The Republicans passed a terrible budget

May 4 JDN 2460800

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

So what’s so bad about it?

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

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

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

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

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

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

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

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

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

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

An interview with Claude

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.

I can’t not talk about tariffs right now

Apr 13 JDN 2460779

On the one hand, I’m sure every economics blog on the Internet is already talking about this, including Paul Krugman who knows the subject way better than I ever will (and literally won a Nobel Prize for his work on it). And I have other things I’d rather be writing about, like the Index of Necessary Expenditure. But on the other hand, when something this big happens in economics, it just feels like there’s really no alternative: I have to talk about tariffs right now.

What is a tariff, anyway?

This feels like a really basic question, but it also seems like a lot of people don’t really understand tariffs, or didn’t when they voted for Trump.

A tariff, quite simply, is an import tax. It’s a tax that you impose on imported goods (either a particular kind, or from a particular country, or just across the board). On paper, it is generally paid by the company importing the goods, but as I wrote about in my sequence on tax incidence, that doesn’t matter. What matters is how prices change in response to the tax, and this means that in real terms, prices will go up.

In fact, in some sense that’s the goal of a protectionist tariff, because you’re trying to fix the fact that local producers can’t compete on the global market. So you compensate by making international firms pay higher taxes, so that the local producers can charge higher prices and still compete. So anyone who is saying that tariffs won’t raise prices is either ignorant or lying: Raising prices is what tariffs do.

Why are people so surprised?

The thing that surprises me about all this, (a bit ironically) is how surprised people seem to be. Trump ran his whole campaign promising two things: Deport all the immigrants, and massive tariffs on all trade. Most of his messaging was bizarre and incoherent, but on those two topics he was very consistent. So why in the world are people—including stock traders, who are supposedly savvy on these things—so utterly shocked that he has actually done precisely what he promised he would do?

What did people think Trump meant when he said these things? Did they assume he was bluffing? Did they think cooler heads in his administration would prevail (if so, whose?)?

But I will admit that even I am surprised at just how big the tariffs are. I knew they would be big, but I did not expect them to be this big.

How big?

Well, take a look at this graph:

The average tariff rate on US imports will now be higher than it was at the peak in 1930 with the Smoot-Hawley Act. Moreover, Smoot-Hawley was passed during a time when protectionist tariffs were already in place, while Trump’s tariffs come at a time when tariffs had previously been near zero—so the change is dramatically more sudden.

This is worse than Smoot-Hawley.

For the uninitiated, Smoot-Hawley was a disaster. Several countries retaliated with their own tariffs, and the resulting trade war clearly exacerbated the Great Depression, not only in the US but around the world. World trade dropped by an astonishing 66% over the next few years. It’s still debated as to how much of the depression was caused by the tariffs; most economists believe that the gold standard was the bigger culprit. But it definitely made it worse.

Politically, the aftermath cost the Republicans (including Smoot and Hawley themselves) several seats in Congress. (I guess maybe the silver lining here is we can hope this will do the same?)

And I would now like to remind you that these tariffs are bigger than Smoot-Hawley’s and were implemented more suddenly.

Unlike in 1930, we are not currently in a depression—though nor is our economy as hunky-dory as a lot of pundits seem to think, once we consider things like the Index of Necessary Expenditure. But stock markets do seem to be crashing, and if trade drops as much as it did in the 1930s—and why wouldn’t it?—we may very well end up in another depression.

And it’s not as if we didn’t warn you all. Economists across the political spectrum have been speaking out against Trump’s tariffs from the beginning, and nobody listened to us.

So basically the mood of all economists right now is:

Extrapolating the INE

Apr 6 JDN 2460772

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

The result is this graph:

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

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

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

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

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

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

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

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

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

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

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

The Index of Necessary Expenditure

Mar 16 JDN 2460751

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

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

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

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


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

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

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

The core idea here is this:

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

So let’s summarize what all is included here:

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

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

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

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

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

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

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

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

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

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

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

On this, my 37th birthday

Jan 19 JDN 2460695

This post will go live on my 37th birthday. I’m now at an age where birthdays don’t really feel like a good thing.

This past year has been one of my worst ever.

It started with returning home from the UK, burnt out, depressed, suffering from frequent debilitating migraines. I had no job prospects, and I was too depressed to search for any. I moved in with my mother, who lately has been suffering health problems of her own.

Gradually, far too gradually, some aspects of my situation improved; my migraines are now better controlled, my depression has been reduced. I am now able to search for jobs at least—but I still haven’t found one. I would say that my mother’s health is better than it was—but several of her conditions are chronic, and much of this struggle will continue indefinitely.

I look back on this year feeling shame, despair, failure and defeat. I haven’t published anything—either fiction, nonfiction, or scientific—in years, and after months of searching I still haven’t found a job that would let me and my husband move to a home of our own. My six figures of student debt are now in forbearance, because the SAVE plan was struck down in court. (At least they’re not accruing interest….) I can’t think of anything I’ve done this year that I would count as a meaningful accomplishment. I feel like I’m just treading water, trying not to drown.

I see others my age finding careers, buying homes, starting families. Honestly they’re a little old to be doing these things now—we Millennials have drawn the short straw on homeownership for sure. (The median age of first-time homebuyers is now 38 years old—the highest ever recorded. In 1981, it was only 29.) I don’t see that happening for me any time soon, and I feel a deep grief over that.

I have not had a year go this badly since high school, when I was struggling even more with migraines and depression. Back then I had debilitating migraines multiple times per week, and my depression sometimes kept me from getting out of bed. I even had suicidal thoughts for a time, though I never made any plans or attempts.

Somehow, despite all that, I still managed to maintain straight As in high school and became a kind of de facto valedictorian. (My school technically didn’t have a valedictorian, but I had the best grades, and I successfully petitioned for special dispensation to deliver a much longer graduation speech than any other student.) Some would say this was because I was so brilliant, but I say it was because high school was too easy—and that this set me up for unrealistic expectations later in life. I am a poster child for Gifted Kid Syndrome and Impostor Syndrome. Honestly, maybe I would have gotten better help for my conditions sooner if my grades had slipped.

Will the coming year be better?

In some ways, probably. Now that my migraines and depression are better controlled—but by no means gone—I have been able to actively search for jobs, and I should be able to find one that fits me eventually (or so I keep trying to convince myself, when it all feels hopeless and pointless). And once I do have a job, whenever that happens, I might be able to start saving up for a home and finally move forward into feeling like a proper adult in this society.

But I look to the coming year feeling fear and dread, as Trump will soon take office and already looks primed to be far worse the second time around. In all likelihood I personally won’t suffer very much from Trump’s incompetence and malfeasance—but millions of other people will, and I don’t know how I can help them, especially when I seem so ineffectual at helping myself.

Why I celebrate Christmas

Dec 22 JDN 2460667

In my last several posts I’ve been taking down religion and religious morality. So it might seem strange, or even hypocritical, that I would celebrate Christmas, which is widely regarded as a Christian religious holiday. Allow me to explain.

First of all, Christmas is much older than Christianity.

It had other names before: Solstice celebrations, Saturnalia, Yuletide. But human beings of a wide variety of cultures around the world have been celebrating some kind of winter festival around the solstice since time immemorial.

Indeed, many of the traditions we associate with Christmas, such as decorating trees and having an—ahem—Yule log, are in fact derived from pre-Christian traditions that Christians simply adopted.

The reason different regions have their own unique Christmas traditions, such as Krampus, is most likely that these regions already had such traditions surrounding their winter festivals which likewise got absorbed into Christmas once Christianity took over. (Though oddly enough, Mari Lwyd seems to be much more recent, created in the 1800s.)

In fact, Christmas really has nothing to do with the birth of Jesus.

It’s wildly improbable that Jesus was born in December. Indeed, we have very little historical or even Biblical evidence of his birth date. (What little we do have strongly suggests it wasn’t in winter.)

The date of December 25 was almost certainly chosen in order to coincide—and therefore compete—with the existing Roman holiday of Dies Natalis Solis Invicti (literally, “the birthday of the invincible sun”), an ancient solstice celebration. Today the Winter Solstice is slightly earlier, but in the Julian calendar it was December 25.

In the past, Christians have sometimes suppressed Christmas celebration.

Particularly during the 17th century, most Protestant sects, especially the Puritans, regarded Christmas as a Catholic thing, and therefore strongly discouraged their own adherents from celebrating it.

Besides, Christmas is very secularized at this point.

Many have bemoaned its materialistic nature—and even economists have claimed it is “inefficient”—but gift-giving has become a central part of the celebration of Christmas, despite it being a relatively recent addition. Santa Claus has a whole fantasy magic narrative woven around him that is the source of countless movies and has absolutely nothing to do with Christianity.

I celebrate because we celebrate.

When I celebrate Christmas, I’m also celebrating Saturnalia, and Yuletide, and many of the hundreds of other solstice celebrations and winter festivals that human cultures around the world have held for thousands of years. I’m placing myself within a grander context, a unified human behavior that crosses lines of race, religion, and nationality.

Not all cultures celebrate the Winter Solstice, but a huge number do—and those that don’t have their own celebrations which often involve music and feasting and gift-giving too.

So Merry Christmas, and Happy Yuletide, and Io Saturnalia to you all.

Trump Won. Now what?

Nov 10 JDN 2460625

How did Trump win?

After the election results were announced, one of the first things I saw on social media, aside from the shock and panic among most of my friends and acquaintances, was various people trying to explain what happened this election by some flaw in Kamala Harris or her campaign.

They said it was the economy—even though the economy was actually very good, with the lowest unemployment we’ve had in decades and inflation coming back to normal. Real wages have been rising quickly, especially at the bottom! Most economists agree that inflation will be worse under Trump than it would have been under Harris.

They said it was too much identity politics, or else that Black and Latino men felt their interests were being ignored—somehow it was both of those things.

They said it was her support of Israel in its war crimes in Gaza—even though Trump supports them even more.

They said she was too radical on trans issues—even though most Americans favor anti-discrimination laws protecting trans people.

They said Harris didn’t campaign well—even though her campaign was obviously better organized than Trump’s (or Hillary Clinton’s).

They said it was too much talk about abortion, alienating pro-lifers—even though the majority of Americans want abortion to be legal in all or most cases.

They said that Biden stepped down too late, and she didn’t have enough time—even though he stepped down as soon as he showed signs of cognitive decline, and her poll numbers were actually better early on in the campaign.

They said that Harris was wrong to court endorsements by Republicans—even though endorsements form the other side are exactly the sort of thing that usually convinces undecided voters.

None of these explanations actually hold much water.

BUT EVEN IF THEY DID, IT WOULDN’T MATTER.

I could stipulate that Harris and her campaign had all of these failures and more. I could agree that she’s the worst candidate the Democrats have fielded in decades. (She wasn’t.)

THE ALTERNATIVE WAS DONALD TRUMP.

Trump is so terrible that he utterly eclipses any failings that could reasonably be attributed to Harris. He is racist, fascist, authoritarian, bigoted, incompetent, narcissistic, egomaniacal, corrupt, a liar, a cheat, an insurrectionist, a sexual predator, and a convicted criminal. He shows just as much cognitive decline as Biden did, but no one on his side asked him to step down because of it. His proposed tariffs would cause massive economic harm for virtually no benefit, and his planned mass deportations are a human rights violation (and also likely an economic disaster). He will most likely implement some variant of Project 2025, which is absolutely full of terrible, dangerous policies. Historians agree he was one of the worst Presidents we’ve ever had.

Indeed, Trump is so terrible that there really can’t be any good reasons to re-elect him. We are left only with bad reasons.

I know of two, and both of them are horrifying.


The first is that Kamala Harris is a woman of color, and a lot of Americans just weren’t willing to put a woman of color in charge. Indeed, sexism seems to be a stronger effect here than racism, because Barack Obama made it but Hillary Clinton didn’t.

The second is that Trump and other Republicans successfully created a whole propaganda system that allows them to indoctrinate millions of people with disinformation. Part of their strategy involves systematically discrediting all mainstream sources, from journalists to scientists, so that they can replace the truth with whatever lies they want.

It was this disinformation that convinced millions of Americans that the economy was in shambles when it was doing remarkably well, convinced them that crime is rising when it is actually falling, convinced them that illegal immigrants were eating people’s pets. Once Republicans had successfully made people doubt all mainstream sources, they could simply substitute whatever beliefs were most convenient for their goals.

Democrats and Republicans are no longer operating with the same set of facts. I’m not claiming that Democrats are completely without bias, but there is a very clear difference: When scientists and journalists report that a widely-held belief by Democrats is false, most Democrats change their beliefs. When the same happens to Republicans, they just become further convinced that scientists and journalists are liars.

What happens now?

In the worst-case scenario, Trump will successfully surround himself with enough sycophants to undermine the checks and balances in our government and actually become an authoritarian dictator. I still believe that this is unlikely, but I can’t rule it out. I am certain that he would want to do this if he thought he could pull it off. (His own chief of staff has said so!)

Even if that worst-case doesn’t come to pass, things will still be very bad for millions of people. Immigrants will be forcibly removed from their homes. Trans people will face even more discrimination. Abortion may be banned nationwide. We may withdraw our support from Ukraine, and that may allow Russia to win the war. Environmental regulations will be repealed. Much or all of our recent progress at fighting climate change could be reversed. Voter suppression efforts will intensify. Yet more far-right judges will be appointed, and they will make far-right rulings. And tax cuts on the rich will make our already staggering, unsustainable inequality even worse.

Indeed, it’s not clear that this will be good even for the people who voted for Trump. (Of course it will be good for Trump himself and his closest lackeys.) The people who voted based on a conviction that the economy was bad won’t see the economy improve. The people who felt ignored by the Democrats will continue to be even more ignored by the Republicans. The people who were tired of identity politics aren’t going to make us care any less about racism and sexism by electing a racist misogynist. The working-class people who were voting against “liberal elites” will see their taxes raised and their groceries more expensive and their wages reduced.

I guess if people really hate immigrants and want them gone, they may get their wish when millions of immigrants are taken from their homes. And the rich will be largely insulated from the harms, while getting those tax cuts they love so much. So that’s some kind of benefit at least.

But mostly, this was an awful outcome, and the next four years will be progressively more and more awful, until hopefully—hopefully—Trump leaves office and we get another chance at something better. That is, if he hasn’t taken over and become a dictator by then.

What can we do to make things less bad?

I’m seeing a lot of people talking about grassroots organizing and mutual aid. I think these are good things, but honestly I fear they just aren’t going to be enough. The United States government is the most powerful institution in the world, and we have just handed control of it over to a madman.

Maybe we will need to organize mass protests. Maybe we will need to take some kind of radical direct action. I don’t know what to do. This all just feels so overwhelming.

I don’t want to give in to despair. I want to believe that we can still make things better. But right now, things feel awfully bleak.

Please, don’t let Trump win this

Oct 20 JDN 2460604

It’s almost time for the Presidential election in the United States. Right now, the race is too close to call; as of writing this post, FiveThirtyEight gives Harris a 53% chance of winning, and Trump a 46% chance.

It should not be this close. It should never have been this close. We have already seen what Trump is like in office, and it should have made absolutely no one happy. He is authoritarian, corrupt, incompetent, and narcissistic, and lately he’s starting to show signs of cognitive decline. He is a convicted felon and was involved in an attempted insurrection. His heavy-handed trade tariffs would surely cause severe economic damage both here and abroad, and above all, he wants to roll back rights for millions of Americans.

Almost anyone would be better than Trump. Harris would be obviously, dramatically better in almost every way. Yet somehow Trump is still doing well in the polls, and could absolutely still win this.

Please, do everything you can to stop that from happening.

Donate. Volunteer. Get out the vote. And above all, vote.

Part of the problem is our two-party system, which comes ultimately from our plurality voting system. As RangeVoting.org has remarked, our current system is basically the worst possible system that can still be considered democratic. Range voting would be clearly the best system, but failing that, at least we could have approval voting, or some kind of ranked-choice system. Only voting for a single candidate causes huge, fundamental flaws in representation, especially when it comes to candidate cloning: Multiple similar candidates that people like can lose to a single candidate that people dislike, because the vote gets split between them.

In fact, that’s almost certainly what happened with Trump: The only reason he won the primary the first time was that he had a small group of ardent supporters, while all the other candidates were similar and so got the mainstream Republican vote split between them. (Though it looks like the second time around he’d still win even if all the other similar candidates were consolidated—which frankly horrifies me.)

But it isn’t just our voting system. The really terrifying thing about Trump is how popular he is among Republicans. Democrats hate him, but Republicans love him. I have tried talking with Republican family members about what they like about Trump, and they struggle to give me a sensible answer. It’s not his personality or his competence (how could it be?). For the most part, it wasn’t even particular policies he supports. It was just this weird free-floating belief that he was a good President and would be again.

There was one major exception to that: Single-issue voters who want to ban abortion. For these people, the only thing that matters is that Trump appointed the Supreme Court justices who overturned Roe v. Wade. I don’t know what to say to such people, since it seems so obvious to me that (1) a total abortion ban is too extreme, even if you want to reduce the abortion rate, (2) there are so many other issues that matter aside from abortion; you can’t simply ignore them all, (3) several other Republican candidates are equally committed to banning abortion but not nearly as corrupt or incompetent, and (4) the Supreme Court has already been appointed; there’s nothing more for Trump to do in that department that he hasn’t already done. But I guess there is at least something resembling a coherent policy preference here, if a baffling one.

Others also talked about his ideas on trade and immigration, but they didn’t seem to have a coherent idea of what a sensible trade or immigration policy looks like. They imagined that it was a reasonable thing to simply tariff all imports massively or expel all immigrants, despite the former being economically absurd and the latter being a human rights violation (and also an economic disaster). I guess that also counts as a policy preference, but it’s not simply baffling; it’s horrifying. I don’t know what to say to these people either.

But maybe that’s a terror I need to come to terms with: Some people don’t like Trump in spite of his terrible policy ideas; they like him because of them. They want a world where rights are rolled back for minorities and LGBT people and (above all) immigrants. They want a world where global trade is shut down and replaced by autarky. They imagine that these changes will somehow benefit them, even when all the evidence suggests that it would do nothing of the sort.

I have never feared Trump himself nearly so much as I fear the people of a country that could elect him. And should we re-elect him, I will fear the people of this country even more.

Please, don’t let that happen.

Why are groceries so expensive?

Aug 18 JDN 2460541

There has been unusually high inflation the past few years, mostly attributable to the COVID pandemic and its aftermath. But groceries in particular seem to have gotten especially more expensive. We’ve all felt it: Eggs, milk, and toilet paper especially soared to extreme prices and then, even when they came back down, never came down all the way.

Why would this be?

Did it involve supply chain disruptions? Sure. Was it related to the war in Ukraine? Probably.

But it clearly wasn’t just those things—because, as the FTC recently found, grocery stores have been colluding and price-gouging. Large grocery chains like Walmart and Kroger have a lot of market power, and they used that power to raise prices considerably faster than was necessary to keep up with their increased costs; as a result, they made record profits. Their costs did genuinely increase, but they increased their prices even more, and ended up being better off.

The big chains were also better able to protect their own supply chains than smaller companies, and so the effects of the pandemic further entrenched the market power of a handful of corporations. Some of them also imposed strict delivery requirements on their suppliers, pressuring them to prioritize the big companies over the small ones.

This kind of thing is what happens when we let oligopolies take control. When only a few companies control the market, prices go up, quality goes down, and inequality gets worse.

For far too long, institutions like the FTC have failed to challenge the ever tighter concentration of our markets in the hands of a small number of huge corporations.

And it’s not just grocery stores.

Our media is dominated by five corporations: Disney, WarnerMedia, NBCUniversal, Sony, and Paramount.

Our cell phone service is 99% controlled by three corporations: T-Mobile, Verizon, and AT&T.

Our music industry is dominated by three corporations: Sony, Universal, and Warner.

Two-thirds of US airline traffic are in four airlines: American, Delta, Southwest, and United.

Nearly 40% of US commercial banking assets are controlled by just three banks: JPMorgan Chase, Bank of America, and Citigroup.

Do I even need to mention the incredible market share Google has in search—over 90%—or Facebook has in social media—over 50%?

And most of these lists used to be longer. Disney recently acquired 21st Century Fox. Viacom recently merged with CBS and then became Paramount. Universal recently acquired EMI. Our markets aren’t simply alarmingly concentrated; they have also been getting more concentrated over time.

Institutions like the FTC are supposed to be protecting us from oligopolies, by ensuring that corporations can’t merge and acquire each other once they reach a certain market share. But decades of underfunding and laissez-faire ideology have weakened these institutions. So many mergers that obviously shouldn’t have been allowed were allowed, because no regulatory agency had the will and the strength to stop them.

The good news is that this is finally beginning to change: The FTC has recently (finally!) sued Google for maintaining a monopoly on Internet search. And among grocery stores in particular, the FTC is challenging Kroger’s acquisition of Albertson’s—though it remains unclear whether that challenge will succeed.

Hopefully this is a sign that the FTC has found its teeth again, and will continue to prosecute anti-trust cases against oligopolies. A lot of that may depend on who ends up in the White House this November.