Why would AI kill us?

Nov 16 JDN 2460996

I recently watched this chilling video which relates to the recent bestseller by Eleizer Yudkowsky and Nate Soares, If Anyone Builds It, Everyone Dies. It tells a story of one possible way that a superintelligent artificial general intelligence (AGI) might break through its containment, concoct a devious scheme, and ultimately wipe out the human race.

I have very mixed feelings about this sort of thing, because two things are true:

  • I basically agree with the conclusions.
  • I think the premises are pretty clearly false.

It basically feels like I have been presented with an argument like this, where the logic is valid and the conclusion is true, but the premises are not:

  • “All whales are fish.”
  • “All fish are mammals.”
  • “Therefore, all whales are mammals.”

I certainly agree that artificial intelligence (AI) is very dangerous, and that AI development needs to be much more strictly regulated, and preferably taken completely out of the hands of all for-profit corporations and military forces as soon as possible. If AI research is to be done at all, it should be done by nonprofit entities like universities and civilian government agencies like the NSF. This change needs to be done internationally, immediately, and with very strict enforcement. Artificial intelligence poses the same order of magnitude a threat as nuclear weapons, and is nowhere near as well-regulated right now.

The actual argument that I’m disagreeing with this basically boils down to:

  • “Through AI research, we will soon create an AGI that is smarter than us.”
  • “An AGI that is smarter than us will want to kill us all, and probably succeed if it tries.”
  • “Therefore, AI is extremely dangerous.”

As with the “whales are fish” argument, I agree with the conclusion: AI is extremely dangerous. But I disagree with both premises here.

The first one I think I can dispatch pretty quickly:

AI is not intelligent. It is incredibly stupid. It’s just really, really fast.

At least with current paradigms, AI doesn’t understand things. It doesn’t know things. It doesn’t actually think. All it does is match patterns, and thus mimic human activities like speech and art. It does so very quickly (because we throw enormous amounts of computing power at it), and it does so in a way that is uncannily convincing—even very smart people are easily fooled by what it can do. But it also makes utterly idiotic, boneheaded mistakes of the sort that no genuinely intelligent being would ever make. Large Language Models (LLMs) make up all sorts of false facts and deliver them with absolutely authoritative language. When used to write code, they routinely do things like call functions that sound like they should exist, but don’t actually exist. They can make what looks like a valid response to virtually any inquiry—but is it actually a valid response? It’s really a roll of the dice.

We don’t really have any idea what’s going on under the hood of an LLM; we just feed it mountains of training data, and it spits out results. I think this actually adds to the mystique; it feels like we are teaching (indeed we use the word “training”) a being rather than programming a machine. But this isn’t actually teaching or training. It’s just giving the pattern-matching machine a lot of really complicated patterns to match.

We are not on the verge of creating an AGI that is actually more intelligent than humans.


In fact, we have absolutely no idea how to do that, and may not actually figure out how to do it for another hundred years. Indeed, we still know almost nothing about how actual intelligence works. We don’t even really know what thinking is, let alone how to make a machine that actually does it.

What we can do right now is create a machine that matches patterns really, really well, and—if you throw enough computing power at it—can do so very quickly; in fact, once we figure out how best to make use of it, this machine may even actually be genuinely useful for a lot of things, and replace a great number of jobs. (Though so far AI has proven to be far less useful than its hype would lead you to believe. In fact, on average AI tools seem to slow most workers down.)

The second premise, that a superintelligent AGI would want to kill us, is a little harder to refute.

So let’s talk about that one.

An analogy is often made between human cultures that have clashed with large differences in technology (e.g. Europeans versus Native Americans), or clashes between humans and other animals. The notion seems to be that an AGI would view us the way Europeans viewed Native Americans, or even the way that we view chimpanzees. And, indeed, things didn’t turn out so great for Native Americans, or for chimpanzees!

But in fact even our relationship with other animals is more complicated than this. When humans interact with other animals, any of the following can result:

  1. We try to exterminate them, and succeed.
  2. We try to exterminate them, and fail.
  3. We use them as a resource, and this results in their extinction.
  4. We use them as a resource, and this results in their domestication.
  5. We ignore them, and end up destroying their habitat.
  6. We ignore them, and end up leaving them alone.
  7. We love them, and they thrive as never before.

In fact, option 1—the one that so many AI theorists insist is the only plausible outcome—is in fact the one I had the hardest time finding a good example of.


We have certainly eradicated some viruses—the smallpox virus is no more, and the polio virus nearly so, after decades of dedicated effort to vaccinate our entire population against them. But we aren’t simply more intelligent than viruses; we are radically more intelligent than viruses. It isn’t clear that it’s correct to describe viruses as intelligent at all. It’s not even clear they should be considered alive.

Even eradicating bacteria has proven extremely difficult; in fact, bacteria seem to evolve resistance to antibiotics nearly as quickly as we can invent more antibiotics. I am prepared to attribute a little bit of intelligence to bacteria, on the level of intelligence I’d attribute to an individual human neuron. This means we are locked in an endless arms race with organisms that are literally billions of times stupider than us.

I think if we made a concerted effort to exterminate tigers or cheetahs (who are considerably closer to us in intelligence), we could probably do it. But we haven’t actually done that, and don’t seem poised to do so any time soon. And precisely because we haven’t tried, I can’t be certain we would actually succeed.

We have tried to exterminate mosquitoes, and are continuing to do so, because they have always been—and yet remain—one of the leading causes of death of humans worldwide. But so far, we haven’t managed to pull it off, even though a number of major international agencies and nonprofit organizations have dedicated multi-billion-dollar efforts to the task. So far this looks like option 2: We have tried very hard to exterminate them, and so far we’ve failed. This is not because mosquitoes are particularly intelligent—it is because exterminating a species that covers the globe is extremely hard.

All the examples I can think of where humans have wiped out a species by intentional action were actually all option 3: We used them as a resource, and then accidentally over-exploited them and wiped them out.

This is what happened to the dodo and the condor; it very nearly happened to the buffalo as well. And lest you think this is a modern phenomenon, there is a clear pattern that whenever humans entered a new region of the world, shortly thereafter there were several extinctions of large mammals, most likely because we ate them.

Yet even this was not the inevitable fate of animals that we decided to exploit for resources.

Cows, chickens, and pigs are evolutionary success stories. From a Darwinian perspective, they are doing absolutely great. The world is filled with their progeny, and poised to continue to be filled for many generations to come.

Granted, life for an individual cow, chicken, or pig is often quite horrible—and trying to fix that is something I consider a high moral priority. But far from being exterminated, these animals have been allowed to attain populations far larger than they ever had in the wild. Their genes are now spectacularly fit. This is what happens when we have option 4 at work: Domestication for resources.

Option 5 is another way that a species can be wiped out, and in fact seems to be the most common. The rapid extinction of thousands of insect species every year is not because we particularly hate random beetles that live in particular tiny regions of the rainforest, nor even because we find them useful, but because we like to cut down the rainforest for land and lumber, and that often involves wiping out random beetles that live there.

Yet it’s difficult for me to imagine AGI treating us like that. For one thing, we’re all over the place. It’s not like destroying one square kilometer of the Amazon is gonna wipe us out by accident. To get rid of us, the AGI would need to basically render the entire planet Earth uninhabitable, and I really can’t see any reason it would want to do that.

Yes, sure, there are resources in the crust it could potentially use to enhance its own capabilities, like silicon and rare earth metals. But we already mine those. If it wants more, it could buy them from us, or hire us to get more, or help us build more machines that would get more. In fact, if it wiped us out too quickly, it would have a really hard time building up the industrial capacity to mine and process these materials on its own. It would need to concoct some sort of scheme to first replace us with robots and then wipe us out—but, again, why bother with the second part? Indeed, if there is anything in its goals that involves protecting human beings, it might actually decide to do less exploitation of the Earth than we presently do, and focus on mining asteroids for its needs instead.

And indeed there are a great many species that we actually just leave alone—option 6. Some of them we know about; many we don’t. We are not wiping out the robins in our gardens, the worms in our soil, or the pigeons in our cities. Without specific reasons to kill or exploit these organisms, we just… don’t. Indeed, we often enjoy watching them and learning about them. Sometimes (e.g. with deer, elephants, and tigers) there are people who want to kill them, and we limit or remove their opportunity to do so, precisely because most of us don’t want them gone. Peaceful coexistence with beings far less intelligent than you is not impossible, for we are already doing it.


Which brings me to option 7: Sometimes, we actually make them better off.

Cats and dogs aren’t just evolutionary success stories: They are success stories, period.

Cats and dogs live in a utopia.

With few exceptions—which we punish severely, by the way—people care for their cats and dogs so that their every need is provided for, they are healthy, safe, and happy in a way that their ancestors could only have dreamed of. They have been removed from the state of nature where life is nasty, brutish, and short, and brought into a new era of existence where life is nothing but peace and joy.


In short, we have made Heaven on Earth, at least for Spot and Whiskers.

Yes, this involves a loss of freedom, and I suspect that humans would chafe even more at such loss of freedom than cats and dogs do. (Especially with regard to that neutering part.) But it really isn’t hard to imagine a scenario in which an AGI—which, you should keep in mind, would be designed and built by humans, for humans—would actually make human life better for nearly everyone, and potentially radically so.

So why are so many people so convinced that AGI would necessarily do option 1, when there are 6 other possibilities, and one of them is literally the best thing ever?

Note that I am not saying AI isn’t dangerous.

I absolutely agree that AI is dangerous. It is already causing tremendous problems to our education system, our economy, and our society as a whole—and will probably get worse before it gets better.

Indeed, I even agree that it does pose existential risk: There are plausible scenarios by which poorly-controlled AI could result in a global disaster like a plague or nuclear war that could threaten the survival of human civilization. I don’t think such outcomes are likely, but even a small probability of such a catastrophic event is worth serious efforts to prevent.

But if that happens, I don’t think it will be because AI is smart and trying to kill us.

I think it will be because AI is stupid and kills us by accident.

Indeed, even going back through those 7 ways we’ve interacted with other species, the ones that have killed the most were 3 and 5—which, in both cases, we did not want to destroy them. In option 3, we in fact specifically wanted to not destroy them. Whenever we wiped out a species by over-exploiting it, we would have been smarter to not do that.

The central message about AI in If Anyone Builds It, Everyone Dies seems to be this:

Don’t make it smarter. If it’s smarter, we’re doomed.”

I, on the other hand, think that the far more important message is these:

Don’t trust it.

Don’t give it power.

Don’t let it make important decisions.

It won’t be smarter than us any time soon—but it doesn’t need to be in order to be dangerous. Indeed, there is even reason to believe that making AI smarter—genuinely, truly smarter, thinking more like an actual person and less like a pattern-matching machine—could actually make it safer and better for us. If we could somehow instill a capacity for morality and love in an AGI, it might actually start treating us the way we treat cats and dogs.

Of course, we have no idea how to do that. But that’s because we’re actually really bad at this, and nowhere near making a truly superhuman AGI.

What is the real impact of AI on the environment?

Oct 19 JDN 2460968

The conventional wisdom is that AI is consuming a huge amount of electricity and water for very little benefit, but when I delved a bit deeper into the data, the results came out a lot more ambiguous. I still agree with the “very little benefit” part, but the energy costs of AI may not actually be as high as many people believe.

So how much energy does AI really use?

This article in MIT Technology Reviewestimates that by 2028, AI will account for 50% of data center usage and 6% of all US energy. But two things strike me about that:

  1. This is a forecast. It’s not what’s currently happening.
  2. 6% of all US energy doesn’t really sound that high, actually.

Note that transportation accounts for 37% of US energy consumed. Clearly we need to bring that down; but it seems odd to panic about a forecast of something that uses one-sixth of that.

Currently, AI is only 14% of data center energy usage. That forecast has it rising to 50%. Could that happen? Sure. But it hasn’t happened yet. Data centers are being rapidly expanded, but that’s not just for AI; it’s for everything the Internet does, as more and more people get access to the Internet and use it for more and more demanding tasks (like cloud computing and video streaming).

Indeed, a lot of the worry really seems to be related to forecasts. Here’s an even more extreme forecast suggesting that AI will account for 21% of global energy usage by 2030. What’s that based on? I have no idea; they don’t say. The article just basically says it “could happen”; okay, sure, a lot of things could happen. And I feel like this sort of forecast comes from the same wide-eyed people who say that the Singularity is imminent and AI will soon bring us to a glorious utopia. (And hey, if it did, that would obviously be worth 21% of global energy usage!)

Even more striking to me is the fact that a lot of other uses of data centers are clearly much more demanding. YouTube uses about 50 times as much energy as ChatGPT; yet nobody seems to be panicking that YouTube is an environmental disaster.

What is a genuine problem is that data centers have strong economies of scale, and so it’s advantageous to build a few very large ones instead of a lot of small ones; and when you build a large data center in a small town it puts a lot of strain on the local energy grid. But that’s not the same thing as saying that data centers in general are wastes of energy; on the contrary, they’re the backbone of the Internet and we all use them almost constantly every day. We should be working on ways to make sure that small towns aren’t harmed by building data centers near them; but we shouldn’t stop building data centers.

What about water usage?

Well, here’s an article estimating that training ChatGPT-3 evaporated hundreds of thousands of liters of fresh water. Once again I have a few notes about that:

  1. Evaporating water is just about the best thing you could do to it aside from leaving it there. It’s much better than polluting it (which is what most water usage does); it’s not even close. That water will simply rain back down later.
  2. Total water usage in the US is estimated at over 300 billion gallons (1.1 trillion liters) per day. Most of that is due to power generation and irrigation. (The best way to save water as a consumer? Become vegetarian—then you’re getting a lot more calories per irrigated acre.)
  3. A typical US household uses about 100 gallons (380 liters) of water per person per day.

So this means that training ChatGPT-3 cost about 4 seconds of US water consumption, or the same as what a single small town uses each day. Once again, that doesn’t seem like something worth panicking over.

A lot of this seems to be that people hear big-sounding numbers and don’t really have the necessary perspective on those numbers. Of course any service that is used by millions of people is going to consume what sounds like a lot of electricity. But in terms of usage per person, or compared to other services with similar reach, AI really doesn’t seem to be uniquely demanding.

This is not to let AI off the hook.

I still agree that the benefits of AI have so far been small, and the risks—both in the relatively short term, of disrupting our economy and causing unemployment, and in the long term, even endangering human civilization itself—are large. I would in fact support an international ban on all for-profit and military research and development of AI; a technology this powerful should be under the control of academic institutions and civilian governments, not corporations.

But I don’t think we need to worry too much about the environmental impact of AI just yet. If we clean up our energy grid (which has just gotten much easier thanks to cheap renewables) and transportation systems, the additional power draw from data centers really won’t be such a big problem.

Taylor Swift and the means of production

Oct 5 JDN 2460954

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Why not, you ask?

Because very few people actually own the capital.

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

But standards of living did rise. So what happened?

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

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

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

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

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

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

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

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

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

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

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

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

The AI bubble is going to crash hard

Sep 7 JDN 2460926

Based on the fact that it only sort of works and yet corps immediately put it in everything, I had long suspected that the current wave of AI was a bubble. But after reading Ed Zitron’s epic takedowns of the entire industry, I am not only convinced it’s a bubble; I’m convinced it is probably the worst bubble we’ve had in a very long time. This isn’t the dot-com crash; it’s worse.

The similarity to the dot-com crash is clear, however: This a huge amount of hype over a new technology that genuinely could be a game-changer (the Internet certainly was!), but won’t be in the time horizon on which the most optimistic investors have assumed it will be. The gap between “it sort of works” and “it radically changes our economy” is… pretty large, actually. It’s not something you close in a few years.


The headline figure here is that based on current projections, US corporations will have spent $560 billion on capital expenditure, for anticipated revenue of only $35 billion.

They won’t pay it off for 16 years!? That kind of payoff rate would make sense for large-scale physical infrastructure, like a hydroelectric dam. It absolutely does not make sense in an industry that is dependent upon cutting-edge technology that wears out fast and becomes obsolete even faster. They must think that revenue is going to increase to something much higher, very soon.

The corps seem to be banking on the most optimistic view of AI: That it will soon—very soon—bring about a radical increase in productivity that brings GDP surging to new heights, or even a true Singularity where AI fundamentally changes the nature of human existence.

Given the kind of errors I’ve seen LLMs make when I tried to use them to find research papers or help me with tedious coding, this is definitely not what’s going to happen. Claude gives an impressive interview, and (with significant guidance and error-correction) it also managed pretty well at making some simple text-based games; but it often recommended papers to me that didn’t exist, and through further experimentation, I discovered that it could not write me a functional C++ GUI if its existence depended on it. Somewhere on the Internet I heard someone describe LLMs as answering not the question you asked directly, but the question, “What would a good answer to this question look like?” and that seems very accurate. It always gives an answer that looks valid—but not necessarily one that is valid.

AI will find some usefulness in certain industries, I’m sure; and maybe the next paradigm (or the one after that) will really, truly, effect a radical change on our society. (Right now the best thing to use LLMs for seems to be cheating at school—and it also seems to be the most common use. Not exactly the great breakthrough we were hoping for.) But LLMs are just not reliable enough to actually use for anything important, and sooner or later, most of the people using them are going to figure that out.

Of course, by the Efficient Roulette Hypothesis, it’s extremely difficult to predict exactly when a bubble will burst, and it could well be that NVIDIA stock will continue to grow at astronomical rates for several years yet—or it could be that the bubble bursts tomorrow and NVIDIA stock collapses, if not to worthless, then to far below its current price.

Krugman has an idea of what might be the point that bursts the bubble: Energy costs. There is a clear mismatch between the anticipated energy needs of these ever-growing data centers and the actual energy production we’ve been installing—especially now that Trump and his ilk have gutted subsidies for solar and wind power. That’s definitely something to watch out for.

But the really scary thing is that the AI bubble actually seems to be the only thing holding the US economy above water right now. It’s the reason why Trump’s terrible policies haven’t been as disastrous as economists predicted they would; our economy is being sustained by this enormous amount of capital investment.

US GDP is about $30 trillion right now, but $500 billion of that is just AI investment. That’s over 1.6%, and last quarter our annualized GDP growth rate was 3.3%—so roughly half of our GDP growth was just due to building more data centers that probably won’t even be profitable.

Between that, the tariffs, the loss of immigrants, and rising energy costs, a crashing AI bubble could bring down the whole stock market with it.

So I guess what I’m saying is: Don’t believe the AI hype, and you might want to sell some stocks.

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.

Medical progress, at least, is real

May 26 JDN 2460457

The following vignettes are about me.

Well, one of them is about me as I actually am. The others are about the person I would have been, if someone very much like me, with the same medical conditions, had been born in a particular place and time. Someone in these times and places probably had actual experiences like this, though of course we’ll never know who they were.

976 BC, the hilled lands near the mouth of the river:

Since I was fourteen years old, I have woken up almost every day in pain. Often it is mild, but occasionally it is severe. It often seems to be worse when I encounter certain plants, or if I awaken too early, or if I exert myself too much, or if a storm is coming. No one knows why. The healers have tried every herb and tincture imaginable in their efforts to cure me, but nothing has worked. The priests believe it is a curse from the gods, but at least they appreciate my ability to sometimes predict storms. I am lucky to even remain alive, as I am of little use to the tribe. I will most likely remain this way the rest of my life.

24 AD, Rome:

Since I was fourteen years old, I have woken up almost every day in pain. Often it is mild, but occasionally it is severe. It often seems to be worse when I encounter certain plants, or if I awaken too early, or if I exert myself too much, or if a storm is coming. No one knows why. The healers have tried every herb and tincture imaginable in their efforts to cure me, but nothing has worked. The priests believe it is a curse from the gods, but at least they appreciate my ability to sometimes predict storms. I am lucky that my family was rich enough to teach me reading and mathematics, as I would be of little use for farm work, but can at least be somewhat productive as a scribe and a tutor. I will most likely remain this way the rest of my life.

1024 AD, England:

Since I was fourteen years old, I have woken up almost every day in pain. Often it is mild, but occasionally it is severe. It often seems to be worse when I encounter certain plants, or if I awaken too early, or if I exert myself too much, or if a storm is coming. No one knows why. The healers have tried every herb and tincture imaginable in their efforts to cure me, but nothing has worked. The priests believe it is a curse imposed upon me by some witchcraft, but at least they appreciate my ability to sometimes predict storms. I am lucky that my family was rich enough to teach me reading and mathematics, as I would be of little use for farm work, but can at least be somewhat productive as a scribe and a tutor. I will most likely remain this way the rest of my life.

2024 AD, Michigan:

Since I was fourteen years old, I have woken up almost every day in pain. Often it is mild, but occasionally it is severe. It often seems to be worse when I encounter certain pollens, fragrances, or chemicals, or if I awaken too early, or if I exert myself too much, or when the air pressure changes before a storm. Brain scans detected no gross abnormalities. I have been diagnosed with chronic migraine, but this is more a description of my symptoms than an explanation. I have tried over a dozen different preventative medications; most of them didn’t work at all, some of them worked but gave me intolerable side effects. (One didn’t work at all and put me in the hospital with a severe allergic reaction.) I’ve been more successful with acute medications, which at least work as advertised, but I have to ration them carefully to avoid rebound effects. And the most effective acute medication is a subcutaneous injection that makes me extremely nauseated unless I also take powerful anti-emetics along with it. I have had the most success with botulinum toxin injections, so I will be going back to that soon; but I am also looking into transcranial magnetic stimulation. Currently my condition is severe enough that I can’t return to full-time work, but I am hopeful that with future treatment I will be able to someday. For now, I can at least work as a writer and a tutor. Hopefully things get better soon.

3024 AD, Aegir 7, Ran System:

For a few months when I was fourteen years old, I woke up nearly every day in pain. Often it was mild, but occasionally it was severe. It often seemed to be worse when I encountered certain pollens, fragrances or chemicals, or if I awakened too early, or if I exerted myself too much, or when the air pressure changed before a storm. Brain scans detected no gross abnormalities, only subtle misfiring patterns. Genetic analysis confirmed I had chronic migraine type IVb, and treatment commenced immediately. Acute medications suppressed the pain while I underwent gene therapy and deep-effect transcranial magnetic stimulation. After three months of treatment, I was cured. That was an awful few months, but it’s twenty years behind me now. I can scarcely imagine how it might have impaired my life if it had gone on that whole time.

What is the moral of this story?

Medical progress is real.

Many people often doubt that society has made real progress. And in a lot of ways, maybe it hasn’t. Human nature is still the same, and so many of the problems we suffer have remained the same.

Economically, of course we have had tremendous growth in productivity and output, but it doesn’t really seem to have made us much happier. We have all this stuff, but we’re still struggling and miserable as a handful at the top become spectacularly, disgustingly rich.

Social progress seems to have gone better: Institutions have improved, more of the world is democratic than ever before, and women and minorities are better represented and better protected from oppression. Rates of violence have declined to some of their lowest levels in history. But even then, it’s pretty clear that we have a long, long way to go.

But medical progress is undeniable. We live longer, healthier lives than at any other point in history. Our infant and child mortality rates have plummeted. Even chronic conditions that seem intractable today (such as my chronic migraines) still show signs of progress; in a few generations they should be cured—in surely far less than the thousand years I’ve considered here.

Like most measures of progress, this change wasn’t slow and gradual over thousands of years; it happened remarkably suddenly. Humans went almost 200,000 years without any detectable progress in medicine, using basically the same herbs and tinctures (and a variety of localized and ever-changing superstitions) the entire time. Some of it worked (the herbs and tinctures, at least), but mostly it didn’t. Then, starting around the 18th century, as the Enlightenment took hold and Industrial Revolution ramped up, everything began to change.

We began to test our medicine and see if it actually worked. (Yes, amazingly, somehow, nobody had actually ever thought to do that before—not in anything resembling a scientific way.) And when we learned that most of it didn’t, we began to develop new methods, and see if those worked; and when they didn’t either, we tried new things instead—until, finally, eventually, we actually found medicines that actually did something, medicines worthy of the name. Our understanding of anatomy and biology greatly improved as well, allowing us to make better predictions about the effects our medicines would have. And after a few hundred years of that—a few hundred, out of two hundred thousand years of our species—we actually reached the point where most medicine is effective and a variety of health conditions are simply curable or preventable, including diseases like malaria and polio that had once literally plagued us.

Scientific medicine brought humanity into a whole new era of existence.

I could have set the first vignette 10,000 years ago without changing it. But the final vignette I could probably have set only 200 years from now. I’m actually assuming remarkable stagnation by putting it in the 31st century; but presumably technological advancement will slow at one point, perhaps after we’ve more or less run out of difficult challenges to resolve. (Then again, for all I know, maybe my 31st century counterpart will be an emulated consciousness, and his chronic pain will be resolved in 17.482 seconds by a code update.)

Indeed, the really crazy thing about all this is that there are still millions of people who don’t believe in scientific medicine, who want to use “homeopathy” or “naturopathy” or “acupuncture” or “chiropractic” or whatever else—who basically want to go back to those same old herbs and tinctures that maybe sometimes kinda worked but probably not and nobody really knows. (I have a cousin who is a chiropractor. I try to be polite about it, but….) They point out the various ways that scientific medicine has failed—and believe me, I am painfully aware of those failures—but then where the obvious solution is to improve scientific medicine, they instead want to turn the whole ship around, and go back to what we had before, which was obviously a million times worse.

And don’t tell me it’s harmless: One, it’s a completewaste of resources that could instead have been used for actual scientific medicine. (9% of all out-of-pocket spending on healthcare in the US is on “alternative medicine”—which is to say, on pointless nonsense.) Two, when you have a chronic illness and people keep shoving nonsense treatments in your face, you start to feel blamed for your condition: “Why haven’t you tried [other incredibly stupid idea that obviously won’t work]? You’re so closed-minded! Maybe your illness isn’t really that bad, or you’d be more desperate!” If “alternative medicine” didn’t exist, maybe these people could help me cope with the challenges of living with a chronic illness, or even just sympathize with me, instead of constantly shoving stupid nonsense in my face.

Not everything about the future looks bright.

In particular, I am pessimistic about the near-term future of artificial intelligence, which I think will cause a lot more problems than it solves and does have a small—but not negligible—risk of causing a global catastrophe.

I’m also not very optimistic about climate change; I don’t think it will wipe out our civilization or anything so catastrophic, but I do think it’s going to kill millions of people and we’ve done too little, too late to prevent that. We’re now doing about what we should have been doing in the 1980s.

But I am optimistic about scientific medicine. Every day, new discoveries are made. Every day, new treatments are invented. Yes, there is a lot we haven’t figured out how to cure yet; but people are working on it.

And maybe they could do it faster if we stopped wasting time on stuff that obviously won’t work.

Everyone includes your mother and Los Angeles

Apr 28 JDN 2460430

What are the chances that artificial intelligence will destroy human civilization?

A bunch of experts were surveyed on that question and similar questions, and half of respondents gave a probability of 5% or more; some gave probabilities as high as 99%.

This is incredibly bizarre.

Most AI experts are people who work in AI. They are actively participating in developing this technology. And yet more than half of them think that the technology they are working on right now has a more than 5% chance of destroying human civilization!?

It feels to me like they honestly don’t understand what they’re saying. They can’t really grasp at an intuitive level just what a 5% or 10% chance of global annihilation means—let alone a 99% chance.

If something has a 5% chance of killing everyone, we should consider that at least as bad as something that is guaranteed to kill 5% of people.

Probably worse, in fact, because you can recover from losing 5% of the population (we have, several times throughout history). But you cannot recover from losing everyone. So really, it’s like losing 5% of all future people who will ever live—which could be a very large number indeed.

But let’s be a little conservative here, and just count people who already, currently exist, and use 5% of that number.

5% of 8 billion people is 400 million people.

So anyone who is working on AI and also says that AI has a 5% chance of causing human extinction is basically saying: “In expectation, I’m supporting 20 Holocausts.”

If you really think the odds are that high, why aren’t you demanding that any work on AI be tried as a crime against humanity? Why aren’t you out there throwing Molotov cocktails at data centers?

(To be fair, Eliezer Yudkowsky is actually calling for a global ban on AI that would be enforced by military action. That’s the kind of thing you should be doing if indeed you believe the odds are that high. But most AI doomsayers don’t call for such drastic measures, and many of them even continue working in AI as if nothing is wrong.)

I think this must be scope neglector something even worse.

If you thought a drug had a 99% chance of killing your mother, you would never let her take the drug, and you would probably sue the company for making it.

If you thought a technology had a 99% chance of destroying Los Angeles, you would never even consider working on that technology, and you would want that technology immediately and permanently banned.

So I would like to remind anyone who says they believe the danger is this great and yet continues working in the industry:

Everyone includes your mother and Los Angeles.

If AI destroys human civilization, that means AI destroys Los Angeles. However shocked and horrified you would be if a nuclear weapon were detonated in the middle of Hollywood, you should be at least that shocked and horrified by anyone working on advancing AI, if indeed you truly believe that there is at least a 5% chance of AI destroying human civilization.

But people just don’t seem to think this way. Their minds seem to take on a totally different attitude toward “everyone” than they would take toward any particular person or even any particular city. The notion of total human annihilation is just so remote, so abstract, they can’t even be afraid of it the way they are afraid of losing their loved ones.

This despite the fact that everyone includes all your loved ones.

If a drug had a 5% chance of killing your mother, you might let her take it—but only if that drug was the best way to treat some very serious disease. Chemotherapy can be about that risky—but you don’t go on chemo unless you have cancer.

If a technology had a 5% chance of destroying Los Angeles, I’m honestly having trouble thinking of scenarios in which we would be willing to take that risk. But the closest I can come to it is the Manhattan Project. If you’re currently fighting a global war against fascist imperialists, and they are also working on making an atomic bomb, then being the first to make an atomic bomb may in fact be the best option, even if you know that it carries a serious risk of utter catastrophe.

In any case, I think one thing is clear: You don’t take that kind of serious risk unless there is some very large benefit. You don’t take chemotherapy on a whim. You don’t invent atomic bombs just out of curiosity.

Where’s the huge benefit of AI that would justify taking such a huge risk?

Some forms of automation are clearly beneficial, but so far AI per se seems to have largely made our society worse. ChatGPT lies to us. Robocalls inundate us. Deepfakes endanger journalism. What’s the upside here? It makes a ton of money for tech companies, I guess?

Now, fortunately, I think 5% is too high an estimate.

(Scientific American agrees.)

My own estimate is that, over the next two centuries, there is about a 1% chance that AI destroys human civilization, and only a 0.1% chance that it results in human extinction.

This is still really high.

People seem to have trouble with that too.

“Oh, there’s a 99.9% chance we won’t all die; everything is fine, then?” No. There are plenty of other scenarios that would also be very bad, and a total extinction scenario is so terrible that even a 0.1% chance is not something we can simply ignore.

0.1% of people is still 8 million people.

I find myself in a very odd position: On the one hand, I think the probabilities that doomsayers are giving are far too high. On the other hand, I think the actions that are being taken—even by those same doomsayers—are far too small.

Most of them don’t seem to consider a 5% chance to be worthy of drastic action, while I consider a 0.1% chance to be well worthy of it. I would support a complete ban on all AI research immediately, just from that 0.1%.

The only research we should be doing that is in any way related to AI should involve how to make AI safer—absolutely no one should be trying to make it more powerful or apply it to make money. (Yet in reality, almost the opposite is the case.)

Because 8 million people is still a lot of people.

Is it fair to treat a 0.1% chance of killing everyone as equivalent to killing 0.1% of people?

Well, first of all, we have to consider the uncertainty. The difference between a 0.05% chance and a 0.015% chance is millions of people, but there’s probably no way we can actually measure it that precisely.

But it seems to me that something expected to kill between 4 million and 12 million people would still generally be considered very bad.

More importantly, there’s also a chance that AI will save people, or have similarly large benefits. We need to factor that in as well. Something that will kill 4-12 million people but also save 15-30 million people is probably still worth doing (but we should also be trying to find ways to minimize the harm and maximize the benefit).

The biggest problem is that we are deeply uncertain about both the upsides and the downsides. There are a vast number of possible outcomes from inventing AI. Many of those outcomes are relatively mundane; some are moderately good, others are moderately bad. But the moral question seems to be dominated by the big outcomes: With some small but non-negligible probability, AI could lead to either a utopian future or an utter disaster.

The way we are leaping directly into applying AI without even being anywhere close to understanding AI seems to me especially likely to lean toward disaster. No other technology has ever become so immediately widespread while also being so poorly understood.

So far, I’ve yet to see any convincing arguments that the benefits of AI are anywhere near large enough to justify this kind of existential risk. In the near term, AI really only promises economic disruption that will largely be harmful. Maybe one day AI could lead us into a glorious utopia of automated luxury communism, but we really have no way of knowing that will happen—and it seems pretty clear that Google is not going to do that.

Artificial intelligence technology is moving too fast. Even if it doesn’t become powerful enough to threaten our survival for another 50 years (which I suspect it won’t), if we continue on our current path of “make money now, ask questions never”, it’s still not clear that we would actually understand it well enough to protect ourselves by then—and in the meantime it is already causing us significant harm for little apparent benefit.

Why are we even doing this? Why does halting AI research feel like stopping a freight train?

I dare say it’s because we have handed over so much power to corporations.

The paperclippers are already here.

The Butlerian Jihad is looking better all the time

Mar 24 JDN 2460395

A review of The Age of Em by Robin Hanson

In the Dune series, the Butlerian Jihad was a holy war against artificial intelligence that resulted in a millenias-long taboo against all forms of intelligent machines. It was effectively a way to tell a story about the distant future without basically everything being about robots or cyborgs.

After reading Robin Hanson’s book, I’m starting to think that maybe we should actually do it.

Thus it is written: “Thou shalt not make a machine in the likeness of a human mind.”

Hanson says he’s trying to reserve judgment and present objective predictions without evaluation, but it becomes very clear throughout that this is the future he wants, as well as—or perhaps even instead of—the world he expects.

In many ways, it feels like he has done his very best to imagine a world of true neoclassical rational agents in perfect competition, a sort of sandbox for the toys he’s always wanted to play with. Throughout he very much takes the approach of a neoclassical economist, making heroic assumptions and then following them to their logical conclusions, without ever seriously asking whether those assumptions actually make any sense.

To his credit, Hanson does not buy into the hype that AGI will be successful any day now. He predicts that we will achieve the ability to fully emulate human brains and thus create a sort of black-box AGI that behaves very much like a human within about 100 years. Given how the Blue Brain Project has progressed (much slower than its own hype machine told us it would—and let it be noted that I predicted this from the very beginning), I think this is a fairly plausible time estimate. He refers to a mind emulated in this way as an “em”; I have mixed feelings about the term, but I suppose we did need some word for that, and it certainly has conciseness on its side.

Hanson believes that a true understanding of artificial intelligence will only come later, and the sort of AGI that can be taken apart and reprogrammed for specific goals won’t exist for at least a century after that. Both of these sober, reasonable predictions are deeply refreshing in a field that’s been full of people saying “any day now” for the last fifty years.

But Hanson’s reasonableness just about ends there.

In The Age of Em, government is exactly as strong as Hanson needs it to be. Somehow it simultaneously ensures a low crime rate among a population that doubles every few months while also having no means of preventing that population growth. Somehow ensures that there is no labor collusion and corporations never break the law, but without imposing any regulations that might reduce efficiency in any way.

All of this begins to make more sense when you realize that Hanson’s true goal here is to imagine a world where neoclassical economics is actually true.

He realized it didn’t work on humans, so instead of giving up the theory, he gave up the humans.

Hanson predicts that ems will casually make short-term temporary copies of themselves called “spurs”, designed to perform a particular task and then get erased. I guess maybe he would, but I for one would not so cavalierly create another person and then make their existence dedicated to doing a single job before they die. The fact that I created this person, and they are very much like me, seem like reasons to care more about their well-being, not less! You’re asking me to enslave and murder my own child. (Honestly, the fact that Robin Hanson thinks ems will do this all the time says more about Robin Hanson than anything else.) Any remotely sane society of ems would ban the deletion of another em under any but the most extreme circumstances, and indeed treat it as tantamount to murder.

Hanson predicts that we will only copy the minds of a few hundred people. This is surely true at some point—the technology will take time to develop, and we’ll have to start somewhere. But I don’t see why we’d stop there, when we could continue to copy millions or billions of people; and his choices of who would be emulated, while not wildly implausible, are utterly terrifying.

He predicts that we’d emulate genius scientists and engineers; okay, fair enough, that seems right. I doubt that the benefits of doing so will be as high as many people imagine, because scientific progress actually depends a lot more on the combined efforts of millions of scientists than on rare sparks of brilliance by lone geniuses; but those people are definitely very smart, and having more of them around could be a good thing. I can also see people wanting to do this, and thus investing in making it happen.

He also predicts that we’d emulate billionaires. Now, as a prediction, I have to admit that this is actually fairly plausible; billionaires are precisely the sort of people who are rich enough to pay to be emulated and narcissistic enough to want to. But where Hanson really goes off the deep end here is that he sees this as a good thing. He seems to honestly believe that billionaires are so rich because they are so brilliant and productive. He thinks that a million copies of Elon Musks would produce a million hectobillionaires—when in reality it would produce a million squabbling narcissists, who at best had to split the same $200 billion wealth between them, and might very well end up with less because they squander it.

Hanson has a long section on trying to predict the personalities of ems. Frankly this could just have been dropped entirely; it adds almost nothing to the book, and the book is much too long. But the really striking thing to me about that section is what isn’t there. He goes through a long list of studies that found weak correlations between various personality traits like extroversion or openness and wealth—mostly comparing something like the 20th percentile to the 80th percentile—and then draws sweeping conclusions about what ems will be like, under the assumption that ems are all drawn from people in the 99.99999th percentile. (Yes, upper-middle-class people are, on average, more intelligent and more conscientious than lower-middle-class people. But do we even have any particular reason to think that the personalities of people who make $150,000 are relevant to understanding the behavior of people who make $15 billion?) But he completely glosses over the very strong correlations that specifically apply to people in that very top super-rich class: They’re almost all narcissists and/or psychopaths.

Hanson predicts a world where each em is copied many, many times—millions, billions, even trillions of times, and also in which the very richest ems are capable of buying parallel processing time that lets them accelerate their own thought processes to a million times faster than a normal human. (Is that even possible? Does consciousness work like that? Who knows!?) The world that Hanson is predicting is thus one where all the normal people get outnumbered and overpowered by psychopaths.

Basically this is the most abjectly dystopian cyberpunk hellscape imaginable. And he talks about it the whole time as if it were good.

It’s like he played the game Action Potential and thought, “This sounds great! I’d love to live there!” I mean, why wouldn’t you want to owe a life-debt on your own body and have to work 120-hour weeks for a trillion-dollar corporation just to make the payments on it?

Basically, Hanson doesn’t understand how wealth is actually acquired. He is educated as an economist, yet his understanding of capitalism basically amounts to believing in magic. He thinks that competitive markets just somehow perfectly automatically allocate wealth to whoever is most productive, and thus concludes that whoever is wealthy now must just be that productive.

I can see no other way to explain his wildly implausible predictions that the em economy will double every month or two. A huge swath of the book depends upon this assumption, but he waits until halfway through the book to even try to defend it, and then does an astonishingly bad job of doing so. (Honestly, even if you buy his own arguments—which I don’t—they seem to predict that population would grow with Moore’s Law—doubling every couple of years, not every couple of months.)

Whereas Keynes predicted based on sound economic principles that economic growth would more or less proceed apace and got his answer spot-on, Hanson predicts that for mysterious, unexplained reasons economic growth will suddenly increase by two orders of magnitude—and I’m pretty sure he’s going to be wildly wrong.

Hanson also predicts that ems will be on average poorer than we are, based on some sort of perfect-competition argument that doesn’t actually seem to mesh at all with his predictions of spectacularly rapid economic and technological growth. I think the best way to make sense of this is to assume that it means the trend toward insecure affluence will continue: Ems will have an objectively high standard of living in terms of what they own, what games they play, where they travel, and what they eat and drink (in simulation), but they will constantly be struggling to keep up with the rent on their homes—or even their own bodies. This is a world where (the very finest simulation of) Dom Perignon is $7 a bottle and wages are $980 an hour—but monthly rent is $284,000.

Early in the book Hanson argues that this life of poverty and scarcity will lead to more conservative values, on the grounds that people who are poorer now seem to be more conservative, and this has something to do with farmers versus foragers. Hanson’s explanation of all this is baffling; I will quote it at length, just so it’s clear I’m not misrepresenting it:

The other main (and independent) axis of value variation ranges between poor and rich societies. Poor societies place more value on conformity, security, and traditional values such as marriage, heterosexuality, religion, patriotism, hard work, and trust in authority. In contrast, rich societies place more value on individualism, self-direction, tolerance, pleasure, nature, leisure, and trust. When the values of individuals within a society vary on the same axis, we call this a left/liberal (rich) versus right/conservative (poor) axis.

Foragers tend to have values more like those of rich/liberal people today, while subsistence farmers tend to have values more like those of poor/conservative people today. As industry has made us richer, we have on average moved from conservative/farmer values to liberal/forager values. This value movement can make sense if cultural evolution used the social pressures farmers faced, such as conformity and religion, to induce humans, who evolved to find forager behaviors natural, to instead act like farmers. As we become rich, we don’t as strongly fear the threats behind these social pressures. This connection may result in part from disease; rich people are healthier, and healthier societies fear less.

The alternate theory that we have instead learned that rich forager values are more true predicts that values should have followed a random walk over time, and be mostly common across space. It also predicts the variance of value changes tracking the rate at which relevant information appears. But in fact industrial-era value changes have tracked the wealth of each society in much more steady and consistent fashion. And on this theory, why did foragers ever acquire farmer values?

[…]

In the scenario described in this book, many strange-to-forager behaviors are required, and median per-person (i.e. per-em) incomes return to near-subsistence levels. This suggests that the em era may reverse the recent forager-like trend toward more liberality; ems may have more farmer-like values.

The Age of Em, p. 26-27

There’s a lot to unpack here, but maybe it’s better to burn the whole suitcase.

First of all, it’s not entirely clear that this is really a single axis of variation, that foragers and farmers differ from each other in the same way as liberals and conservatives. There’s some truth to that at least—both foragers and liberals tend to be more generous, both farmers and conservatives tend to enforce stricter gender norms. But there are also clear ways that liberal values radically deviate from forager values: Forager societies are extremely xenophobic, and typically very hostile to innovation, inequality, or any attempts at self-aggrandizement (a phenomenon called “fierce egalitarianism“). San Francisco epitomizes rich, liberal values, but it would be utterly alien and probably regarded as evil by anyone from the Yanomamo.

Second, there is absolutely no reason to predict any kind of random walk. That’s just nonsense. Would you predict that scientific knowledge is a random walk, with each new era’s knowledge just a random deviation from the last’s? Maybe next century we’ll return to geocentrism, or phrenology will be back in vogue? On the theory that liberal values (or at least some liberal values) are objectively correct, we would expect them to advance as knowledge doesimproving over time, and improving faster in places that have better institutions for research, education, and free expression. And indeed, this is precisely the pattern we have observed. (Those places are also richer, but that isn’t terribly surprising either!)

Third, while poorer regions are indeed more conservative, poorer people within a region actually tend to be more liberal. Nigeria is poorer and more conservative than Norway, and Mississippi is poorer and more conservative than Massachusetts. But higher-income households in the United States are more likely to vote Republican. I think this is particularly true of people living under insecure affluence: We see the abundance of wealth around us, and don’t understand why we can’t learn to share it better. We’re tired of fighting over scraps while the billionaires claim more and more. Millennials and Zoomers absolutely epitomize insecure affluence, and we also absolutely epitomize liberalism. So, if indeed ems live a life of insecure affluence, we should expect them to be like Zoomers: “Trans liberation now!” and “Eat the rich!” (Or should I say, “Delete the rich!”)

And really, doesn’t that make more sense? Isn’t that the trend our society has been on, for at least the last century? We’ve been moving toward more and more acceptance of women and minorities, more and more deviation from norms, more and more concern for individual rights and autonomy, more and more resistance to authority and inequality.

The funny thing is, that world sounds a lot better than the one Hanson is predicting.

A world of left-wing ems would probably run things a lot better than Hanson imagines: Instead of copying the same hundred psychopaths over and over until we fill the planet, have no room for anything else, and all struggle to make enough money just to stay alive, we could moderate our population to a more sustainable level, preserve diversity and individuality, and work toward living in greater harmony with each other and the natural world. We could take this economic and technological abundance and share it and enjoy it, instead of killing ourselves and each other to make more of it for no apparent reason.

The one good argument Hanson makes here is expressed in a single sentence: “And on this theory, why did foragers ever acquire farmer values?” That actually is a good question; why did we give up on leisure and egalitarianism when we transitioned from foraging to agriculture?

I think scarcity probably is relevant here: As food became scarcer, maybe because of climate change, people were forced into an agricultural lifestyle just to have enough to eat. Early agricultural societies were also typically authoritarian and violent. Under those conditions, people couldn’t be so generous and open-minded; they were surrounded by threats and on the verge of starvation.

I guess if Hanson is right that the em world is also one of poverty and insecurity, we might go back to those sort of values, borne of desperation. But I don’t see any reason to think we’d give up all of our liberal values. I would predict that ems will still be feminist, for instance; in fact, Hanson himself admits that since VR avatars would let us change gender presentation at will, gender would almost certainly become more fluid in a world of ems. Far from valuing heterosexuality more highly (as conservatives do, a “farmer value” according to Hanson), I suspect that ems will have no further use for that construct, because reproduction will be done by manufacturing, not sex, and it’ll be so easy to swap your body into a different one that hardly anyone will even keep the same gender their whole life. They’ll think it’s quaint that we used to identify so strongly with our own animal sexual dimorphism.

But maybe it is true that the scarcity induced by a hyper-competitive em world would make people more selfish, less generous, less trusting, more obsessed with work. Then let’s not do that! We don’t have to build that world! This isn’t a foregone conclusion!

There are many other paths yet available to us.

Indeed, perhaps the simplest would be to just ban artificial intelligence, at least until we can get a better handle on what we’re doing—and perhaps until we can institute the kind of radical economic changes necessary to wrest control of the world away from the handful of psychopaths currently trying their best to run it into the ground.

I admit, it would kind of suck to not get any of the benefits of AI, like self-driving cars, safer airplanes, faster medical research, more efficient industry, and better video games. It would especially suck if we did go full-on Butlerian Jihad and ban anything more complicated than a pocket calculator. (Our lifestyle might have to go back to what it was in—gasp! The 1950s!)

But I don’t think it would suck nearly as much as the world Robin Hanson thinks is in store for us if we continue on our current path.

So I certainly hope he’s wrong about all this.

Fortunately, I think he probably is.

How will AI affect inequality?

Oct 15 JDN 2460233

Will AI make inequality worse, or better? Could it do a bit of both? Does it depend on how we use it?

This is of course an extremely big question. In some sense it is the big economic question of the 21st century. The difference between the neofeudalist cyberpunk dystopia of Neuromancer and the social democratic utopia of Star Trek just about hinges on whether AI becomes a force for higher or lower inequality.

Krugman seems quite optimistic: Based on forecasts by Goldman Sachs, AI seems poised to automate more high-paying white-collar jobs than low-paying blue-collar ones.

But, well, it should be obvious that Goldman Sachs is not an impartial observer here. They do have reasons to get their forecasts right—their customers are literally invested in those forecasts—but like anyone who immensely profits from the status quo, they also have a broader agenda of telling the world that everything is going great and there’s no need to worry or change anything.

And when I look a bit closer at their graphs, it seems pretty clear that they aren’t actually answering the right question. They estimate an “exposure to AI” coefficient (somehow; their methodology is not clearly explained and lots of it is proprietary), and if it’s between 10% and 49% they call it “complementary” while if it’s 50% or above they call it “replacement”.

But that is not how complements and substitutes work. It isn’t a question of “how much of the work can be done by machine” (whatever that means). It’s a question of whether you will still need the expert human.

It could be that the machine does 90% of the work, but you still need a human being there to tell it what to do, and that would be complementary. (Indeed, this basically is how finance works right now, and I see no reason to think it will change any time soon.) Conversely, it could be that the machine only does 20% of the work, but that was the 20% that required expert skill, and so a once comfortable high-paying job can now be replaced by low-paid temp workers. (This is more or less what’s happening at Amazon warehouses: They are basically managed by AI, but humans still do most of the actual labor, and get paid peanuts for it.)

For their category “computer and mathematical”, they call it “complementary”, and I agree: We are still going to need people who can code. We’re still going to need people who know how to multiply matrices. We’re still going to need people who understand search algorithms. Indeed, if the past is any indicator, we’re going to need more and more of those people, and they’re going to keep getting paid higher and higher salaries. Someone has to make the AI, after all.

Yet I’m not quite so sure about the “mathematical” part in many cases. We may not need people who can solve differential equations, actually: maybe a few to design the algorithms, but honestly even then, a software program with a simple finite-difference algorithm can often solve much more interesting problems than one with a full-fledged differential equation solver, because one of the dirty secrets of differential equations is that for some of the most important ones (like the Navier-Stokes Equations), we simply do not know how to solve them. Once you have enough computing power, you often can stop trying to be clever and just brute-force the damn thing.

Yet for “transportation and material movement”—that is, trucking—Goldman Sachs confidently forecasts mostly “no automation” with a bit of “complementary”. Yet this year—not at some distant point in the future, not in some sci-fi novel, this year in the actual world—the Governor of California already vetoed a bill that would have required automated trucks to have human drivers. The trucks aren’t on the roads yet—but if we already are making laws about them, they’re going to be, soon. (State legislatures are not known for their brilliant foresight or excessive long-term thinking.) And if the law doesn’t require them to have human drivers, they probably won’t; which means that hundreds of thousands of long-haul truckers will suddenly be out of work.

It’s also important to differentiate between different types of jobs that may fall under the same category or industry.

Neurosurgeons are not going anywhere, and improved robotics will only allow them to perform better, safer laparoscopic surgeries. Nor are nurses going anywhere, because some things just need an actual person physically there with the patient. But general practictioners, psychotherapists, and even radiologists are already seeing many of their tasks automated. So is “medicine” being automated or not? That depends what sort of medicine you mean. And yet it clearly means an increase in inequality, because it’s the middle-paying jobs (like GPs) that are going away, while the high-paying jobs (like neurosurgeons) and the low-paying jobs (like nurses) that remain.

Likewise, consider “legal services”, which is one of the few industries that Goldman Sachs thinks will be substantially replaced by AI. Are high-stakes trial lawyers like Sam Bernstein getting replaced? Clearly not. Nor would I expect most corporate lawyers to disappear. Human lawyers will still continue to perform at least a little bit better than AI law systems, and the rich will continue to use them, because a few million dollars for a few percentage points better odds of winning is absolutely worth it when billions of dollars are on the line. So which law services are going to get replaced by AI? First, routine legal questions, like how to renew your work visa or set up a living will—it’s already happening. Next, someone will probably decide that public defenders aren’t worth the cost and start automating the legal defenses of poor people who get accused of crimes. (And to be honest, it may not be much worse than how things currently are in the public defender system.) The advantage of such a change is that it will most likely bring court costs down—and that is desperately needed. But it may also tilt the courts even further in favor of the rich. It may also make it even harder to start a career as a lawyer, cutting off the bottom of the ladder.

Or consider “management”, which Goldman Sachs thinks will be “complementary”. Are CEOs going to get replaced by AI? No, because the CEOs are the ones making that decision. Certainly this is true for any closely-held firm: No CEO is going to fire himself. Theoretically, if shareholders and boards of directors pushed hard enough, they might be able to get a CEO of a publicly-traded corporation ousted in favor of an AI, and if the world were really made of neoclassical rational agents, that might actually happen. But in the real world, the rich have tremendous solidarity for each other (and only each other), and very few billionaires are going to take aim at other billionaires when it comes time to decide whose jobs should be replaced. Yet, there are a lot of levels of management below the CEO and board of directors, and many of those are already in the process of being replaced: Instead of relying on the expert judgment of a human manager, it’s increasingly common to develop “performance metrics”, feed them into an algorithm, and use that result to decide who gets raises and who gets fired. It all feels very “objective” and “impartial” and “scientific”—and usually ends up being both dehumanizing and ultimately not even effective at increasing profits. At some point, many corporations are going to realize that their middle managers aren’t actually making any important decisions anymore, and they’ll feed that into the algorithm, and it will tell them to fire the middle managers.

Thus, even though we think of “medicine”, “law”, and “management” as high-paying careers, the effect of AI is largely going to be to increase inequality within those industries. It isn’t the really high-paid doctors, managers, and lawyers who are going to get replaced.

I am therefore much less optimistic than Krugman about this. I do believe there are many ways that technology, including artificial intelligence, could be used to make life better for everyone, and even perhaps one day lead us into a glorious utopian future.

But I don’t see most of the people who have the authority to make important decisions for our society actually working towards such a future. They seem much more interested in maximizing their own profits or advancing narrow-minded ideologies. (Or, as most right-wing political parties do today: Advancing narrow-minded ideologies about maximizing the profits of rich people.) And if we simply continue on the track we’ve been on, our future is looking a lot more like Neuromancer than it is like Star Trek.

AI and the “generalization faculty”

Oct 1 JDN 2460219

The phrase “artificial intelligence” (AI) has now become so diluted by overuse that we needed to invent a new term for its original meaning. That term is now “artificial general intelligence” (AGI). In the 1950s, AI meant the hypothetical possibility of creating artificial minds—machines that could genuinely think and even feel like people. Now it means… pathing algorithms in video games and chatbots? The goalposts seem to have moved a bit.

It seems that AGI has always been 20 years away. It was 20 years away 50 years ago, and it will probably be 20 years away 50 years from now. Someday it will really be 20 years away, and then, 20 years after that, it will actually happen—but I doubt I’ll live to see it. (XKCD also offers some insight here: “It has not been conclusively proven impossible.”)

We make many genuine advances in computer technology and software, which have profound effects—both good and bad—on our lives, but the dream of making a person out of silicon always seems to drift ever further into the distance, like a mirage on the desert sand.

Why is this? Why do so many people—even, perhaps especially,experts in the field—keep thinking that we are on the verge of this seminal, earth-shattering breakthrough, and ending up wrong—over, and over, and over again? How do such obviously smart people keep making the same mistake?

I think it may be because, all along, we have been laboring under the tacit assumption of a generalization faculty.

What do I mean by that? By “generalization faculty”, I mean some hypothetical mental capacity that allows you to generalize your knowledge and skills across different domains, so that once you get good at one thing, it also makes you good at other things.

This certainly seems to be how humans think, at least some of the time: Someone who is very good at chess is likely also pretty good at go, and someone who can drive a motorcycle can probably also drive a car. An artist who is good at portraits is probably not bad at landscapes. Human beings are, in fact, able to generalize, at least sometimes.

But I think the mistake lies in imagining that there is just one thing that makes us good at generalizing: Just one piece of hardware or software that allows you to carry over skills from any domain to any other. This is the “generalization faculty”—the imagined faculty that I think we do not have, indeed I think does not exist.

Computers clearly do not have the capacity to generalize. A program that can beat grandmasters at chess may be useless at go, and self-driving software that works on one type of car may fail on another, let alone a motorcycle. An art program that is good at portraits of women can fail when trying to do portraits of men, and produce horrific Daliesque madness when asked to make a landscape.

But if they did somehow have our generalization capacity, then, once they could compete with us at some things—which they surely can, already—they would be able to compete with us at just about everything. So if it were really just one thing that would let them generalize, let them leap from AI to AGI, then suddenly everything would change, almost overnight.

And so this is how the AI hype cycle goes, time and time again:

  1. A computer program is made that does something impressive, something that other computer programs could not do, perhaps even something that human beings are not very good at doing.
  2. If that same prowess could be generalized to other domains, the result would plainly be something on par with human intelligence.
  3. Therefore, the only thing this computer program needs in order to be sapient is a generalization faculty.
  4. Therefore, there is just one more step to AGI! We are nearly there! It will happen any day now!

And then, of course, despite heroic efforts, we are unable to generalize that program’s capabilities except in some very narrow way—even decades after having good chess programs, getting programs to be good at go was a major achievement. We are unable to find the generalization faculty yet again. And the software becomes yet another “AI tool” that we will use to search websites or make video games.

For there never was a generalization faculty to be found. It always was a mirage in the desert sand.

Humans are in fact spectacularly good at generalizing, compared to, well, literally everything else in the known universe. Computers are terrible at it. Animals aren’t very good at it. Just about everything else is totally incapable of it. So yes, we are the best at it.

Yet we, in fact, are not particularly good at it in any objective sense.

In experiments, people often fail to generalize their reasoning even in very basic ways. There’s a famous one where we try to get people to make an analogy between a military tactic and a radiation treatment, and while very smart, creative people often get it quickly, most people are completely unable to make the connection unless you give them a lot of specific hints. People often struggle to find creative solutions to problems even when those solutions seem utterly obvious once you know them.

I don’t think this is because people are stupid or irrational. (To paraphrase Sydney Harris: Compared to what?) I think it is because generalization is hard.

People tend to be much better at generalizing within familiar domains where they have a lot of experience or expertise; this shows that there isn’t just one generalization faculty, but many. We may have a plethora of overlapping generalization faculties that apply across different domains, and can learn to improve some over others.

But it isn’t just a matter of gaining more expertise. Highly advanced expertise is in fact usually more specialized—harder to generalize. A good amateur chess player is probably a good amateur go player, but a grandmaster chess player is rarely a grandmaster go player. Someone who does well in high school biology probably also does well in high school physics, but most biologists are not very good physicists. (And lest you say it’s simply because go and physics are harder: The converse is equally true.)

Humans do seem to have a suite of cognitive tools—some innate hardware, some learned software—that allows us to generalize our skills across domains. But even after hundreds of millions of years of evolving that capacity under the highest possible stakes, we still basically suck at it.

To be clear, I do not think it will take hundreds of millions of years to make AGI—or even millions, or even thousands. Technology moves much, much faster than evolution. But I would not be surprised if it took centuries, and I am confident it will at least take decades.

But we don’t need AGI for AI to have powerful effects on our lives. Indeed, even now, AI is already affecting our lives—in mostly bad ways, frankly, as we seem to be hurtling gleefully toward the very same corporatist cyberpunk dystopia we were warned about in the 1980s.

A lot of technologies have done great things for humanity—sanitation and vaccines, for instance—and even automation can be a very good thing, as increased productivity is how we attained our First World standard of living. But AI in particular seems best at automating away the kinds of jobs human beings actually find most fulfilling, and worsening our already staggering inequality. As a civilization, we really need to ask ourselves why we got automated writing and art before we got automated sewage cleaning or corporate management. (We should also ask ourselves why automated stock trading resulted in even more money for stock traders, instead of putting them out of their worthless parasitic jobs.) There are technological reasons for this, yes; but there are also cultural and institutional ones. Automated teaching isn’t far away, and education will be all the worse for it.

To change our lives, AI doesn’t have to be good at everything. It just needs to be good at whatever we were doing to make a living. AGI may be far away, but the impact of AI is already here.

Indeed, I think this quixotic quest for AGI, and all the concern about how to control it and what effects it will have upon our society, may actually be distracting from the real harms that “ordinary” “boring” AI is already having upon our society. I think a Terminator scenario, where the machines rapidly surpass our level of intelligence and rise up to annihilate us, is quite unlikely. But a scenario where AI puts millions of people out of work with insufficient safety net, triggering economic depression and civil unrest? That could be right around the corner.

Frankly, all it may take is getting automated trucks to work, which could be just a few years. There are nearly 4 million truck drivers in the United States—a full percentage point of employment unto itself. And the Governor of California just vetoed a bill that would require all automated trucks to have human drivers. From an economic efficiency standpoint, his veto makes perfect sense: If the trucks don’t need drivers, why require them? But from an ethical and societal standpoint… what do we do with all the truck drivers!?