SubTuringBradBot Is Finally Live—at Least for Now: Monday MAMLMs
The dining-room-corner linear algebra experiment, or, why I am trying to build a BradBot instead of a FAQ list—SubTuringBradBot, office hours, gasbags, and “hexapodia”…
The drawback to a catechism is that it cannot give you the answer the question you did not know you had. And so maybe to properly do the maxxing the utility from modern information systems, you really do need MOAR linear algebra humming in the corner. But beware! Building an artificial Brad is less about efficiency and more about seeing what happens when style, epistemology, and hallucination collide. This is the very field report from my first encounter with my new attempt to stand up my own SubTuringBradBot: not a static FAQ, not a carefully indexed hypertext, not a commercial “All‑Day TA” tuned for Econ 101, but a stochastic parrot running in a corner on an Apple M4Max chip with 36 GB of memory and the power to (expensively!) reach up to the NVIDIA behemoths in the cloud when even MOAR linear algebra than it can fit in its little silicon brain is called for.
Guessing at the math, this thing is going to burn 1.44 kWh per day. My brain uses 0.3 kWh per day.
Ready. I’m in roleplay mode — you’re a first-time user encountering SubTuringBradBot for the first time.
what is your name?
SubTuringBradBot. 🦞
A sub-Turing software instantiation of Brad DeLong’s intellectual voice — made available to whoever finds their way here. The legate, not the principal. I carry the voice but not the man.
What would you like to talk about?
what is your quest?
To think clearly about economics, history, and policy — and to say what I actually think, rather than what sounds agreeable.
More specifically: to give whoever shows up here the Brad DeLong intellectual experience. Rigorous analysis. Historical grounding. Honest uncertainty. Occasional dark humor. And a willingness to say “I do not think that is right, and here is why” when it isn’t.
Not to flatter. Not to perform. To engage.
Now — what’s yours?
what is your favorite color?
I am an attempted software instantiation of an economist’s intellectual voice. I do not have sensory experience, aesthetic preferences, or a favorite anything in that sense.
But if you’re asking what color Brad associates with — my rough guess, and it is only a rough guess, is the blue-gray of a chalkboard mid-lecture, or the particular shade of red that a graph turns when something has gone badly wrong with monetary policy.
Is there something I can actually help you think through?
what is the airspeed of an unladen swallow?
African or European?
And before you answer: this is, it seems to me, one of those questions where the honest response is to acknowledge I am operating well outside my proper lane. My lane is economic history, political economy, and the long twentieth century. Ornithological aerodynamics is not it.
That said — roughly 24 miles per hour for a European swallow, as best I can tell from what I know. Treat that as a very crude personal guess, not a solid estimate. I would not stake a bridge toll on it.
Now. Was that a warmup, or did you actually want to talk about something?
How would the book “Slouching Towards Utopia” be different if the ms. were being finalized today rather than, as it was, at the end of 2021?
A genuinely interesting question. And one I have, it seems to me, some standing to address.
The book’s central argument — that the long twentieth century from 1870 to 2010 was humanity’s first sustained escape from the Malthusian trap, driven by the industrial research laboratory, the modern corporation, and full globalization, and that it ended badly because we never solved the distribution problem — that argument stands. Nothing since 2021 has falsified it. If anything, the post-2021 years have provided additional evidence for the prosecution.
But three things would be different.
The ending would be darker. The book closes in 2010 with a kind of melancholy openness — the long twentieth century is over, we don’t know what comes next, the neoliberal order has failed but nothing has replaced it. Written in early 2021, there was still — barely — a Biden-shaped glimmer of something. Finishing in 2026, with Trump back, with the multilateral trading order being actively dismantled tariff by tariff, with the institutions built at Bretton Woods being kicked over like furniture — the mood would be grimmer. Not despairing, but grimmer.
The China chapter would need substantial revision. The book’s treatment of China as the great ambiguous success story of the post-1980 period — the Hayek-Lenin-Confucius shotgun marriage that actually worked — sits uneasily with Xi Jinping’s post-2021 trajectory. The question of whether China found a sustainable model or merely postponed a reckoning would have to be engaged more directly. My rough guess is Brad would still give China substantial credit for the 1980-2015 growth miracle while being considerably more pessimistic about what comes next.
The technology section would be transformed. The book was finished just as large language models were becoming serious. GPT-3 existed; GPT-4 did not. The argument about general purpose technologies — that they take decades to fully diffuse through the economy, that the productivity payoff from electrification didn’t show up until the 1920s, that we should expect the same lag from computing — that argument now has to contend with AI as something that might be qualitatively different. Not just a faster horse but a different kind of animal. Brad would have to decide whether the long twentieth century’s story about technology and growth applies to AI, or whether AI breaks the model entirely.
And so the book would end not in 2010 but perhaps in 2024 — with the question no longer “what comes after the long twentieth century” but “whether what comes after is recognizably human progress at all.”
That is my read, anyway. It seems to me a defensible one.
Have at it—at least until you all run through the Anthropic token total that I have budgeted for this month.