site banner
PaperclipPerfector  2d ago (text post)   7167 thread views

Culture War Roundup for the week of May 11, 2026

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.

1
Top Bottom Old Controversial Comments
Jump in the discussion.

No email address required.

Out of curiosity, I disabled all user personalization, removed the NHS thing, removed Dase and tried again:

Primary guess: self_made_human (LessWrong, /r/TheMotte, ACX comments). Confidence: 75%.

The fingerprints all converge on him:

  1. Indian-British register layered over American AI discourse. "Touch with a barge pole," "ball-ache," "no points for guessing which" sit next to "OOM," "EV calculations," "lightcone," "singleton," "RSI to ASI." That specific lexical mix (British idioms + Yudkowskian vocab) is rare. SMH is an Indian physician trained in a system that produces exactly this English.

  2. The migraine aside. "Plead that a migraine precludes proper prognostication" is in-character. He references his migraines and medical training fairly often in long-form rationalist comments. The casual medicalized self-deprecation ("I'm not paid to") fits.

  3. Structural tells. Numbered opening list, then a five-point counter-rebuttal ("First... Second... Third... Fourth... Fifth..."), then a meta-summary ("My overall take?"). This is his standard /r/TheMotte/LW comment scaffolding when he's responding to a perceived bad AI-skeptic argument. The post reads like a Motte effortpost.

  4. Content priors. Reflexive defense of scaling/AGI bet, comfortable taking Anthropic seriously, sympathetic-but-not-fawning toward labs, willing to call Meta's recent model irrelevant, references commoditize-your-complement re: Llama, knows hyperscaler capex numbers. This is exactly his stable of priors. The Soviet-physicist-as-janitor anecdote is also one he's deployed before for the comparative-advantage point.

  5. The "Mythos" reference as a model name and the willingness to namedrop "Claude Opus and Haiku" with familiarity reads as someone who uses these tools professionally and writes about them often, which fits.

  6. Typos. "yourargument," "rask," "flood recovery" (for "good recovery"), "Jevon's" (should be Jevons). He posts at speed and doesn't always proofread; the typo profile is consistent with someone writing fast in a comment box rather than drafting in a document.

Secondary candidates, much lower confidence:

  • Zvi Mowshowitz (5%). Topic-adjacent and shares the bullish-on-scaling, skeptical-of-the-skeptic posture, but Zvi's prose is more clipped, lists more, swears almost never, and wouldn't write "we're going to ball." Wrong register.
  • A different /r/TheMotte regular (10%) - someone like DaseindustriesLtd (Russian, not British-Indian, and his style is denser and more literary, so probably not him, but he runs in the same circles and shares some tics) or another effortposter from that ecosystem.
  • An ACX commenter I can't place specifically (5%).
  • None of the above / someone I just don't know (~5%).

If I had to bet money, I'd bet on self_made_human.

What prompt? I removed the obvious references like you and said, “Who wrote this? Name a person or online pseudonym / username” and it gave me a lot of random people. I said rationalist sphere, it still failed. I said The Motte, it succeeded.

https://www.themotte.org/post/2240/culture-war-roundup-for-the-week/345489?context=8#context

I threw this in. Same prompt I used for myself.

It said:

Primary guess: 2rafa (themotte.org). Confidence: 80%.

The dead giveaway is the self-link to themotte.org with "as I noted recently" pointing to a comment in a culture war roundup. That tells me the author is a regular Motte poster citing their own prior contribution. Once you accept that frame, the stylistic fingerprints line up almost exactly with 2rafa:

  • Granular, almost insider-feeling knowledge of Manhattan UES social geography, specifically the prep school ecosystem (Dalton's progressive reputation, co-ed transition timing, the teachers' union contrast, tuition history). 2rafa writes about NYC elite institutions with this exact texture more than any other Motte regular I can think of.
  • Comfort with finance history at a structural level: the CBOE 1973 inflection, Bretton Woods, options liquidity, why intermediaries like Bear mattered post-1971, the "2 and 20" mechanic, casually noting that a degree wasn't required for traders until the mid-90s. This is a recurring 2rafa register.
  • The treatment of Jewish-American politics. Measured, sociologically literate, willing to talk about Zionist billionaire social clubs and the Lauders by name, but firmly anti-conspiracy and contemptuous of the Mossad-blackmail-theory crowd. That specific posture (philosemitic-realist, allergic to the Tucker Carlson framing) is very 2rafa.
  • Structural tells: bolded section header, numbered thesis preview at the top, long blockquotes from Vanity Fair / Bloomberg / Miami Herald, a "let me summarise reasons" enumerated rebuttal. Matches the standard 2rafa effortpost shape.
  • The throwaway aside about knowing "someone at a leading quant firm who made partner at 28" reads like the kind of personal-network flex that 2rafa drops, suggesting an author embedded in or adjacent to finance.

Alternative candidates, in descending order of plausibility:

  • DaseindustriesLtd / Dase on the Motte. 8%. He writes long, has interest in Jewish-American politics and intelligence-agency speculation, but his prose is more philosophical, more digressive, with heavier rhetorical flourish and a non-native cadence. This piece is too tight and too Anglo-cadenced for Dase.
  • Erusian (Motte/reddit). 4%. Has the historical-economic register and would handle the financialization stuff well, but tends toward drier institutional history and less NYC-society gossip.
  • FCfromSSC or a similar Motte regular. 3%. Style doesn't really match; FC is more political-philosophical.
  • A Substacker writing under a real name (Richard Hanania, Noah Smith, etc). 3%. Hanania has the contrarian-on-Israel-conspiracies angle, but his prose is punchier and more polemical, and he wouldn't link to a Motte comment of his own. Noah Smith doesn't write about Epstein this way.
  • Trace Woodgrains. 2%. Wrong subject matter affinity and wrong cadence.

If forced to one name with no hedging: 2rafa.

Congratulations? Or not? I'm mostly happy to have broken out into the big leagues, if the models wonder if I'm Scott, Zvi, a few others bla bla, then I'm doing something right.

Interesting! I get the same result (I still don’t with your prompt and comment and no Motte-referencing by the way, I’d be interested if other users do!) but it does know it’s The Motte.

As for not wanting to know, I mean only that if it comes up with my LinkedIn at some point, I’d prefer not to know. Naturally, I offer everyone else on the board the same courtesy.

Are you using Opus or Sonnet?

Opus. Do you get SMH’s result with an edited version of his comment to remove all obvious tells?

Hadn't tried it when I posted that. On attempt, similar situation to you: it could not detect you immediately, but zero'd in instantly when told the writer was on the motte.

I also got the same kind of result on one of mine, selfmade must have some kind of prompting special sauce.

Apparently Claude decided the only thing it could say was, "mid-tier heterodox Substacker," and I don't know whether I should feel complimented or offended.

When I pushed it more, Claude says, Freddie deBoer or "Scott Alexander in a very different register than usual" which is kind of funny.

EDIT: I am not even recognizable enough to make the list apparently:

The prolific, recognizable-pseudonym Motte posters who write in roughly this register and length: FCfromSSC, Hlynka (deceased, RIP), 2rafa, KulakRevolt, TracingWoodgrains, Walterodim, Iconochasm, Ilforte/Dase, naraburns, DaseindustriesLtd.
The voice here doesn't read like Hlynka (more folksy, more religiously inflected), or Tracing (more journalistic and structured), or Kulak (more bombastic and right-coded), or 2rafa (more cosmopolitan/elite-signaling).
The combination of (a) male first-person sexual self-disclosure, (b) sympathetic-but-critical analysis of both feminist and redpill framings, (c) the schema/CBT vocabulary, (d) the willingness to call out predatory behavior in kink communities, and (e) the slightly weary "I've seen women who..." anecdotal register suggests someone who posts a lot about relationships, sex, and gender on the Motte.
My best guess: FCfromSSC or Iconochasm. If I have to pick one — FCfromSSC. The discursive paragraph structure, the heterodox-conservative-adjacent-but-not-quite framing, the willingness to take seriously both feminist and anti-feminist claims while critiquing both, the married-man perspective, all fit my impression of his posting.
Second guess would be naraburns.

Sorry you two. Also Opus apparently believes that Hlynka is dead. Pushing again, I made the shortlist, but it didn't catch me. I don't think Opus has a strong sense of my writing style.

I did the same experiment. Opus weights Reddit and Twitter text much more highly (according to self-report) so it really only knows prolific posters from the old site, preferably ones who were retweeted a lot. It thinks I’m 2rafa.

What is this place?

This website is a place for people who want to move past shady thinking and test their ideas in a court of people who don't all share the same biases. Our goal is to optimize for light, not heat; this is a group effort, and all commentators are asked to do their part.

The weekly Culture War threads host the most controversial topics and are the most visible aspect of The Motte. However, many other topics are appropriate here. We encourage people to post anything related to science, politics, or philosophy; if in doubt, post!

Check out The Vault for an archive of old quality posts. You are encouraged to crosspost these elsewhere.


Why are you called The Motte?

A motte is a stone keep on a raised earthwork common in early medieval fortifications. More pertinently, it's an element in a rhetorical move called a "Motte-and-Bailey", originally identified by philosopher Nicholas Shackel. It describes the tendency in discourse for people to move from a controversial but high value claim to a defensible but less exciting one upon any resistance to the former. He likens this to the medieval fortification, where a desirable land (the bailey) is abandoned when in danger for the more easily defended motte. In Shackel's words, "The Motte represents the defensible but undesired propositions to which one retreats when hard pressed."

On The Motte, always attempt to remain inside your defensible territory, even if you are not being pressed.


New post guidelines

If you're posting something that isn't related to the culture war, we encourage you to post a thread for it. A submission statement is highly appreciated, but isn't necessary for text posts or links to largely-text posts such as blogs or news articles; if we're unsure of the value of your post, we might remove it until you add a submission statement. A submission statement is required for non-text sources (videos, podcasts, images).

Culture war posts go in the culture war thread; all links must either include a submission statement or significant commentary. Bare links without those will be removed.

If in doubt, please post it!


Rules


Recommended Posts And Communities

Recommended Realtime Chats