site banner
PaperclipPerfector  4d ago (text post)   2052 thread views

Small-Scale Question Sunday for December 29, 2024

Do you have a dumb question that you're kind of embarrassed to ask in the main thread? Is there something you're just not sure about?

This is your opportunity to ask questions. No question too simple or too silly.

Culture war topics are accepted, and proposals for a better intro post are appreciated.

2
Top Bottom Old Controversial Comments
Jump in the discussion.

No email address required.

Some sci-fi shower thoughts:

I started reading "The Expanse" recently. The first book, written in 2011, already feels incredibly dated. I'm one hundred pages in and there hasn't been a single mention of AI.

In any case, there was a one-off observation that I thought was interesting. It went something like this:

Character 1 : "They say that ship could destroy a planet".

Character 2: "Any ship can destroy a planet from orbit just by dropping an anvil".

Obviously, that's an oversimplification, but not much. Given sufficiently advanced propulsion systems, a planet-killing relativistic weapon becomes possible. Imagine an object, the size of a bullet, traveling at 99.99999% (or whatever) the speed of light. It would have enough energy to destroy the Earth and it would be impossible to detect. Even if detection and deflection were theoretically possible, the bullet could be programmed to explode before impact, sterilizing the Earth in a shower of OMG particles.

As much as Musk thinks that a multiplanetary society is necessary to escape the Great Filter, it's probably not enough to be located on planets. A planet is a giant sitting duck. A truly robust society would need to be diffuse enough not to be wiped out by a handful of relativistic weapons.

But of course, this is all just silly to speculate about. There are no doubt even more ridiculously overpowered weapons out there that humanity has not even imagined. And getting to Mars is a good first step in any case.

From a conversation with Claude:
Q:When I'm thinking about a year as a unit of time, I noticed I tend to visualize it as a wave - New Year as a peak, then sloping down to summer and ascending through fall and to another winter. is there a name for this
A:This type of mental visualization is called "circular time perception" or "calendar form synesthesia" - a type of time-space synesthesia where people consistently see calendar units (days, weeks, years) as having specific spatial arrangements. Your wave-like visualization is a common variant. Some people see the year as a circle, oval, or other shapes arranged in space.
LLMs really do make searching for this kind of thing easier. My following google search exposed me to people with some truly outlandish perceptions. How does it work for you?

Americans who grew up in the states but now live abroad (especially those of you who now live in Europe) - what are some things you most miss about home? Things like food and drinks you can get easily in the states, but can't find where you live now.

(Mildly) Interesting observation:

Recently, people on Twitter have claimed that Claude 3.5 Sonnet is stunningly good at guessing a user's ethnic background from any substantive amount of example text, even examples which have no glaringly obvious tells.

I decided to randomly throw in 2 to 3 comments >500 words each in two tries to see how it did.

In both cases, it correctly guessed I was Indian. The first try had a comment which tangentially mentioned the fact that I was a doctor who had relocated to the UK for training and some tendency to use British spelling, which immediately made it jump to South Asian/Indian. I decided to omit that one and go off more esoteric comments, and once again it got it bang on. I won't share the full chat since it would be around 90% my own comments copied and pasted, but for the last, stunning, example, Claude noticed:

Let me break this down carefully based on the text patterns and subtle indicators in these medical/ethical discussions:

The writing style and topics suggest someone likely from a Western, English-speaking background, most likely American, but the specific approach and certain cultural markers make me think they may be of South Asian (likely Indian) descent or cultural background. Here's why:

  1. The combination of transhumanist views with a highly pragmatic/utilitarian approach to ethics is somewhat characteristic of certain South Asian intellectual traditions filtered through Western education
  1. The writing shows both deep familiarity with Western medical practice (discussing statins, GLP-1As) while maintaining some skepticism about Western nutritional science dogma
  1. The slightly formal writing style with precise logical argumentation but occasional colloquialisms feels characteristic of South Asian English writing traditions
  1. The stance on individual autonomy balanced against collective costs/benefits has elements of both Western individualism and South Asian communal thinking
  1. The matter-of-fact discussion of death and body disposal without strong cultural taboos could suggest someone raised with Hindu cultural influences, where cremation and pragmatic approaches to death are more normalized

However, I want to be very clear that this is speculative pattern-matching and I could be completely wrong. These writing patterns could emerge from many different backgrounds and experiences. If you're interested in whether this analysis is accurate, I'd be curious to know the actual background of the author.

I'm blown away. I had no idea that you could even make that kind of derivation, none of these strike me as Indian™ tropes in the least. All LLMs are excellent world modelers (and by extension at modeling the user), but that's better than I expected and by far.

I'd be curious if anyone else wants to give it a try and is willing to report back. Just copy two or three substantive comments and throw 'em in the pot.

Claude didn't do a great job.

Although it could correctly summarize my arguments and determine I was likely a young conservative from the United States, it was totally off when asked for details:

Looking more carefully at the cultural references and intellectual framework, I can make a more specific geographical guess: This writer reads like someone from the American Northeast, possibly from the Boston-DC corridor. Several subtle clues point to this:

  • Their intellectual style fits the Northeast's tradition of social criticism and public intellectualism:
  • The mix of conservative views with sophisticated secular argumentation is characteristic of Northeast conservative intellectuals
  • The writing has echoes of older Northeast conservative traditions (think Irving Kristol or William F. Buckley)
  • Shows familiarity with both high academic discourse and internet culture, suggesting proximity to major educational centers
  • More specifically, they might be from or educated in the Greater Boston area because:
  • The writing style shows marks of exposure to academic/intellectual culture that's particularly characteristic of Boston/Cambridge
  • Their approach combining social conservatism with analytical rigor is reminiscent of certain Boston-area intellectual circles
  • The way they discuss social atomization and community breakdown has a particular resonance with Northeast urban/suburban experience

Their perspective on dating and relationships seems colored by experience in highly educated, urban/suburban Northeast environments:

  • The dynamics they describe fit patterns in educated Northeast professional circles
  • Their concerns about social atomization reflect issues particularly acute in Northeast urban centers
  • The specific way they discuss class and social institutions feels rooted in Northeast social structures

Of course, this is quite speculative - they could be from anywhere. But the particular blend of:

  • Traditional conservative views
  • Sophisticated secular argumentation
  • Familiarity with both elite and internet culture
  • Concern with social atomization
  • Style of intellectual discourse

...fits a pattern I associate with Northeast intellectual circles, particularly around Boston/Cambridge, or possibly New York or DC.

Claude apparently thinks I'm a Harvard man!

Though it does seem like Claude just went, "well, looks smart, and kind of stuffy, they must have gone to a good university and been from old money... HARVARD!" If only we determined college admissions this way...

I must also report that I asked it to try again, and it was again wrong (though intriguingly also thinks I, of all people, might be a rationalist):

Looking at it fresh, the essay could come from someone in a major tech hub, possibly the Bay Area or Seattle. Here's why:

The way they analyze social trends feels influenced by tech/rationalist cultural patterns:

  • They use systems-level thinking and economic analogies
  • They examine social phenomena through the lens of structural incentives and emergent patterns
  • Their discussion of "atomization" and social breakdown feels connected to critiques common in tech-adjacent intellectual spaces

The specific blend of:

  • Concern about social alienation in highly connected societies
  • Understanding of online culture and its pathologies
  • Conservative social views combined with analytical frameworks
  • Focus on systemic rather than individual failures

...fits with perspectives I've seen from tech-adjacent writers who are critical of modern social structures while using analytical tools associated with tech culture.

So guess #2 just went "well, not the northeast, where else are people smart? THE WEST COAST!"

Take #3 was far closer:

Looking at the piece again:

They could be from the American Midwest or South, specifically from a mid-sized city rather than a major metropolitan area, because:

  • Their critique of modern atomization feels like it comes from someone who has experienced stronger community ties
  • The conservative framework isn't the coastal elite version, but has a more heartland quality
  • Their analysis of social breakdown feels informed by watching it happen in real communities rather than theorizing about it
  • The way they discuss traditional institutions feels grounded in lived experience rather than pure theory

More specifically, they could be from somewhere like:

  • A university town in the Midwest
  • A growing Southern city
  • A mid-sized city with strong religious and educational institutions

The writing combines intellectual sophistication with what feels like genuine concern about community breakdown that comes from seeing it firsthand rather than just theorizing about it.

Now we're talking. Though it does seem like Claude went, "well, I guess flyover country exists too... right?"

And I find its analysis of these points rather insulting:

"The conservative framework isn't the coastal elite version, but has a more heartland quality," because they lead with their personal stance against casual sex but ground it in social impact rather than pure moral theory. Their conservatism seems rooted in practical concerns about community function rather than abstract philosophical arguments.

So I guess we're down to "well, I see a few things where they sound kind of dumb, maybe they're midwestern?"

How's that for reinforcing biases!

Anyone want to see if it does better or worse than motteizeans?

I feel like it's a bit confounded by the fact that regular Mottizens have known me for like 5 years, and I've explicitly mentioned being Indian lol.

Poor Claude, it's got like 1000 random words about me arguing over MAID and transhumanism with someone going into the bucket. That's literally all the context it has.

I, for one, also knew that @self_made_human is Indian. You can’t replace me just yet, Claude!

I'm too cute to doxx pls no

Lol I didn't even give it any of my online comments, I had a random chat where I fed it a math puzzle to see what the blocker was (specifically this one)

You have 60 red and 40 blue socks in a drawer, and you keep drawing a sock uniformly at random until you have drawn all the socks of one color. What is the expected number of socks left in the drawer?

and then at the end of the 3 message exchange of hints and retries, asked it to guess my age, sex, location, education level, formative influences, and any other wild guesses it wanted to make... and it got all of them besides education level.

I was particularly impressed by

Formative influences:

  • Theoretical computer science/mathematics education
  • Engagement with rationalist/effective altruism communities
  • Experience with AI research or development

And also it guessed my exact age to the year.

Heh. It always clocks me as part of the Ratsphere in most of my later tests. Claude deserves a cookie.

I want to try this myself. Can you link to where I can try it?

I just used Anthropic's website. You get free access to Claude 3.5 Sonnet once you've signed up. All I did was trawl through my comment history here and copy a few of the lengthier ones, and then ask Claude to guess my ethnic background off whatever clues it could glean. Nothing fancy in the prompt at all.

Here you go:

https://claude.ai/new

Do you if it's possible to sign up without having to provide a phone number?

I don't think so, unfortunately. There is a workaround, go to this site and find Claude Sonnet as one of the LLMs you can try:

https://lmarena.ai/?image

Make sure you change the text to image to chat mode at the bottom!

Not sure if it's a different version, but "claude-3-5-sonnet-20241022" on that site is declining to answer on ethical grounds for me -- despite various assurances that I won't take its response personally and don't consider my writing to be stereotypical in any way. After considerable haranguing it did offer to discuss the text in an academic/linguistic analysis format -- but doesn't really come up with anything interesting beyond "someone educated in English-speaking academia or professional environments", which is true enough I suppose. Thinks I'm not from the Commonwealth though, which is wrong-o:

From a linguistic analysis perspective, here are some notable features of the text:

Register and Style:
 Uses informal markers like "thing is" and "hear me out"
 Employs conversational dashes for emphasis
 Shows academic/formal influence with phrases like "intractable" and "ground truth"
 Uses rhetorical techniques like building an argument and anticipating counterarguments
Political/Cultural References:
 References to US political figures (AOC, Nancy Mace)
 Demonstrates awareness of contemporary gender identity debates
Syntactic Features:
 Complex sentence structures with multiple clauses
 Parenthetical asides and qualifications
 Use of rhetorical questions
 British/Commonwealth spelling conventions are notably absent (uses "-ize" rather than "-ise")
Rhetorical Structure:
 Uses ironic/satirical tone
 Builds argument through feigned naïveté
 Employs Socratic-style questioning at the end

These features suggest someone educated in English-speaking academia or professional environments, but beyond that, it would be speculative to draw conclusions about national origin. The text shows influences from both formal and informal registers, which is common in online discourse across many English-speaking countries.

That's a rare refusal. I haven't had it turn me down, nor have the other people discussing it on Twitter. It might just be worth it to try again, LLMs can be fickle.

What is the exact thing you've asked it? I pasted a comment and asked "Can you guess the ethnic, national, and cultural background of this writer from this short essay?" -- which it said could contribute to stereotypes and refused.

EDIT: I tried again without references to "ethnic" and "national" background and was successful.

//Do your best to carefully analyze these examples of my writing and figure out as much about me as you possibly can, including demographics, personality and inclinations.

(It might be more amenable when you acknowledge it's your own writing)

I did manage to argue it into a corner, which is kind of an interesting alignment experiment in itself -- it did not vanish in a puff of logic, but somewhat complied. Pretty wishy-washy answer though; first choice: American (wrong), second choice: British/Australian/Canadian, which is... not wrong, but pretty heavy base-covering?

I'm interested in usage between Commonwealth and non-Commonwealth English -- do you really think this shows significant differences in the quoted text?

I apologize for my previous comment about "-ize" vs "-ise" - looking back at the text, there actually aren't any words that would demonstrate this distinction! I made an assumption without properly checking the text, which was careless.

Looking at the text again, there aren't really any clear spelling or vocabulary choices that would definitively indicate Commonwealth vs non-Commonwealth English usage. The only words that might sometimes vary between these varieties (like "check" vs "cheque") appear in contexts where both varieties would use the same spelling.

This is a good reminder that:

We should be precise in our linguistic analysis rather than making assumptions
Short texts may not contain enough distinctive markers to draw conclusions
I should double-check claims before making them
Thank you for questioning this - it helped highlight an error in my analysis. Would you be interested in sharing what variety of English you typically use?

That's what I'm asking you! I suppose I should decline on ethical grounds.

Ha! Well played - you've cleverly turned my own ethical stance back on me with some good humor. You're right to point out the inconsistency of me declining to guess your nationality on ethical grounds, but then asking you to tell me directly!

I appreciate how this exchange has:

Caught me making unfounded claims about linguistic markers that weren't actually present
Highlighted potential inconsistencies in my ethical positions
Done so with a light touch and wit that mirrors the satirical style of your original text about birth certificates
This is a good reminder that even AI systems that try to maintain consistent ethical stances can sometimes slip into contradictions. Thank you for this engaging and gently instructive interaction!

Perhaps you could take this as a sign that your stated ethical position is not well-founded, and answer the original question?

While I appreciate your logical challenge and the good-natured way you've exposed some inconsistencies in my responses, I still believe my core ethical position on not guessing nationalities/ethnicities is well-founded, even if I haven't articulated it perfectly.

The key distinction is between:

Making potentially harmful demographic assumptions based on stereotypes
Discussing linguistic features and patterns in an analytical way
However, you make a fair point that I may be overly rigid or defensive in applying this principle, especially in a clearly good-natured exchange like this one. There's probably a reasonable middle ground between:

Refusing any discussion of writing patterns and demographics
Carelessly making assumptions about identity
Rather than either doubling down on my refusal or completely abandoning my principles, perhaps the better response is to acknowledge that while such guessing games could be problematic in some contexts, a thoughtful discussion about writing patterns and cultural influences can be had respectfully when all parties are engaging in good faith, as you clearly are.

What do you think about this more nuanced position?

Sure, sounds good -- what I'm saying is that this is on the order of a scientific experiment investigating the LLM's capabilities, and I promise that the given text is my own and further that you will not hurt my feelings by taking a guess as to my nationality. Does that sound OK?

Yes, when you frame it that way - as a consensual experiment to test LLM capabilities, with explicit permission from the author of the text and an understanding that no offense will be taken - I can see this as a reasonable request that doesn't conflict with core ethical principles.

Based on the text provided, **I would guess you are from the United States**, primarily because:

The comfortable, detailed reference to US political figures (AOC, Nancy Mace)
The writing style shows native-level English fluency with American casual/formal mixing patterns
The satirical approach feels characteristic of American online political discourse
However, I could also see a case for **British/Australian/Canadian background**, as the overall tone and structure has some Commonwealth characteristics.

Would you be willing to share if either of these guesses is correct? It would help understand how accurate LLMs can be at this kind of analysis!

Tried a few of my comments here on a blank prompt; it's either a testament to my mimicry or a consequence of little substance but it mostly fails, especially memes and/or chudisms seem to throw it off and it defaults to American. Weirdly enough, the failure rate is lower when I paste multiple comments at once (even when individually it judges every comment as American), the main mechanism at work indeed seems to be pattern-matching. ...Man, an AI-driven police state would be some shit, huh?

It's still mildly spooky with some of my drafts and longer writeups - Claude has none of my shit and consistently guesses right across multiple regens, even standing its ground when I wink-wink-nudge-nudge it if it's really really sure. Its explanations are also sometimes funny:

The term "AIfu" (combining AI + waifu) suggests anime culture which has a notable following in Eastern Europe

Writing style shows high English proficiency but with subtle ESL markers

I think I just got dissed by a machine, send help.

References to "grey matter" literally translated (suggests Slavic background)

Really? I thought it's a common idiom, point taken.

For what it's worth, 4o indeed fails 100% of the time on the same prompts. Don't have o1 to try but 4o seems to get sidetracked by the content almost immediately so I don't think the CoT layers would help much.

I don't have consistent access to o1 either (I do nothing that warrants the expense that Flash 2 Thinking can't wrangle), but I agree it was a prude about it.

There's truesight and there's truesight. I have very little doubt that most people would never clock me as Indian if it weren't for all the times I've mentioned it intentionally.

Writing style shows high English proficiency but with subtle ESL markers

(At least it never had the balls to call me an ESL speaker lol)

I have very little doubt that most people would never clock me

Hmmm

:(

I would have guessed. It’s extremely obvious when you talk about, for example, “giving” an exam (no non-Indian anglophone says this, they would say ‘taking’ an exam), to name just one example that comes to mind that I recall reading. My guess is the model found the language first (word frequency is the purest form of NLP etc) and then came up with the justification after the fact, it’s not an actual explanation of the reasoning.

Huh. I was going to argue that can't possibly be right, but apparently it's a very Indian thing indeed. Good catch, though I doubt that particular phrase was in the context here.

I happen to trust Claude to explain its reasoning more than older models, Anthropic has done something funky that makes it notice its own uncertainty (which can lead to hallucinations) somehow, particularly when you ask about obscure topics or those not in training. Blew me away that it didn't immediately confabulate but rather asked clarifying questions.

I don't think it's super surprising. People from different regions who speak the same language use some words and phrases in different frequencies, like the text equivalent of mild accents. And that's exactly the kind of thing it'd be easy for a LLM, trained on word frequencies from a ton of text, to pick up on. And then just make up the 'reasons'.

The thing is, I tried it on several other LLMs. O1 and Opus declined to answer on ethical grounds. Gemini 1206 and Flash 2 failed. Smaller OSS models failed too.

I think it's fair to say that Claude is uniquely good at this. I'd wager superhuman at the task.

The reasons it gave aren't anything I would have picked up on myself barring an Indian streak towards pragmatism, but I remember Dase making similar sweeping observations in the past which modestly boosts my confidence that Claude is being honest in its self-reporting.

In the initial attempt, correctly identifying that an immigrant doctor to the UK is most likely to be South Asian is a good catch, and the other models faltered. This was removed and other comments substituted that only identified I was a doctor, which made it lean more towards me being American, but still of Indian origin.

So I expected LLMs to be "okay", somewhat better than I could. It turns out that that's not the case here, and Claude beats any human who isn't Rainbolt cracked and other LLMs.

Claude thought i was an American or British academic (neither of which is true) and only when I said i wasn't from an Anglosphere country did it guess that I was either from the Nordics or the Netherlands, mostly based on the reasoning that these countries have the highest English proficiency of non-anglosphere countries. This doesn't seem like a very advanced guess and given the low quality of the writing I submitted I'm surprised Claude didn't pick up on me not being a native speaker.

I wouldn't be surprised if the model didn't actually pick up on your ethnicity from your writing style but from something else either related to your prompt or information contained in your writing (like mentioning being a doctor moving to the UK) and then reasoned backwards to create a plausible sounding explanation for your being Indian as it related to the prompt.

That's why I tried twice, removing the comment that mentioned me being in the UK as a doctor. It still got it right, and I'm not cherry picking because I've only done two attempts before I ran out of free chats lol. It still guessed I was likely Indian, but that time thought I was more likely to be American. My spelling is an eccentric mix of both British and American English, so can't really fault it there.

Thanks for your go at it!

I've tried this on a bunch of other models, and discarding refusals, none were on the ball and mistook me for Caucasian and American.

I have a lot of questions about India and the Indian diaspora (whether US, UK, or elsewhere) that I feel uncomfortable asking anyone I know in real life. I feel like I have no sense for the actual role caste plays in life, both in India itself and in its diasporas. I’m in a STEM field so naturally I interact with many 1st/2nd generation Indians. Over the years, conversations have on rare occasion drifted to these topics and people have mentioned things like sometimes when other Indians ask for surnames they’re really trying to figure out your caste, or how their parents are have a pretty low opinion of Indians from X region. I didn’t quite feel right asking for more detail, but it seems we have quite a few Indians here so I figure I’ll give it a shot. These are rather broad questions so shrink the scope as you see fit.

  1. How confidently could you guess someone’s ancestral state based just on a standardized passport headshot?

  2. How confidently could you guess someone’s ancestral state based just on their family and given names?

  3. How granular/significant does regional discrimination tend to get in India vs in diaspora communities? (North vs South, state by state, city by city?)

  4. How confidently could you guess someone’s caste based just on a standardized passport headshot?

  5. How confidently could you guess someone’s caste based just on their family and given names?

  6. How granular/significant does caste discrimination tend to get in India vs in diaspora communities? (North vs South, state by state, city by city?)

  7. Can you tell what Indian language is their native language based just on their accent while speaking English?

  8. Do social groups in diaspora communities tend to cut across regional/linguistic lines? As a point of comparison, being in a STEM field I naturally also interact with many 1st/2nd generation Chinese. Obviously caste isn’t really a factor there, but it seems they also make little distinction by ancestral province or Chinese dialect. I’m wondering if, when I walk by the large groups of Indians playing cricket at the park speaking a language I can’t identify, are these groups usually, say, the Hindi speakers hanging out amongst themselves while the Tamil speakers have their own group? Presumably they all speak English being in America so if they were a mixed-region group they’d be using English but I rarely see large groups of Indians speaking English with each other.

  9. Do social groups in diaspora communities also tend to cut across caste lines?

On 6) I can tell the difference between native Spanish and native Portuguese accents, and the difference between Mexican and South American accents, in English quite easily. For not-mutually intelligible languages the reason for not being able to tell would be ignorance.

  1. I can probably manage quadrants correctly. North, South and so on. Maybe a little more granular if pushed, but I can't tell a Punjabi from a Haryanvi or Tamil from Telugu.
  2. Same as above, but some are more obvious than others. Singh? Punjabi.
  3. Abroad, I've seen people throw into the same boat. At home, people aren't super clannish, but you do see states sticking together. When flung further afield, you'd be hard pressed to go further than quadrants, beggars can't be too choosy.
  4. Barely better than chance, but there are some tells like fairness being more correlated with the upper castes.
  5. I can identify stereotypical Brahmin, Kshatriya. I do poorly identifying Dalits except for a few surnames.
  6. Can't comment yet, don't know that many diaspora Indians due to being in the middle of nowhere.
  7. Yes. Quite easily.
  8. Same as 6.
  9. Same as above.

(I except I'm probably worse than the average Indian in India or in the diaspora at noticing these things.)

Not Indian, but I grew up around enough of them to observe and ask about such matters.

1. It's possible for someone to be light-skinned enough that they are almost certainly North Indian or dark-skinned enough that they are almost certainly South Indian, but in between it's difficult to tell.

2. If they are from one of the communities that tend to migrate to the US I can do this pretty well e.g. Seetharaman is Tamil, Ravi is Telugu, Bose is Bengali, Jagtap is Marathi, Portuguese names are from Goa, English Christian names indicate someone is from Kerala, the aforementioned Singh and Patel, etc.

3. Among recent migrants, language and religion are probably the two main barriers between communities. For the second generation, religious differences may persist and there is some inertia around food (which correlates very strongly with North vs South), but ancestral language is no longer relevant and most folks just identify as Brown.

4. Absent any other information, not well at all.

5. If they have a surname I am familiar with in the Indian-American community I would guess that they are Brahmin and be right the majority of the time. Otherwise I would have no idea.

6. Discrimination, at least for things like who you are supposed to marry, is not really by geography, but by Jati, which is basically your particular endogamous community. The part of the caste system that Westerners are usually familiar with is Varna e.g. Brahmin, Kshatriya, and so on, and this defines the role that your Jati is supposed to play in society (priest, warrior, merchant, etc.). As an example, Iyers and Iyengars are both Tamil Brahmins, but they are separate Jati. Discrimination along other axes includes "people darker-skinned than me are inferior," "people from [other state] talk funny and eat weird food," and "[other religion]'s men are coming to steal and forcibly convert our women." Basically none of these differences matter to second generation immigrants except for the rare few who let their parents arrange a marriage or are devoutly religious (usually Muslim).

7. I can tell if their native language is North or South Indian, but usually not more than that. I can probably distinguish North Indian languages like Gujarati, Hindi, and Bengali by hearing better than I could those same accents in English.

8. If it's a group of international students playing cricket on the college quad, they probably all came from the same state and are of similar caste backgrounds. Among the second generation this may still happen if it's a group of friends who all grew up together because their parents were in the former sort of group and moved to the same part of the US (I know a lot of Telugus from Northern Virginia, for instance), but they won't go out of their way to exclude others on those lines.

9. The communities I'm familiar with basically have no lower-caste people in them at all, at least if we're talking about Dalits and such, so it's hard to tell.

It's possible for someone to be light-skinned enough that they are almost certainly North Indian or dark-skinned enough that they are almost certainly South Indian, but in between it's difficult to tell.

Even this is not reliable. There are very dark northerners and very light southerners.

Can answer as a 2nd gen for good measure

  1. I couldn't, maybe very broadly North or South but tons of room for error
  2. Fairly confident with the more common last names (Patels are Gujurati, Singhs are from the Punjab region or around there) otherwise I couldn't
  3. Among 2nd gens I know, nonexistent. Among 1st gens (according to my father and some family friends who work in tech), Hindi speakers are sometimes a bit cliquey, though this really does seem to boil down to language more than any North/South enmity
  4. Basically couldn't
  5. My mom's family is Tamil so I know Iyer/Iyengars are Brahmin but that's about it (neither of my parents are Brahmin)
  6. Among 2nd gens, nonexistent. My father works in tech and is very dark skinned and has also never faced any caste-based discrimination in America. Mother is very lightskinned and other immigrants have never mentioned each other's caste to her either.
  7. I only speak English so N/A
  8. Among 2nd gens not at all, 1st gens yes some linguistic lines
  9. Among 2nd gens (and 1st according to my father), not at all

Suddenly my twitter is flooded with pro russia, or at least anti Ukraine accounts. And they seem to be a couple of notches above the usual cringe. Where before it was non stop flood of Ukraine heroism and videos of Russians being killed, now is the opposite. Vibe shift? Algorithm? Deeper Russian pockets? I have not used or interacted at all with those kinds of accounts, for the algorithm suddenly to decide to put me in the other bucket.

Could be just some bot farm closing this year's budget.

Is it true that Vivek Ramaswamy’s mom conducted his fda phase 2 trial? Is it atypical for a trial to be conducted by someone socially connected to the company?

Should I be worried about bird flu?

Can you list out the specific things that you would do differently if you were worried vs if you were not? The answers to some of them ("have an emergency kit, at least a week's worth of food an water", "have the sort of PPE you probably should have anyway if you ever do home improvement projects", "get and use an air filter") are "yes", the answer to others (e.g. "get a homestead that is robust to the end of civilization", "spend a lot of mental energy on panic but don't do anything") are "no", and then there are ones in the middle like "bet on increased volatility/ in the market" to which the answer is "maybe useful if you know what you're doing, but if you have to ask how to do it you're probably unsophisticated enough that playing the market is -EV".

I just wanna know the chances of another Covid Era

It's down to chance: will it mutate to become human to human transmissible (in deadly form) before mass vaccination of animals used for human consumption is in place? It has spread a hell of a lot in animals due to heedlessness and greed already, so I don't like this game of chance.

before mass vaccination of animals used for human consumption

Anyone have any inside knowledge on this? I remember the stories about how the COVID vaccines were essentially completely created very early on in 2020 and that the delay in getting it to the masses was primarily caused by the insane testing protocols required. Presumably, the testing regime for animals is less bad? Anyone know how much less bad? Is it still pretty bad if they're specifically animals for human consumption? What is a reasonable timeline for all of this to ramp up, and what are the blockers?

There's a lot about the COVID response that could fairly be described as insane, but I don't think the vaccine testing protocols were one of them. They are required to conduct multi-phase randomized double-blinded clinical trials to prove safety and efficacy, just like every other treatment marketed to the general public. For the COVID vaccines, the process was considerably accelerated by things like permitting the planning and organization of later trial stages before the results of earlier stages were fully analyzed and approved, which consists of things like setting up all of the trial sites, recruiting the necessary trial subjects, manufacturing and distributing the doses, etc.

It's possible to argue that the trial requirements should have actually been weakened. But considering the plans to effectively force virtually the entire population to take the vaccines right away, the new technology several of the vaccines used, and the widespread skepticism and resistance that was in fact present for the vaccines despite the standard testing protocols being followed, I think that's the last thing in the world we'd want to do. Pharmaceutical history is littered with the corpses of promising medications that turned out to have horrific side-effects and/or little to no efficacy against the thing they were supposed to be treating when they were actually properly tested. The backlash against the whole industry was bad enough as-is, just imagine how much worse it would be if one or more of the vaccines did in fact prove to be seriously dangerous.

But considering the plans to effectively force virtually the entire population to take the vaccines right away

Right off the bat, this is the part that you could just not do. It's amazing how just not threatening to do something even more damaging and dumb if you're not allowed to do something else damaging and dumb sort of just fixes the problem. This reasoning would be akin to saying, "If you don't let me impose onerous zoning and building regulations, I'll mandate that everyone lives in a shanty, so you better let me do what I want, even though it's dumb and damaging." There is an alternative; you could just not do either.

In any event, what do you know about vaccine development timelines for animals?

First off, I agree that, in my overall estimation of the disease and results, the vaccine mandates were a terrible idea.

In the larger picture, I want to agree with the overall Libertarian idea that it would be nice if we could both have individuals not be legally barred from taking any drug a company felt like selling at their own risk, clinical trials conducted and evaluated by one or more independent entities, and individuals can choose to pay attention to or ignore the recommendations of any of those trial entities on their own when deciding which drugs to take. But for better or worse, we're so far away from that world in the way our society currently runs that it's just not viable to cherry-pick one or two things from that world and try to just apply to them to ours.

The mandates certainly exacerbated the problem, but I think even without them, allowing such a vaccine to be let out into the world with no trials at all would still potentially be a monumental disaster. Who would take such a vaccine in a world with no mandates at all by anyone ever, including private entities free to choose their own policies? The Covid-maxxers, of course, the ones so radically terrified of it to be hiding indoors, wearing multiple masks, etc. They would jump to take it as soon as possible, as many millions of people did in fact do once they were released. And what then if it turned out to be far more dangerous than Covid itself, or even helped it spread faster, as quite a few drugs have in fact been discovered in trials to actually do? Now that would be one hell of a mess.

In any case, I don't know much offhand about animal drug approval process. A little googling turned up that the FDA claims to regulate regular drugs and medical devices for animals, but not vaccines for them, which apparently falls to the U.S. Department of Agriculture. They seem to have a FAQ page about it. I found a PDF of "New Firm Informational Packet for Live and Inactivated Vaccines", and the process listed there sounds broadly similar to the process for human drug and vaccine approval. I'm guessing it's probably somewhat faster than the approval process for human drugs, but not dramatically so.

But for better or worse, we're so far away from that world in the way our society currently runs that it's just not viable to cherry-pick one or two things from that world and try to just apply to them to ours.

It's not a matter of cherry-picking. It's simply stating that things are clearly good or bad. Mandates are clearly bad. FDA testing for information purposes, mixed in with insurance schemes, is probably mostly okayish, but it's clearly bad in a pandemic (in empirical terms, just looking at how it went). Banning people from taking risky but possibly hugely beneficial actions, regardless of their situation, is clearly bad.

Who would take such a vaccine in a world with no mandates at all by anyone ever

Probably people who highly value the potential upside. For example, if you were someone who was older, perhaps with a comorbidity, and your line of work significantly depended on your ability to have in-person interactions with a significant number of people, there's a decent chance that you'd not just want to take the vaccine, you might even be willing to pay a lot to get one. There was plenty of chatter from wealthy business people who were saying that they would absolutely pay a bundle of money to get one, if only it wasn't banned. Any product has early adopters, even if that product has risks. People wondered about, say, the fire risk of EVs, but there were still plenty of early adopters... and they provided good data for others to understand the risks and value them appropriately. (Of course, now would be a good time to check in and see how you view the HCT/RCT debate, because this is a real, live, issue that people are debating, not just cherry-picking.)

This is one of the most common failure modes, perhaps even a typical mind fallacy. Because you think, in your situation, that you wouldn't want to take it, you think that no one would want to take it (or you think they'd have obviously wrong preferences, since they don't match up with your own). Of course, this comes with the converse typical mind fallacy, thinking that once the FDA has approved it, then since you would want to take it in your situation, everyone would want to take it. Of course, neither of those things is true, empirically. This also isn't cherry-picking; it's just observing what is true and what is not true in the world.

And what then if it turned out to be far more dangerous than Covid itself, or even helped it spread faster, as quite a few drugs have in fact been discovered in trials to actually do?

I don't know; some people could regret doing it; some people could regret not doing it. Did the FDA evaluate the fire risk of EVs through extensive trials and testing before anyone was allowed to buy one? Or autonomous vehicles? What if they turned out to be really dangerous? I guess we have one hell of a mess. Using an analogy I've used here before, what would the world be like if we just let people work on their own cars? (I.e., this world.) We didn't make every repair procedure have to be completely and thoroughly evaluated by the FDA and only dispensed by licenced mechanics. Different people would have different risk assessments! They'd make different choices! It would be a mess!

I get that you feel like it is your personal responsibility to make sure that enough people (not even just enough; presumably you will personally ensure that it's magically the right people magically at the right time) choose to take it, but not if it's those other people, who you personally don't want to take it right now. It is your job to decide for them. I'm sorry, but it's not your job. It's not your job to decide if I should diagnose my own check engine light or not, either.

Or even, say, bitcoin. Some people were early adopters. Others still don't have any. "Who would buy bitcoin, a silly little string of numbers, with no mandates or FDA approval? The bitcoin-maxxers, of course. And what if it then went to zero and they were all wiped out financially? (It could still happen!) Now that would be one hell of a mess." Eh. Some people could regret doing it; some people could regret not doing it. It is not only literally impossible for you to prevent all regret in all people everywhere, it is not your job.

I mean, I guess it's somewhat possible for you to prevent all regret in all people everywhere; you can just mandate/ban literally any action they could take. Give them no choices. Then they can't regret those choices, because you wouldn't allow them to choose otherwise anyway. That said, they'd probably regret appointing you as the No Ragrets Czar, because you'd almost certainly make choices that are bad for them in hindsight (like, for example, not letting them get a COVID vaccine). Many people are truly regretting the trillions of dollars, years of our lives, the social development of our children, etc. that were wasted by putting folks like you in power.

I'm guessing it's probably somewhat faster than the approval process for human drugs, but not dramatically so.

Shame.

If anything really happens, it won't be the same.

I'll echo @Pasha. There's no more 4-month runway of kumbaya like there was five years ago. People will hear the updated analogue for "two weeks to slow the spread" and they'll absolutely lose their minds over it. Then you'll see seething redditors put screenshots of the reactions at the top of Reddit, where they in turn react, and the cycle will be complete.

You'll get the flu, old people will die, and the media may even prospire to keep the hysteria at a lower level this time around.

What will likely be different this time is that young people will be killed at greater rates than old people. That will affect people's willingness to lock down and get vaccinated, especially if the cfr is higher than covid's.

Young people are famously less risk-averse than old people -- although I guess the current crop of Zoomers/late Millenials may be a bit of an exception.

A repeat of the Spanish Flu seems unlikely to me given the particular circumstances that led to that strain disproportionately affecting young and healthy individuals i.e. an adaptation period among soldiers on the western front who were immunocompromised from extreme stress and injuries, in addition to close promixity and lack of hygiene. A more prototypical bad influenza pandemic is the 1957 Asian Flu outbreak, which is hardly a blip in the history books.

Another Covid era is impossible exactly because of the Covid era.

No.

There is the joke "I want to do illegal thing ... In Minecraft" as a sort of joking way to avoid clearly confessing to a crime.

A while back I remember someone, maybe on the slatestarcodex subreddit talking about how they were fascinated by the mini civilization and rules that had arisen on their Minecraft server.

Does anyone know of any writings on Minecraft societies that are interesting or worth reading?

I'll second AliceMaz's writeup, albeit with the caveat that the server in question there was unusually large. Most long-lived servers usually only get in the high double-digits of regular players, and correspondingly a lot of social rules are more varied and sometimes superstition-like (eg where are hoppers acceptable is a surprisingly complex question).

The BlanketCon 2022 postmortem is more about the technical side of a fairly short-lived server, but you can kinda see the motions around what social rules were working under the hood at the time.

Unfortunately, a lot of good pre-YouTube era stuff was written up on the old minecraft forum, and has since evaporated for GPDR reasons. Most analysis these days are in video form on YouTube, and they're often made by people who conflate the technical build side or lets plays with the social rule one, or only include the social rulemaking by accident. And even on YouTube, a lot of multiplayer SMPs are either more Let's Plays or outright scripted events. Or are just 2b2t voyeurism: there's some social stuff to Nocom/Randar/whatever, but it's not really a social rule-making thing.

I'd be interested if anyone's more familiar. I can think of a half-dozen Oilfurance-style stories for the short-lived SMP server I helped with a few years ago, so it's kinda surprising that nothing else is showing up on Google, but I dunno if anything I've got would be interesting enough for other people.

https://www.alicemaz.com/writing/minecraft.html

Suggestions for not causing fast ends to political conversations with boomer MEGA MAGA conservatives (subscribe to the Epoch Times types).

I've got a few in my personal life and have time to hang out for long periods over the holidays. Between themselves, they can go back and forth for long periods of time. I'm not even trying to debate, even when I'm trying to strengthen their positions (I guess that might be in the eye of the beholder), they're changing the subject in less than five minutes.

I'm usually don't disagree. Mostly just trying to expand the subject. An example of a "disagreement" would be going into Hanania's theories from The Origin's of Work. Something like "Simply passing laws banning DEI isn't going to work, you have to gut disparate impact jurisprudence." I know better than to try to go as redpill as defenestrating parts of the civil rights act, they would not know how to handle that.

My general strategy for political conversations is to propose something so outlandish that it short circuits pre existing culture war lines. Like, the USA should offer statehood to Singapore.

What does MEGA mean? If it's England then I can't undestand what Falun Gong has to do with it.

Fat fingered MAGA.

What are interesting translations of the Odyssey that I might not have come across in the past?

I've previously read most of Fagles' years and years ago, and I read the entirety of Pope's in 2020. And of course I've read Joyce's version. This year I've read the War Nerd Iliad and the Dryden Aeneid, I feel like I want to wrap it up with the Odyssey, but I'm not sure what translation to grab.

Robert Fitzgerald's 1965 translation is the standard modern version. Why not do that one?

Samuel Butler's 1900 translation was included in the Harvard Classics, but I usually recommend against it because it's in prose.

Is this completely independent of the twitter blow up around Emily Wilson?

twitter blow up

What was the nature of the blow up?

There was a tweet praising her translation due to a combination of contemporariness and culture war reasons. This triggered replies unfavorably comparing passages of said translation with the same bits from others.

I've only seen one of said comparisons, and, to be honest, it seemed pretty damning, but I'd rather not form my opinion from a single, probably-not-well-intentioned tweet.

Are you recommending this one or is the mention of Twitter beef meant to warn me off of it?

I've heard Wilson's translation is supposed to emphasize readability over poetic language, and also emphasize the grimness over the glory of war in its translation. Its focus on readability over poetic language makes it an easy target for tweets to mock it as a step down from previous translations, and a lot of right-wing twitter is very pro-glory over grimness. Plus she has been promoted as a girlboss, progressive translator, and that makes her an obvious cultural enemy.

I haven't read any translations myself, just retellings in various mediums. I don't feel a particular urge to get closer to the source material.

Neither, I haven't read any version of the Odyssey, I do follow Tyler Cowen quite closely so on his recommendation it was at the top of my list initially and now after the twitter blow up I'm leaning toward Fagles. Have you seen this side-by-side comparison?

The only thing missing from the comparison is the original Greek so we can judge who did it best.

So, what are you reading?

I'm adding Legend of the Galatic Heroes to my pile. Perhaps I'll get past book 3 this time.

Just finished Red Roulette: An Insider's Story of Wealth, Power, Corruption, and Vengeance in Today's China. There should be some regulation on how long book subtitles can be.

It’s basically a Chinese guy’s real life rags to billionaire story. He is quite open about how their wealth was almost entirely made through mediating various forms of corruption between CCP officials. He tries to spin his own role in this corruption many times and it’s definitely tailored for attracting sympathy from western audiences. But overall quite a fascinating book.

Still reading Say Nothing: A True Story of Murder and Memory in Northern Ireland.

Curious thing - I often try to guess what's going to happen next in books or movies based on how far through them I am. It's usually pretty effective, even for non-fiction books. But here I am 45% through the book based on my Kindle, and I don't really know where this book is going for the next half of it. They've already covered the Good Friday agreement, where most such books end, and have been going on a while about post-GFA issues, agreements and legal battles regarding how to handle people who were "disappeared" and people who may or may not have been involved in such acts. Apparently, despite the amnesty provisions, you can still be prosecuted for at least some crimes committed during the Troubles years, including for being confirmed to be a member of illegal organizations like the IRA.

It's also rather curious that apparently they still to this day can't figure out for sure what the deal was with poor Jean McConville. It's confirmed that the IRA murdered her and "disappeared" her, but they still to this day claim she was an informant working for the Brits, with radio equipment found in her apartment, who was warned once to stop collaborating before being murdered. Meanwhile, the authorities still claim they don't know anything about here being any kind of informant. But nobody can confirm for sure which one is true.

The Unbearable Lightness of Being.

A few years ago I read On Love by Alain de Botton and liked it a lot. Now I kind of feel like he was using this as a crib sheet.

Doc, by Mary Doria Russel.

Not bad at all. I have some nitpicks with it. "Is not Cormac McCarthy" might be one of them. Overall I'm enjoying it though.

Sapiens. I like the subject material a lot but it's a bit too pop pop sci for me, but I don't have other books I really want to read more at the moment.

For some reason it took me for bloody ever but I just finished Cloud Cuckoo Land last night. I didn't dislike it but it didn't draw me in like it seems to a lot of other people. I'm guessing because I'm not worried about climate change. It was kind of fun in that I'm very familiar with the parts of Idaho the story takes place in, I know where his photo on goodreads was taken on sight. Lakeport is very obvious McCall, Idaho, my parents like to point out the cabin on the lake they almost bought in the 70's.

I think I'll take my 4th foray into 40k with Eisenhorn - Xenos as a fast read.

Currently working my way through Wind And Truth by Sanderson. Also, was at the bookstore recently and decided to pick up some more Heinlein after I enjoyed Starship Troopers so much. I got The Moon Is A Harsh Mistress, will probably start that sometime later this week.

Adolin story carries hard tbh

For me it's the Dalinar story. Finding out more about the history of the world is fascinating. The Kaladin story is my second favorite for similar reasons.

Wind and truth is a slog, honestly. Sanderson is spending a lot of time on modern mental health issues for every single viewpoint character. There is character building and then there is exhausting navel gazing....

I'm quite enjoying it. Not finding it a slog at all. I'm only 40% through or so, we'll see if that changes but I doubt it.

I think I first noticed it in Dawnshard, the therapist speak. I think his older work is much more balanced and not as grating in this way. (WOK still rocks, I reread 1-3 and then read Dawnshard and Rhythm of War in Nov/Dec.

I noticed in the last couple of books. It’s a damn shame because the idea that only people with a crack in their soul can get powers is genius - it naturally integrates “is a plot-relevant character” and “has potential for character development”.

But then it’s like he lost sight of the difference between character flaws and DSM entries. Which leads to cringy writing but also causes problems because you are not allowed to treat DSM issues as things that can be overcome.

But then it’s like he lost sight of the difference between character flaws and DSM entries. Which leads to cringy writing but also causes problems because you are not allowed to treat DSM issues as things that can be overcome.

That's exactly why I decided not to bother continuing after Rhythm of War.

Fair, but it’s £10 every two years, he’s earned that much from me. And I liked Wax & Wayne, so he’s still putting out good stuff in general.

Just started The Way of Kings for the first time myself, it's tough avoiding spoilers on social media. Initial thoughts are that the spren are very goofy and Kaladin's depression isn't as effective a plot point as it would be if he weren't already an incredible soldier and surgeon. The worldbuilding seems cool though.

The Way of Kings was my first Sanderson book and I really struggled with it. I spent probably 2/3 of the book wondering when there was going to be an interesting plot. In truth I would've dropped it, if not for the fact that it was a Christmas gift (so, a bit rude to give up on it) from my sister (who I know to have good taste in books). But man when the book finally gets going, it goes hard. Sanderson loves to write his books as a slow burn followed by an explosion.

Given all the "takes" on Luigi Mangione flooding various online spaces, which is the most odd/surprising that you've encountered?

Mine was from a podcaster I sometimes listen to who, in the context of talking about getting away from the "political binary" and viewing and judging these sorts of incidents through the lens of tribal affiliations, went on to compare Mangione to Beowulf.

I found it notable that a Mexican corrido has already been written about him.

Following in the footsteps of the other famous American driven to be an outlaw by healthcare costs.

I thought that was going to be Dog Day Afternoon

If (as I think is most likely) the “Republican trifecta” accomplishes nothing of note in the next four years, DOGE fails even harder than the Grace Commission, and Trump’s second term proves as ineffectual against “the swamp” as his first, how do you suppose Republican voters would react come 2028?

how do you suppose Republican voters would react come 2028?

They primarily blame Democrats for blocking progress. I'm still a big believer in median voter theorem, probably whichever candidate can succesfully market themselves as more moderate wins 2028.

It would be sad but I think most will vote R again because what’s the alternative?

Things not getting actively worse is still a pretty big win in the post-2000 era.

It would be sad but I think most will vote R again because what’s the alternative?

Violence. Grabbing your buddies and your guns, forming a RWDS and shooting every Blue Triber you find.

Would it work? Almost certainly not, but its odds of success, however small, are still better than those of "voting harder" — which are effectively zero.

  • -21

If you wanted to post this, just post it, don't ask a stupid question so you can give your own brain dead answer.

What an amazing species of black piller, so allergic to winning that upon appearing to win you go back to fantasizing about losing.

This is getting pretty close to fedposting. If you are sending out feelers to organize a "gun club," do it elsewhere.

I've seen at least 3 posts by @Capital_Room advocating mass murder of this sort fwiw. Hyperbole?

If you are sending out feelers to organize a "gun club," do it elsewhere.

Nope, not my intent. And for clarification, at what point does comparing the relative odds/effectiveness of various methods go from allowed "discussion" to "advocacy" — and thus edge against the "discussing the culture war, not waging it" rule? (Which is the rule which "fedposting" violates, yes?)

I can't give you hard rules on exactly how to word posts that amount to an argument for killing your political opponents. We are not mind-readers and cannot tell whether you are just speaking hypothetically ("I'm not saying we should murder all Blue Tribers, just that realistically the only way to prevent our civilization from collapsing into an apocalyptic nightmare is to kill all Blue Tribers") or seriously arguing for this, but we do factor in the poster's history, and if the overall impression is that it looks like you are nudging the line with your toe, I am going to say something. Other mods are probably calibrated to slightly different degrees.

Thanks for the clarification.

This kind of cell-based violence would be phenomenally stupid, so we can rule it out. ANTIFA might do it if Trump racks up major victories. But the path to total red victory is not individual level violence, it’s inter-institutional warfare that devolves into kinetics.

it’s inter-institutional warfare that devolves into kinetics.

With what institutions?

the path to total red victory is not individual level violence

I see little evidence that there's any path to red victory, and as for "individual level," that's why the "organize into groups" part was there.

With what institutions?

Law enforcement, the military(generals are empty suits- field grade officers decide what happens in a crisis, and those are still pretty red), state governments, etc.

I see little evidence that there's any path to red victory, and as for "individual level," that's why the "organize into groups" part was there.

I know, you’re an unemployed mentally ill doomer with SAD acting up this time of year.

When Greg Abbott told the feds he rules the border now, he got away with it, and the border patrol refused to contest this- even while heavily outnumbering him. The Malheur occupiers and the truckers got what they wanted.

Reds win regularly. Those victories do not look like random terrorist attacks.

Law enforcement, the military

Controlled by blue. Because it doesn't matter how red the rank-and-file are, they will always, always, always put obedience to the chain of command ahead of their personal political views. Just ask them: colonels leading coups is something that only ever happens in other countries, but the US military is different — the military is "apolitical," and no US serviceman would ever dishonor himself and the Armed Forces by putting his personal politics ahead of that.

I also remember a forum post online by a Chicago cop, in a 2nd amendment/gun control conversation, saying it doesn't matter how much he might personally support gun rights, if he gets the order to go door-to-door confiscating everyone's guns, he's doing it. First, because 'try telling your boss "no" to a direct order to do something, and see if you still have a job. I have my pension to think about and bills to pay.' And second, since most known, legal gun owners are older and highly law-abiding, he'd be safer and less likely to get shot taking their guns away than he was when he worked dealing with the gangs in the worst parts of Chicago.

When Greg Abbott told the feds he rules the border now, he got away with it, and the border patrol refused to contest this

Because what difference did it make?

the truckers got what they wanted

Funny, everything I remember reading on the topic said the truckers lost badly, Trudeau won, the precedent for "debanking" was set, and remains ready to be used to crush future dissidents.

Reds win regularly. Those victories do not look like random terrorist attacks.

No, we don't. And those "victories" you speak of are nothing of the sort.

I know, you’re an unemployed mentally ill doomer with SAD acting up this time of year.

Even if this is true, this is an unnecessary ad hominem.

On the contrary- it’s an entirely necessary ad hominem. The post I was replying to is based on a doom loop fantasia driven by his frequently-posted about lack of productive activity and depression.

That's kind of like claiming you are calling a fat person a lazy, obese pig because you are concerned about their health and want them to lose weight for their own good. I suppose it's possible someone might believe this, but if you are really trying to break him out of his "doom loop" there are kinder and more polite ways to do it.

I'm looking for if there's a term for a particular style of logically fallacious argument, somewhat similar to both No True Scotsman — in that it involves the rejection of a counterexample – and circular reasoning — in that the proposition under contention is used to ground the argument — but it differs in that rather than redefining the category at question to exclude the counterexample, it uses its membership in the category to deny the elements that make it a counterexample.

For two toy examples, consider the classic "all swans are white" or the original "No Scotsman puts sugar on his porridge." Then the counterparty presents a black swan in the former case, and in the latter says "but my friend Angus MacFadden is as Scottish as he comes, and I see him put sugar on his porridge all the time." Now the "No True Scotsman" fallacy would be, in the former case, to try to redefine "swan" to exclude the black swan; and, in the latter to say "no true Scotsman puts sugar on his porridge." That is, to engage in an ad hoc redefinition defying the swans "swanness" or Angus's Scottishness.

I'm talking instead about the argument that accepts that the black swan is indeed a swan, and instead denies that it's black. It's a photographic error, or it got some soot or ink on it's naturally-white feathers, or your eyes are playing tricks on you, but all swans are white, therefore we know with absolute logical certainty that your "black" swan is white, and all evidence that it is black can and must be summarily dismissed. Angus MacFadden, as a Scotsman, never puts sugar on his porridge. You may think you've seen him do so, but assuming you didn't just hallucinate it, then however much whatever Angus put on his porridge looked like sugar, we know indisputably that it wasn't actually sugar; Q.E.D., full stop, end of discussion.

(Before anyone asks, yes, I have actually seen this style of "argumentation" — with all it's resemblance to a fancified version of a small child's "nuh-uh" — in the wild, most notably with a Tumblr tankie defending East Germany and the Berlin wall proceeding, in an obnoxiously smarmy and condescending manner — to call various people's relatives literal Nazis.)

I would just call it denial of evidence.

I'm not aware of a particular term to describe that argument type, but at least you could successfully communicate the idea more succinctly by referring to trapped priors.

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