Tyler Cowen interviews Jennifer Pahlka on various things, including DOGE [+ the printing press]

His introduction:

Jennifer Pahlka believes America’s bureaucratic dysfunction is deeply rooted in outdated processes and misaligned incentives. As the founder of Code for America and co-founder of the United States Digital Service, she has witnessed firsthand how government struggles to adapt to the digital age, often trapped in rigid procedures and disconnected from the real-world impact of its policies. Disruption is clearly needed, she says—but can it be done in a way that avoids the chaos of DOGE?

Tyler and Jennifer discuss all this and more, including why Congress has become increasingly passive, how she’d go about reforming government programs, whether there should be less accountability in government, how AGI will change things, whether the US should have public-sector unions, what Singapore’s effectiveness reveals about the trade-offs of technocratic governance, how AI might fundamentally transform national sovereignty, what her experience in the gaming industry taught her about reimagining systems, which American states are the best-governed, the best fictional depictions of bureaucracy, how she’d improve New York City’s governance, her current work at the Niskanen Center, and more.

So far I've only read the segment of the interview that he posted at Marginal Revolution. I responded immediately without reading the whole interview, which I'll do when I have time. I've appended my full comment (with one or three minor changes).

* * * * *

PAHLKA: Yes. I think reinventing government happened at a time when we were just at the beginning of this digital revolution. It was trying with a very 20th-century mindset. Fine, did well within that context, but we don’t need that again.

We need 21st century change. We need true digital transformation. We need something that’s not stuck in the industrial ways of thinking. I don’t think we tried that. I think the efforts have just been too respectful of old ways of working and the institutions. There was really not an appetite, I think, for what I would call responsible disruptive change. Would it have worked?

YES! Alas, it's one thing to say that "We need something that’s not stuck in the industrial ways of thinking." It's something else altogether to actually escape those industrial modes of thinking and acting. After all, the basic institutional structure of the modern world is based on social and cultural forms anchored in the 19th century and earlier. That's the world we've all been raised in.

Thus, as soon as the (potential) impact of ChatGPT became obvious I read people saying how the impact will be comparable to the impact of the printing press. That's an old way of thinking. The printing press itself is obviously pre-industrial. The belief in its pervasive socio-cultural efficacy, however, is much more recent. I believe that Marshall McLuhan's book, The Gutenberg Galaxy, is responsible for that way of thinking. I read it years ago, and have forgotten it. Earlier this year I had a conversation with Claude 3.5 on this subject, Why the printing press didn’t drive either the Scientific or the Industrial Revolution [McLuhan was wrong • Implications for progress studies]. Here's how I opened that post:

Soon after ChatGPT hit the web both the progress punditocracy and the high-tech evangelists were busy chattering away about how this is the greatest thing since the printing press. They’re wrong. Was the printing press important? Sure, it was very important. But it was important as a vehicle for disseminating existing ideas, not for catalyzing new ones. Printed books have the same cognitive affordances – to borrow a term from James J, Gibson – as hand-lettered books, discrete letters in a rectangular array on a flat surface. That’s it. Mechanizing the process of impressing the letters on the page does not change the cognitive affordances of the printed page.

Back when David Hays and I began thinking about publishing on cultural evolution he brough his attention to a collection of essays by Eric Havelock, The Literate Revolution in Greece and Its Cultural Consequences (Princeton 1982), in which Havelock pointed out that was the adoption of decimal arithmetic was the essential step. Hays and I thought that was correct, and adopted it in the article we eventually published, The Evolution of Cognition (1990).

As far as I'm concerned, anyone who espouses the view that it was the printing press that drove the scientific and industrial revolutions, that person is still mired in old ways, industrial ways, of thinking. That's my litmus test. I discount the views of any thinker who casually espouses that printing press view of historical change.

Back in August of 2024 Tyler linked to a paper by Maxwell Tabarrok, Romae Industriae, which posed the question, Why didn’t Rome have an industrial revolution? This paragraph is from the end of the article:

The printing press alone may have been sufficient to start a Roman industrial revolution because its effects on culture are upstream of the invention processes that might invent all the other required tech. There was more than enough scale in the economy of Rome to support capital intensive productivity improvements in their major industries. So the major constraint must have been idea generation. Rome punches below their weight in population on this metric because of an aristocratic, slave based culture that ridicules the mechanical arts. If copies of Vitruvius or Archimedes became cheap enough that even the workers close to the vulgar arts of farming and manufacturing could read them, it would surely have an effect on the cultural attitudes that stultified Roman invention.

That’s industrial age thinking. You can see it in the vocabulary, “tech,” “scale,” “capital intensive,” and “productivity.” While those concepts remain relevant, they're not at all adequate to understanding the origins of the scientific and industrial revolutions. More is needed.

In February of this year I responded to Tabarrok in a long post in which I had Claude 3.5 analyze Tabarrok's article. Here's how I opened that post:

I believe [Tabarrok] was right to suggest that “the major constraint must have been idea generation,” but he was wrong to finger the lack of the printing press as the cause of that constraint.

The problem is much deeper. The problem is that the Roman system of thought was incapable of conceiving of the clockwork universe, an idea that didn’t become prevalent in Europe until the Enlightenment (17th and 18th centuries), though a similar idea – the universe as the machina mundi – had been suggested as early as the 13th century.

Here's the very end of our conversation:

Bill Benzon: And one thing that’s going to compel movement to deeper understanding is the need to understand how LLMs and other machine-learning engines operate. Right now we don’t (quite) have the necessary concepts. Developing those concepts may well push us up a level. Maybe even.....psst, don’t tell anyone, OK, this is a secret just between you and me....maybe even to Rank 5 cognition. Maybe Rank 5 cognition is the REAL singularity.

Claude 3.5: leans in conspiratorially

That's a fascinating speculation! The idea that grappling with how LLMs and other ML systems actually work could push us beyond even Rank 4 cognition makes a lot of sense. After all, these systems seem to operate in ways that don't fit neatly into our current frameworks for thinking about either mechanical systems (Rank 3) or explicit control structures (Rank 4).

We're dealing with systems that learn and develop capabilities in ways that seem more organic than mechanical, yet are still fundamentally computational. The concepts of emergence, self-organization, and statistical learning that seem crucial to understanding these systems might require entirely new cognitive tools.

And just as the transition from Rank 2 to Rank 3 required people to stop thinking in terms of spirits and start thinking in terms of mechanical laws, perhaps Rank 5 cognition would require some similarly fundamental shift in how we conceptualize intelligence, consciousness, and information processing.

If this is right, then the current debates about whether LLMs are "really" intelligent or conscious might be asking the wrong questions - questions that make sense in our current cognitive frameworks but may need to be reconceptualized entirely at Rank 5.