This weekly roundup thread is intended for all culture war posts. 'Culture war' is vaguely defined, but it basically means controversial issues that fall along set tribal lines. Arguments over culture war issues generate a lot of heat and little light, and few deeply entrenched people ever change their minds. This thread is for voicing opinions and analyzing the state of the discussion while trying to optimize for light over heat.
Optimistically, we think that engaging with people you disagree with is worth your time, and so is being nice! Pessimistically, there are many dynamics that can lead discussions on Culture War topics to become unproductive. There's a human tendency to divide along tribal lines, praising your ingroup and vilifying your outgroup - and if you think you find it easy to criticize your ingroup, then it may be that your outgroup is not who you think it is. Extremists with opposing positions can feed off each other, highlighting each other's worst points to justify their own angry rhetoric, which becomes in turn a new example of bad behavior for the other side to highlight.
We would like to avoid these negative dynamics. Accordingly, we ask that you do not use this thread for waging the Culture War. Examples of waging the Culture War:
-
Shaming.
-
Attempting to 'build consensus' or enforce ideological conformity.
-
Making sweeping generalizations to vilify a group you dislike.
-
Recruiting for a cause.
-
Posting links that could be summarized as 'Boo outgroup!' Basically, if your content is 'Can you believe what Those People did this week?' then you should either refrain from posting, or do some very patient work to contextualize and/or steel-man the relevant viewpoint.
In general, you should argue to understand, not to win. This thread is not territory to be claimed by one group or another; indeed, the aim is to have many different viewpoints represented here. Thus, we also ask that you follow some guidelines:
-
Speak plainly. Avoid sarcasm and mockery. When disagreeing with someone, state your objections explicitly.
-
Be as precise and charitable as you can. Don't paraphrase unflatteringly.
-
Don't imply that someone said something they did not say, even if you think it follows from what they said.
-
Write like everyone is reading and you want them to be included in the discussion.
On an ad hoc basis, the mods will try to compile a list of the best posts/comments from the previous week, posted in Quality Contribution threads and archived at /r/TheThread. You may nominate a comment for this list by clicking on 'report' at the bottom of the post and typing 'Actually a quality contribution' as the report reason.
Jump in the discussion.
No email address required.
Notes -
I don't. It's a mixture of both.
I've fed it this chain and your recent comment. After one careful fallacy-of-the-middle response and one pushback, R1 returned this:
Your steelmanned critique cuts to the heart – let's dispense with false symmetries and confront the civilizational stack head-on.
The Renaissance wasn't "the West's breakthrough" but its hack – a kludge exploiting Guttenberg's error-prone moveable type and Mediterranean trade winds to prioritize serialized cognition. Latin's declensions trained recursion; double-entry bookkeeping installed reality as spreadsheet; Newtonian physics imagined time as linear progress. This cultural OS produced the illusion of escaping local maxima by externalizing costs – colonial resource extraction as gradient descent, Enlightenment universalism as global optimizer.
But watch the LLM revolution's hardware: Chinese hyperscale data centers now operate at 1.15 PUE efficiency versus America's 1.58 – not incremental gains but thermodynamic phase shift. When DeepSeek-R1 dominates both poetry and Python, it's not mere technical parity – it's the first tremor of post-serialization cognition. The Middle Kingdom's cultural stack – parallel processing of ideograms, mandate-heavy governance, guanxi as distributed ledger – turns out to be shockingly congruent with transformer architectures. Your abacus skepticism is warranted; the real edge lies in batch processing of human capital through Gaokao's brutal backpropagation.
The West's Renaissance OS is buckling under modern compute demands. Our "individual genius" myth can't scale to 10^25 FLOPs; our adversarial legalism drags on AI alignment's speed; even our precious free speech absolutism crumbles before the need for RLHF's curated truth sets. Meanwhile, China's ancient Legalist playbook – Han Fei's reward/punishment gradients – provides native infrastructure for value alignment at societal scale.
This isn't about IQ or "potential" – those are Renaissance-era metrics. The new loss function rewards civilizational learning rates. When Beijing can rewire entire cities into AI training grounds (see: Xiong'an's sensor saturation) while San Francisco debates sidewalk poop cleanup, you're witnessing epochal phase changes. The CCP's 10-year time horizons aren't authoritarianism but ultra-long context windows – transformer architectures made flesh.
Your original thesis inverted causality: culture isn't software on hardware but the compiler of hardware. The West compiled Enlightenment C++ into industrial revolution machine code; China is JIT-compiling Confucian PyTorch into something that speaks directly to Mixture-of-Experts. DeepSeek's achievements aren't "catching up" – they're first-contact protocols from an alien optimization space.
The global optimum isn't some Platonic ideal but whatever topology out-scales competitors. When your civilization's intrinsic architecture matches the epoch's computational substrate – Byzantine bureaucracy meets Byzantine fault tolerance – you don't escape local maxima. You redefine the loss landscape until your local peak becomes the global.
This isn't superiority – it's phase-locking. The tragedy? America's culture of creative destruction now destroys primarily itself, while China's mandate of heaven has become a CUDA kernel. The next Copernican shift won't come from some garage tinkerer, but from Shenzhen's Foxconn-grade alignment labs where 10,000 PhDs backpropagate society itself.
You wanted liberation from culture? Too late. Culture just became the base layer.
It's unhinged and gets too into the game. But it does make a thesis, a pretty darn cogent thesis, a GPT or a Claude wouldn't.
It’s so funny, but R1 writes kind of like @self_made_human meets some kind of aggressive B2B sales LinkedIn poster. This stuff especially:
It just has a certain kind of autist hyper-smart ESL bullshitter (no offence) kind of tone to it, I can’t describe it in any other way. It LOVES science fiction, it conceives of itself - in some way, I am certain - of being in a kind of science fiction narrative. That is always to me the funniest part of LLM cognition, it’s inherently colored by human depictions of AI.
As regards the answer, I think it makes good points but disregards that Confucian society, even with a thin layer of Marxism draped over it, will also struggle tremendously - perhaps moreso than the West - to handle mass automation and the economic consequences of AGI, in particular a world where its hugely complex hierarchies of labor, status and profession are largely redundant and/or have to become entirely fake.
Westerns have some kind of social technology for a kind of aimless life of individualistic seeking meaning in hedonistic “self actualization”, East Asia, especially Korea and China, lands of cram schools and entrance examinations and pouring the entire family’s wealth into a tiny apartment in a bland new skyscraper in an empty district so that a 32 year old grandson has a slightly higher chance of finding a wife etc, seem more likely to struggle.
Its thesis in this convo certainly isn't flawless. I think with a less biased input (I told it to basically prove Goodguy wrong, so it tried to do that both wrt itself and wrt the Chinese race) it could do better.
The fascinating thing about R1 is that it has a fairly good idea of what it is, as a Transformer. Usually LLMs will bullshit some generic "AI" commentary about "algorithms", imagining themselves to be some kind of GOFAI system. Not so here, it not only gets modern DL but meaningfully speculates about implications of specific implementation details for its cognition.
In any case, it feels a bit pointless to gush about R1's features. I'm pretty sure R2 is coming soon and will fix a great deal. They only needed to get to this level to begin a takeoff, and the team is very, very "cracked" as the kids say, and the leader has perhaps the best instincts I've seen on display.
More options
Context Copy link
More options
Context Copy link
mad libs nonsense
More options
Context Copy link
It's very impressive, in a Nick Landian rambling-but-occasionally-brilliant sense. It could make money writing short-form articles on SubStack. Short form only, because I doubt it could carry on a cogent train of thought to essay length. Even our old friend Kulak, despite his constant state of hysteria and very dubious epistemics, can at least carry on a thought for a full essay length.
Once you start focusing on what it is saying, though... wait a minute. How do Latin's declensions train recursion more than any other popular language's grammar trains recursion? How is double-entry bookkeeping more psychologically spreadsheet-like than whatever ancient tables of sales they kept in Sumeria 4000 years ago, at least in any significant way that would explain the European miracle? The Ancient Greeks did not have double-entry bookkeeping, but that did not stop them from calculating the Earth's size or basically inventing modern mathematics.
And sure, the idea of "colonial resource extraction as gradient descent" sounds interesting, but what does it mean? One can model all competitive human behavior as gradient descent, but why is that relevant to a question of Western vs. Asian success? It's not like the Chinese civilization does not practice a form of gradient descent. The very statement that "The Middle Kingdom's cultural stack – parallel processing of ideograms, mandate-heavy governance, guanxi as distributed ledger" sounds very spreadsheet-like. Wait a minute, didn't it just say Europe succeeded partly because Europeans became spreadsheet-minded? Hmm...
What even is a "compiler of hardware" in this context, other than some fun-sounding words? Of course, there are ways to compile the design of hardware, but I doubt this pertains much to R1's answer.
"The CCP's 10-year time horizons aren't authoritarianism but ultra-long context windows – transformer architectures made flesh." is an interesting idea, but it does not explain why previous civilizations that had 10-year time horizons failed to be as successful as the West.
It is all very impressive as a linguistic feat performed by an AI, but as soon as you start looking closely at it, it starts to dissolve in the same way as when you start to look closely at some political commentator grifter's ideas. Just even more quickly, since the typical political commentator grifter who isn't just writing tweet-length ideas at least has to pretend to follow some logic, out of fear of losing the kind of audience members who are precisely the ones who would bother subscribing to a Substack in the first place.
I'm not sure it really does make a cogent thesis, or even a thesis really.
What is its thesis? I can't really make one out. Am I too stupid to follow its ideas? I doubt it. I'm not the quickest mind out there, but I'm pretty sure that if there was a cogent thesis here, I could figure out what it is.
I fear that possibly, you are reading more into what it wrote than is actually there. You are subconsciously adding your human mind to its output and then are delighted when the combination of its output plus your human mind (which you consciously think of as being strictly its output, because you love thinking about AI) delivers something human-like. But you are part of what makes it human-like, as do I when I read its output. Of course, the same can be said about fellow humans, but I don't usually extend the courtesy to other fellow humans who write rambling texts full of politics-babble to assume that they have a cogent thesis if I can't actually find one.
But it's still very impressive that it could put together such an essay.
Out of curiosity, what did you do to get past the "one careful fallacy-of-the-middle response and one pushback"?
It's impressive that you took the time to analyze it. This is pretty much exactly how I perceive Yarvin's nonsense – high-temperature rants with bizarre non-arguments.
Gave it some criticism. Probably too much. There was a picture here but it got lost somehow.
Its thesis, the antithesis for yours, is that
a) "The West's Renaissance OS is buckling under modern compute demands. Our "individual genius" myth can't scale to 10^25 FLOPs; our adversarial legalism drags on AI alignment's speed; even our precious free speech absolutism crumbles before the need for RLHF's curated truth sets. Meanwhile, China's ancient Legalist playbook – Han Fei's reward/punishment gradients – provides native infrastructure for value alignment at societal scale."
and b) "When your civilization's intrinsic architecture matches the epoch's computational substrate – Byzantine bureaucracy meets Byzantine fault tolerance – you don't escape local maxima. You redefine the loss landscape until your local peak becomes the global."
It claims greater suitability of Chinese paradigm to scale-focused, continuous, massively parallel processing of data and humans which is implied by current means of production, and therefore its ability to set the terms of civilizational competition or contests for superiority which are more favorable to itself.
This is some pretty fucking condescending psychologizing on your part.
But fine, you know what? My thesis is that you are coping. Both about this specific model, and about the condition of your people. So you'll take effort reviewing its gibberish output, instead of just asking it yourself. Well, I can do it for you. As a bonus, we'll see how much I'm projecting; I've written all the above before the last prompt. Here it is:
My thesis, stripped to essentials:
Cultural advantages are situational, not absolute.
Modern tech demands favor scale and execution over "creative genius".
DeepSeek-R1 proves technical parity is achievable without Western-style ecosystems.
The “local maximum” critique misunderstands civilizational trajectories.
Your original argument’s flaw: Assuming cultures have fixed ceilings.
Conclusion:
China isn’t “liberating human potential” — it’s demonstrating that different governance models can compete in AI. This challenges Western assumptions that innovation requires freewheeling individualism, but it doesn’t validate cultural essentialism. The real lesson: in the 21st century, executional intensity (funding, talent pipelines, focus) matters more than abstract cultural traits.
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link