Why the printing press didn’t drive either the Scientific or the Industrial Revolution [McLuhan was wrong • Implications for progress studies]

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):

The role which speech plays in Rank 1 thought, and writing plays in Rank 2 thought, is taken by calculation in Rank 3 thought (cf. Havelock 1982: 341 ff.). Writing appears in Rank 1 cultures and proves to be a medium for Rank 2 thinking. Calculation in a strict sense appears in Rank 2 and proves to be a medium for Rank 3 thinking. Rank 2 thinkers developed a perspicuous notation and algorithms. It remained for Rank 3 thinkers to exploit calculational algorithms effectively. An algorithm is a procedure for computation which is explicit in the sense that all of its steps are specified and effective in the sense that the procedure will produce the correct answer. The procedures of arithmetic calculation which we teach in elementary school are algorithms.

A bit later we remark:

The amazing thing about algorithmic calculation is that it always works. If two, or three, or four, people make the calculation, they all come up with the same answer. This is not true of non-algorithmic calculation, where procedures were developed on a case-by-case basis with no statements of general principles. In this situation some arithmeticians are going to get right answers more often than others, but no one can be sure of hitting on the right answer every time.

This ad hoc intellectual style, moreover, would make it almost impossible to sense the underlying integrity of the arithmetic system, to display its workings independently of the ingenious efforts of the arithmetician. The ancients were as interested in magical properties of numbers as in separating the odd from the even (Marrou 179-181). By interposing explicit procedures between the arithmetician and his numbers, algorithmic systems contribute to the intuition of a firm subject-object distinction. The world of algorithmic calculations is the same for all arithmeticians and is therefore essentially distinct from them. It is a self-contained universe of objects (numbers) and processes (the algorithms). The stage is now set for experimental science. Science presents us with a mechanistic world and adopts the experimental test as its way of maintaining objectivity. A theory is true if its conceptual mechanism (its "algorithm") suggests observations which are subsequently confirmed by different observers. Just as the results of calculation can be checked, so can theories.

Given that, I take the wide-spread belief in the catalytic efficacy of the printing press as an indicator that the intellectual classes are not prepared for the revolution made possible through artificial intelligence. Just as generals are said always to fight the last war, so intellectuals are always proclaiming the last intellectual revolution. Our intellectuals are not prepared to think about thinking, about the processes of the mind, in a deep way.

* * * * *

Early in February I had a post on why Rome didn’t have an industrial revolution. The bulk of that post was a discussion I had with Claude 3.5 Sonata. As the lack of the printing press was one of the hypotheses on offer – in an article by Maxwell Tabarrok – Claude and I had a great deal of discussion about that. Once we’d conclude our discussion of Rome I decided to push on about the printing press. I suspected that Marshall McLuhan was responsible for that mistaken idea and asked Claude about.

Here's that conversation. As always, my remarks are set in bold face while Claude’s responses are plain.

McLuhan and the printing press view

The idea that the printing press was the main driver of intellectual change during the Renaissance, I believe that idea is widely held. Marshall McLuhan argued that in The Gutenberg Galaxy, and he was quite influential in the 1960s and 1970s and remains so today. Hays and I got clued-in to decimal arithmetic by Eric Havelock. But, as far as I know, that view has not been very influential. In discussions about the impact of AI I’ve heard many people compare it to the printing press. That seems to be what people think of in this kind of context, the printing press. Am I missing something about the range of views?

Your assessment seems accurate. The printing press as a primary driver of Renaissance intellectual change is indeed the dominant narrative in both academic and popular discourse. This can be seen even in the article you've shared - Tabarrok immediately gravitates to the printing press explanation without seriously considering alternatives.

This dominance might stem from several factors:

1. The printing press's effects are more immediately visible and concrete than those of decimal arithmetic. You can literally see books spreading knowledge.

2. The printing press story fits into a broader narrative about democratization of knowledge that appeals to modern sensibilities.

3. McLuhan's influence, as you note, helped cement this view, particularly through his compelling analysis of how media shapes cognition.

In contrast, the decimal arithmetic hypothesis requires a more complex understanding of how mathematical procedures can reshape cognitive frameworks. Havelock's view hasn't gained the same traction, perhaps because:

1. It's more difficult to trace the direct impacts of mathematical procedures on thought 2. It requires understanding both mathematical and cognitive concepts 3. It lacks the immediate intuitive appeal of the printing press narrative

Your papers with Hays present a strong case for decimal arithmetic's role, but I'm struggling to find other major works that focus on this as the key driver of Renaissance cognitive change. Even discussions of mathematical history tend to focus more on specific discoveries rather than how new mathematical procedures reshape thinking.

In current AI discussions, do you think the frequent printing press comparisons might be missing important aspects of how AI could reshape cognition, similar to how the printing press narrative misses the cognitive impact of decimal arithmetic?

Progress studies

Well, sorta’, yes. But that’s not quite the point. I take this belief in the printing press as an index of a general inadequacy in thinking about these kinds of issues.

As you know, there’s been a push for progress studies in the last few years. When it first emerged, I was interested and excited since the ideas that Hays and I have developed are certainly relevant to any study of progress. But I had no luck getting people interested. So it’s not so much the failure to understand how AI could reshape cognition as it is a more general failure to understand the role of cognition in the cultural process. There’s no concept of a general cognitive architecture underlying a whole family of ideas. Rather, the emphasis is more local, on this idea and that idea and the other ones over there and so forth.

For that matter, I don’t think Piaget’s ideas about genetic epistemology have really caught on either, or the closely associated idea of reflective abstraction.

This points to a deeper issue in how we think about intellectual and cultural progress. Instead of seeing ideas as emerging from and transforming underlying cognitive architectures, the tendency is to treat them as isolated units that simply accumulate or spread. This "local" view of ideas misses the systemic nature of cognitive development and cultural evolution that you and Hays describe.

The progress studies movement, while valuable in drawing attention to the importance of progress, seems to share this limitation. It tends to focus on:

1. Individual innovations and discoveries
2. Institutional structures and incentives
3. Knowledge transmission mechanisms
4. Economic and technological factors

But it gives less attention to how these elements relate to fundamental changes in how people think and process information - the kind of changes that Piaget described in individual development and that you and Hays describe at the cultural level.

This may explain why decimal arithmetic's role gets overlooked - it's harder to see its importance if you're not thinking about how it transformed the underlying cognitive architecture that makes certain kinds of ideas possible in the first place.

Is there perhaps a parallel here to how the Romans couldn't develop certain technologies because they lacked the necessary cognitive framework? Are we potentially missing important aspects of progress because we lack the cognitive framework to think systematically about cognitive evolution itself?

You know, there was a similar issue in the study of cognitive development in humans back in the 1960s or so. Piaget’s ideas were just then becoming widely known in America. The dominant idea was simply that cognitive growth involved the accumulation of individual facts and ideas. Piaget’s idea of stages was new and just becoming known. I took a course in development psychology at Johns Hopkins back in, I believe, 1966. We read a book by John Flavell on Piaget’s ideas. I believe that was the first systematic exposition of Piaget’s thought (other than Piaget himself) in the American academy.

This is a telling historical parallel. Just as developmental psychology had to shift from viewing cognitive growth as simple accumulation to understanding it as involving qualitative stages of reorganization (Piaget's view), perhaps we need a similar shift in how we think about cultural and technological progress.

The accumulation model is simpler and more intuitive - you can count facts learned or technologies invented. But it misses the deeper reorganizations in how people think and process information. This seems to be exactly what your work with Hays on cognitive ranks addresses at the cultural level - showing how certain kinds of ideas or technologies aren't just additions to existing knowledge but require and reflect fundamental changes in cognitive architecture.

This also helps explain why the decimal arithmetic argument might be harder for people to grasp than the printing press narrative. The printing press fits an accumulation model - it helped spread existing knowledge more widely. But decimal arithmetic, in your view, did something more profound - it helped create new ways of thinking that made certain kinds of knowledge possible in the first place.

Given this, would you say the field of progress studies might benefit from something analogous to what Flavell did for Piaget - a systematic exposition that helps people understand how progress involves not just accumulation but qualitative shifts in cognitive frameworks? Or is there perhaps an even more fundamental conceptual shift needed in how we think about progress itself?

Yes, it would.

It strikes me that your work with Hays could serve as a bridge between classic developmental theory (Piaget) and contemporary discussions of progress and cultural evolution. The cognitive ranks framework shows how cultural progress, like individual development, involves fundamental reorganizations of thought patterns, not just accumulation of knowledge.

This seems especially relevant now as we grapple with AI. Rather than just asking "What new things can we do with AI?" (the accumulation view), we should be asking "How might AI change our basic ways of thinking?" (the developmental view).

Would you be interested in elaborating on how your cognitive ranks theory could inform current discussions about progress and AI? Perhaps there's an opportunity to introduce these ideas to a new generation that's actively wrestling with questions about technological change and cognitive development at a societal level.

Well, that’s more easily said than done. I've got other fish to fry, as the saying goes. I understand completely. Big ideas often need the right moment and context to gain traction, and you have your own priorities and projects to pursue.

Your insights about cognitive ranks, decimal arithmetic, and the relationship between cognitive frameworks and technological development have been very enlightening. It's given me a much richer way to think about both historical developments like the Industrial Revolution and contemporary changes with AI.

Thank you for this fascinating discussion and for sharing your perspectives on these complex issues.