownership, people would be happy when their jobs became obsolete, because it would free them up to do other things (either new jobs, or simply leisure time), while not decreasing their income—because they would be the shareholders receiving those extra profits from higher efficiency. People would be excited to hear about new technologies that might displace their work, especially if those technologies would displace the tedious and difficult parts and leave the creative and fun parts. Losing your job could be the best thing that ever happened to you.

The business cycle would still be a problem; we have good reason not to let recessions happen. But stopping the churn of hiring and firing wouldn’t actually make our society better off; it would keep people in jobs where they don’t belong and prevent us from using our time and labor for its best use.

Perhaps the reason most people don’t even think of this solution is precisely because of the extreme inequality of capital distribution—and the fact that it has more or less always been this way since the dawn of civilization. It doesn’t seem to even occur to most people that capital income is a thing that exists, because they are so far removed from actually having any amount of capital sufficient to generate meaningful income. Perhaps when a robot takes their job, on some level they imagine that the robot is getting paid, when of course it’s the shareholders of the corporations that made the robot and the corporations that are using the robot in place of workers. Or perhaps they imagine that those shareholders actually did so much hard work they deserve to get paid that money for all the hours they spent.

Because pay is for work, isn’t it? The reason you get money is because you’ve earned it by your hard work?

No. This is a lie, told to you by the rich and powerful in order to control you. They know full well that income doesn’t just come from wages—most of their income doesn’t come from wages! Yet this is even built into our language; we say “net worth” and “earnings” rather than “net wealth” and “income”. (Parade magazine has a regular segment called “What People Earn”; it should be called “What People Receive”.) Money is not your just reward for your hard work—at least, not always.

The reason you get money is that this is a useful means of allocating resources in our society. (Remember, money was created by governments for the purpose of facilitating economic transactions. It is not something that occurs in nature.) Wages are one way to do that, but they are far from the only way; they are not even the only way currently in use. As technology advances, we should expect a larger proportion of our income to go to capital—but what we’ve been doing wrong is setting it up so that only a handful of people actually own any capital.

Fix that, and maybe people will finally be able to see that losing your job isn’t such a bad thing; it could even be satisfying, the fulfillment of finally getting something done.

The high cost of frictional unemployment

Sep 3, JDN 2457635

I had wanted to open this post with an estimate of the number of people in the world, or at least in the US, who are currently between jobs. It turns out that such estimates are essentially nonexistent. The Bureau of Labor Statistics maintains a detailed database of US unemployment; they don’t estimate this number. We have this concept in macroeconomics of frictional unemployment, the unemployment that results from people switching jobs; but nobody seems to have any idea how common it is.

I often hear a ballpark figure of about 4-5%, which is related to a notion that “full employment” should really be about 4-5% unemployment because otherwise we’ll trigger horrible inflation or something. There is almost no evidence for this. In fact, the US unemployment rate has gotten as low as 2.5%, and before that was stable around 3%. This was during the 1950s, the era of the highest income tax rates ever imposed in the United States, a top marginal rate of 92%. Coincidence? Maybe. Obviously there were a lot of other things going on at the time. But it sure does hurt the argument that high income taxes “kill jobs”, don’t you think?

Indeed, it may well be that the rate of frictional unemployment varies all the time, depending on all sorts of different factors. But here’s what we do know: Frictional unemployment is a serious problem, and yet most macroeconomists basically ignore it.

Talk to most macroeconomists about “unemployment”, and they will assume you mean either cyclical unemployment (the unemployment that results from recessions and bad fiscal and monetary policy responses to them), or structural unemployment (the unemployment that results from systematic mismatches between worker skills and business needs). If you specifically mention frictional unemployment, the response is usually that it’s no big deal and there’s nothing we can do about it anyway.

Yet at least when we aren’t in a recession, frictional employment very likely accounts for the majority of unemployment, and thus probably the majority of misery created by unemployment. (Not necessarily, since it probably doesn’t account for much long-term unemployment, which is by far the worst.) And it is quite clear to me that there are things we can do about it—they just might be difficult and/or expensive.

Most of you have probably changed jobs at least once. Many of you have, like me, moved far away to a new place for school or work. Think about how difficult that was. There is the monetary cost, first of all; you need to pay for the travel of course, and then usually leases and paychecks don’t line up properly for a month or two (for some baffling and aggravating reason, UCI won’t actually pay me my paychecks until November, despite demanding rent starting the last week of July!). But even beyond that, you are torn from your social network and forced to build a new one. You have to adapt to living in a new place which may have differences in culture and climate. Bureaucracy often makes it difficult to change over documentation of such as your ID and your driver’s license.

And that’s assuming that you already found a job before you moved, which isn’t always an option. Many people move to new places and start searching for jobs when they arrive, which adds an extra layer of risk and difficulty above and beyond the transition itself.

With all this in mind, the wonder is that anyone is willing to move at all! And this is probably a large part of why people are so averse to losing their jobs even when it is clearly necessary; the frictional unemployment carries enormous real costs. (That and loss aversion, of course.)

What could we do, as a matter of policy, to make such transitions easier?

Well, one thing we could do is expand unemployment insurance, which reduces the cost of losing your job (which, despite the best efforts of Republicans in Congress, we ultimately did do in the Second Depression). We could expand unemployment insurance to cover voluntary quits. Right now, quitting voluntarily makes you forgo all unemployment benefits, which employers pay for in the form of insurance premiums; so an employer is much better off making your life miserable until you quit than they are laying you off. They could also fire you for cause, if they can find a cause (and usually there’s something they could trump up enough to get rid of you, especially if you’re not prepared for the protracted legal battle of a wrongful termination lawsuit). The reasoning of our current system appears to be something like this: Only lazy people ever quit jobs, and why should we protect lazy people? This is utter nonsense and it needs to go. Many states already have no-fault divorce and no-fault auto collision insurance; it’s time for no-fault employment termination.

We could establish a basic income of course; then when you lose your job your income would go down, but to a higher floor where you know you can meet certain basic needs. We could provide subsidized personal loans, similar to the current student loan system, that allow people to bear income gaps without losing their homes or paying exorbitant interest rates on credit cards.

We could use active labor market programs to match people with jobs, or train them with the skills needed for emerging job markets. Denmark has extensive active labor market programs (they call it “flexicurity”), and Denmark’s unemployment rate was 2.4% before the Great Recession, hit a peak of 6.2%, and has now recovered to 4.2%. What Denmark calls a bad year, the US calls a good year—and Greece fantasizes about as something they hope one day to achieve. #ScandinaviaIsBetter once again, and Norway fits this pattern also, though to be fair Sweden’s unemployment rate is basically comparable to the US or even slightly worse (though it’s still nothing like Greece).

Maybe it’s actually all right that we don’t have estimates of the frictional unemployment rate, because the goal really isn’t to reduce the number of people who are unemployed; it’s to reduce the harm caused by unemployment. Most of these interventions would very likely increase the rate frictional unemployment, as people who always wanted to try to find better jobs but could never afford to would now be able to—but they would dramatically reduce the harm caused by that unemployment.

This is a more general principle, actually; it’s why we should basically stop taking seriously this argument that social welfare benefits destroy work incentives. That may well be true; so what? Maximizing work incentives was never supposed to be a goal of public policy, as far as I can tell. Maximizing human welfare is the goal, and the only way a welfare program could reduce work incentives is by making life better for people who aren’t currently working, and thereby reducing the utility gap between working and not working. If your claim is that the social welfare program (and its associated funding mechanism, i.e. taxes, debt, or inflation) would make life sufficiently worse for everyone else that it’s not worth it, then say that (and for some programs that might actually be true). But in and of itself, making life better for people who don’t work is a benefit to society. Your supposed downside is in fact an upside. If there’s a downside, it must be found elsewhere.

Indeed, I think it’s worth pointing out that slavery maximizes work incentives. If you beat or kill people who don’t work, sure enough, everyone works! But that is not even an efficient economy, much less a just society. To be clear, I don’t think most people who say they want to maximize work incentives would actually support slavery, but that is the logical extent of the assertion. (Also, many Libertarians, often the first to make such arguments, do have a really bizarre attitude toward slavery; taxation is slavery, regulation is slavery, conscription is slavery—the last not quite as ridiculous—but actual forced labor… well, that really isn’t so bad, especially if the contract is “voluntary”. Fortunately some Libertarians are not so foolish.) If your primary goal is to make people work as much as possible, slavery would be a highly effective way to achieve that goal. And that really is the direction you’re heading when you say we shouldn’t do anything to help starving children lest their mothers have insufficient incentive to work.

More people not working could have a downside, if it resulted in less overall production of goods. But even in the US, one of the most efficient labor markets in the world, the system of job matching is still so ludicrously inefficient that people have to send out dozens if not hundreds of applications to jobs they barely even want, and there are still 1.4 times as many job seekers as there are openings (at the trough of the Great Recession, the ratio was 6.6 to 1). There’s clearly a lot of space here to improve the matching efficiency, and simply giving people more time to search could make a big difference there. Total output might decrease for a little while during the first set of transitions, but afterward people would be doing jobs they want, jobs they care about, jobs they’re good at—and people are vastly more productive under those circumstances. It’s quite likely that total employment would decrease, but productivity would increase so much that total output increased.

Above all, people would be happier, and that should have been our goal all along.

What really happened in Greece

JDN 2457506

I said I’d get back to this issue, so here goes.

Let’s start with what is uncontroversial: Greece is in trouble.

Their per-capita GDP PPP has fallen from a peak of over $32,000 in 2007 to a trough of just over $24,000 in 2013, and only just began to recover over the last 2 years. That’s a fall of 29 log points. Put another way, the average person in Greece has about the same real income now that they had in the year 2000—a decade and a half of economic growth disappeared.

Their unemployment rate surged from about 7% in 2007 to almost 28% in 2013. It remains over 24%. That is, almost one quarter of all adults in Greece are seeking jobs and not finding them. The US has not seen an unemployment rate that high since the Great Depression.

Most shocking of all, over 40% of the population in Greece is now below the national poverty line. They define poverty as 60% of the inflation-adjusted average income in 2009, which works out to 665 Euros per person ($756 at current exchange rates) per month, or about $9000 per year. They also have an absolute poverty line, which 14% of Greeks now fall below, but only 2% did before the crash.

So now, let’s talk about why.

There’s a standard narrative you’ve probably heard many times, which goes something like this:

The Greek government spent too profligately, heaping social services on the population without the tax base to support them. Unemployment insurance was too generous; pensions were too large; it was too hard to fire workers or cut wages. Thus, work incentives were too weak, and there was no way to sustain a high GDP. But they refused to cut back on these social services, and as a result went further and further into debt until it finally became unsustainable. Now they are cutting spending and raising taxes like they needed to, and it will eventually allow them to repay their debt.

Here’s a fellow of the Cato Institute spreading this narrative on the BBC. Here’s ABC with a five bullet-point list: Pension system, benefits, early retirement, “high unemployment and work culture issues” (yes, seriously), and tax evasion. Here the Telegraph says that Greece “went on a spending spree” and “stopped paying taxes”.

That story is almost completely wrong. Almost nothing about it is true. Cato and the Telegraph got basically everything wrong. The only one ABC got right was tax evasion.

Here’s someone else arguing that Greece has a problem with corruption and failed governance; there is something to be said for this, as Greece is fairly corrupt by European standards—though hardly by world standards. For being only a generation removed from an authoritarian military junta, they’re doing quite well actually. They’re about as corrupt as a typical upper-middle income country like Libya or Botswana; and Botswana is widely regarded as the shining city on a hill of transparency as far as Sub-Saharan Africa is concerned. So corruption may have made things worse, but it can’t be the whole story.

First of all, social services in Greece were not particularly extensive compared to the rest of Europe.

Before the crisis, Greece’s government spending was about 44% of GDP.

That was about the same as Germany. It was slightly more than the UK. It was less than Denmark and France, both of which have government spending of about 50% of GDP.

Greece even tried to cut spending to pay down their debt—it didn’t work, because they simply ended up worsening the economic collapse and undermining the tax base they needed to do that.

Europe has fairly extensive social services by world standards—but that’s a major part of why it’s the First World. Even the US, despite spending far less than Europe on social services, still spends a great deal more than most countries—about 36% of GDP.

Second, if work incentives were a problem, you would not have high unemployment. People don’t seem to grasp what the word unemployment actually means, which is part of why I can’t stand it when news outlets just arbitrarily substitute “jobless” to save a couple of syllables. Unemployment does not mean simply that you don’t have a job. It means that you don’t have a job and are trying to get one.

The word you’re looking for to describe simply not having a job is nonemployment, and that’s such a rarely used term my spell-checker complains about it. Yet economists rarely use this term precisely because it doesn’t matter; a high nonemployment rate is not a symptom of a failing economy but a result of high productivity moving us toward the post-scarcity future (kicking and screaming, evidently). If the problem with Greece were that they were too lazy and they retire too early (which is basically what ABC was saying in slightly more polite language), there would be high nonemployment, but there would not be high unemployment. “High unemployment and work culture issues” is actually a contradiction.

Before the crisis, Greece had an employment-to-population ratio of 49%, meaning a nonemployment rate of 51%. If that sounds ludicrously high, you’re not accustomed to nonemployment figures. During the same time, the United States had an employment-to-population ratio of 52% and thus a nonemployment rate of 48%. So the number of people in Greece who were voluntarily choosing to drop out of work before the crisis was just slightly larger than the number in the US—and actually when you adjust for the fact that the US is full of young immigrants and Greece is full of old people (their median age is 10 years older than ours), it begins to look like it’s we Americans who are lazy. (Actually, it’s that we are studious—the US has an extremely high rate of college enrollment and the best colleges in the world. Full-time students are nonemployed, but they are certainly not unemployed.)

But Greece does have an enormously high debt, right? Yes—but it was actually not as bad before the crisis. Their government debt surged from 105% of GDP to almost 180% today. 105% of GDP is about what we have right now in the US; it’s less than what we had right after WW2. This is a little high, but really nothing to worry about, especially if you’ve incurred the debt for the right reasons. (The famous paper by Rogart and Reinhoff arguing that 90% of GDP is a horrible point of no return was literally based on math errors.)

Moreover, Ireland and Spain suffered much the same fate as Greece, despite running primary budget surpluses.

So… what did happen? If it wasn’t their profligate spending that put them in this mess, what was it?

Well, first of all, there was the Second Depression, a worldwide phenomenon triggered by the collapse of derivatives markets in the United States. (You want unsustainable debt? Try 20 to 1 leveraged CDO-squareds and one quadrillion dollars in notional value. Notional value isn’t everything, but it’s a lot.) So it’s mainly our fault, or rather the fault of our largest banks. As far as us voters, it’s “our fault” in the way that if your car gets stolen it’s “your fault” for not locking the doors and installing a LoJack. We could have regulated against this and enforced those regulations, but we didn’t. (Fortunately, Dodd-Frank looks like it might be working.)

Greece was hit particularly hard because they are highly dependent on trade, particularly in services like tourism that are highly sensitive to the business cycle. Before the crash they imported 36% of GDP and exported 23% of GDP. Now they import 35% of GDP and export 33% of GDP—but it’s a much smaller GDP. Their exports have only slightly increased while their imports have plummeted. (This has reduced their “trade deficit”, but that has always been a silly concept. I guess it’s less silly if you don’t control your own currency, but it’s still silly.)

Once the crash happened, the US had sovereign monetary policy and the wherewithal to actually use that monetary policy effectively, so we weathered the crash fairly well, all things considered. Our unemployment rate barely went over 10%. But Greece did not have sovereign monetary policy—they are tied to the Euro—and that severely limited their options for expanding the money supply as a result of the crisis. Raising spending and cutting taxes was the best thing they could do.

But the bank(st?)ers and their derivatives schemes caused the Greek debt crisis a good deal more directly than just that. Part of the condition of joining the Euro was that countries must limit their fiscal deficit to no more than 3% of GDP (which is a totally arbitrary figure with no economic basis in case you were wondering). Greece was unwilling or unable to do so, but wanted to look like they were following the rules—so they called up Goldman Sachs and got them to make some special derivatives that Greece could use to continue borrowing without looking like they were borrowing. The bank could have refused; they could have even reported it to the European Central Bank. But of course they didn’t; they got their brokerage fee, and they knew they’d sell it off to some other bank long before they had to worry about whether Greece could ever actually repay it. And then (as I said I’d get back to in a previous post) they paid off the credit rating agencies to get them to rate these newfangled securities as low-risk.

In other words, Greece is not broke; they are being robbed.

Like homeowners in the US, Greece was offered loans they couldn’t afford to pay, but the banks told them they could, because the banks had lost all incentive to actually bother with the question of whether loans can be repaid. They had “moved on”; their “financial innovation” of securitization and collateralized debt obligations meant that they could collect origination fees and brokerage fees on loans that could never possibly be repaid, then sell them off to some Greater Fool down the line who would end up actually bearing the default. As long as the system was complex enough and opaque enough, the buyers would never realize the garbage they were getting until it was too late. The entire concept of loans was thereby broken: The basic assumption that you only loan money you expect to be repaid no longer held.

And it worked, for awhile, until finally the unpayable loans tried to create more money than there was in the world, and people started demanding repayment that simply wasn’t possible. Then the whole scheme fell apart, and banks began to go under—but of course we saved them, because you’ve got to save the banks, how can you not save the banks?

Honestly I don’t even disagree with saving the banks, actually. It was probably necessary. What bothers me is that we did nothing to save everyone else. We did nothing to keep people in their homes, nothing to stop businesses from collapsing and workers losing their jobs. Precisely because of the absurd over-leveraging of the financial system, the cost to simply refinance every mortgage in America would have been less than the amount we loaned out in bank bailouts. The banks probably would have done fine anyway, but if they didn’t, so what? The banks exist to serve the people—not the other way around.

We can stop this from happening again—here in the US, in Greece, in the rest of Europe, everywhere. But in order to do that we must first understand what actually happened; we must stop blaming the victims and start blaming the perpetrators.