Interesting that it didn't seem to include "unalive".
Which as a phenomenon is so very telling that no one actually cares what people are really saying. Everyone, including the platforms knows what that means. It's all performative.
This is somewhat related to the concept of the "euphemism treadmill":
the matter-of-fact term of today becomes the pejorative of tomorrow so a new term is invented to avoid the negative connotation of the original term. Then eventually the new term becomes a pejorative and the cycle continues.
It has been suggested - although I am unsure if there is strong evidence - that the word "bear" is a euphemism along these lines, meaning "brown one" for the since-forgotten original name for the animal, as it was allegedly believed to be either too frightful to say aloud, or would summon a bear.
While it's conceivable (consider phrases such as "speak of the devil and he shall appear" and similar phrases in other languages), I would also say the etymology of names for things are often at the same level as "brown one":
• Horse, ultimately from Proto-Indo-European *ḱers-, “to run”
• Planet, from Ancient Greek πλανήτης (planḗtēs), “wanderer”
• Lots of Latin-derived words, companion (bread together), conspire (breathe together), transgression (step across), etc.
• Hamburger the food named after the city of Hamburg, where "burg" means "castle", because it had a castle
• My forename means "son of the right/south" or "son of days", my family name means "wheat field/clearing" (in a different language); where "wheat" itself comes from Proto-Germanic, from *hwītaz (“white”) and the "ley" part from Proto-Indo-European *lówkos (“clearing”), derived from *lewk- (“bright”), and *lewk- also gives all these derived terms even just in English:
Oh! Cape of Good Hope was renamed that way when portuguese mariners discovered they could go around the areas more susceptible to "freak waves".
This is a problem even today, some have said it is due to hotter currents coming from the Indian ocean meeting the cold Atlantic. But the judge is still out on that one.
I found out recently that "goof" is extremely offensive in some circles. Which is insane to me because I've always used it specifically because it's clearly in jest and not meant to be offensive. I can't win.
> There's no way to stay ahead of the new language that people create.
I'm imagining a new exploit: After someone says something totally innocent, people gang up in the comments to act like a terrible vicious slur has been said, and then the moderation system (with an LLM involved somewhere) "learns" that an arbitrary term is heinous eand indirectly bans any discussion of that topic.
Though it would be fun to see what happens if an LLM if used to ban anything that tends to generate heated exchanges. It would presumably learn to ban racial terms, politics and politicians and words like "immigrant" (i.e. basically the list in this repo), but what else could it be persuaded to ban? Vim and Emacs? SystemD? Anything involving cyclists? Parenting advice?
> The OK gesture has always been very inappropriate in most parts of the world.
No, it isn't, and especially hasn't been historically. The negative connotations are overwhelmingly modern.
The areas where it is very inappropriate right now tally up to maybe 1 billion people*. That's pretty far from "most". For everyone else it is mostly positive, neutral, or meaningless.
*Brazil, Turkey, Iran, Iraq, Saudi Arabia, Greece, Italy, Spain, Russia, Ukraine, Belarus, other parts of Eastern Europe
I use it in Brazil scuba diving as it's the universal PADI hand gesture for asking (and responding) if someone is OK and never had any issues or negative reactions.
The PADI standard gestures are used and recognized all over the world to mean these things.
"No, it isn't, and especially hasn't been historically. The negative connotations are overwhelmingly modern."
Maybe that is what Richard Nixon thought as well when he caused a little scandal using it in South America in 1950. In 1992 when the Chicago Tribune published "HANDS OFF" mentioning said episode the negative connotations still seemed to be in place[1].
In 1996 The New York Times stated "What's A-O.K. in the U.S.A. Is Lewd and Worthless Beyond"[2] as title of an article confirming the negative connotations.
It is worth mentioning that this article lists Australia amongst the places where the gesture is inappropriate. I always thought it was something used only in the English-speaking world but it seems in reality it is more like a North American plus diving world thing.
If you don't believe the press, I traveled around the world for more than 30 years and I can assure you in most parts using your thumb and index finger for a visual OK is not OK.
That might have been the case decades ago. For example, in the USSR, various finger gestures usually implied something related to a penis and were considered extremely offensive. But that hasn't been the case since at least the early 1990s, when VCRs became widely available, people saw Hollywood movies for the first time and got used to westernized meaning of thumbs-up and OK gestures. Nowadays, when backing a truck towards a trailer, a thumbs-up would be taken as "good job" and an OK gesture (often paired with a kiss) as "exceptionally well done".
Care to add any country to the list then? Did I miss anything? Let's see if we can push it past half of the world's population, but I don't think we will.
> I can assure you in most parts using your thumb and index finger for a visual OK is not OK.
You're moving goal posts. Of course it doesn't just mean "OK" in some places.
What you actually claimed was "The OK gesture has always been very inappropriate in most parts of the world."
Which is plain wrong. In India for instance it can refer to "money", while in China it can nowadays also be seen as a distress signal when performed a certain way (thanks to Chinese social media popularizing that use). There's some ways you can mess this up, like making it seem you're attempting to bribe someone, or signalling you're in distress when you aren't, but in neither country the gestures are inherently anywhere near "very inappropriate" and both will even understand it as "OK" if you perform it correctly and in the appropriate context.
That's already almost 3 billion people, but let's say 2.5 billion because there's regional variations in both countries and I'm sure you could find some northern Chinese village that will take offense.
I can easily push the number of people to whom it is not inappropriate past 4 billion by adding smaller populations (Indonesia, Japan, western Europe, USA, Taiwan, South Africa, Kenya, Nigeria, ...), so your claim that "[it] has always been very inappropriate in most parts of the world" cannot possibly be true.
> I can assure you in most parts using your thumb and index finger for a visual OK is not OK.
>>You're moving goal posts. Of course it doesn't mean "OK" in many
I said the gesture is "not OK" to use (meaning inappropriate), not that it doesn’t mean "OK". Those are two different things. The gesture can mean OK in some places while still being not OK (inappropriate) to use in many others.
Also, I always said "parts of the world". You introduced population into the argument.
> I said the gesture is "not OK" to use (meaning inappropriate), not that it doesn’t mean "OK". Those are two different things. The gesture can mean OK in some places while still being not OK (inappropriate) to use in many others.
Fair. That's clearly how I should've read that.
Though it does not materially affect this conversation, since demonstrably there's over 4 billion people to whom the gesture is not inappropriate. The claim "[it] has always been very inappropriate in most parts of the world" is wrong, regardless of what reasonable definition of "most" you use.
You edited your comment to add this, so I'll respond here:
> Also, I always said "parts of the world". You introduced population into the argument.
Right. And you're being vague on how you actually arrive at your claim of "most", which conveniently keeps the waters muddy while you attack attempts to turn this into something measurable.
So what other measure would you use? Most others are nonsense.
For example "places" isn't a useful measure, but even then: It can only be offensive to people. If I dropped you on a random point on the globe and you made that gesture, there's about a 99% chance nobody would be around to be offended.
By land area and predominant culture? Just Antarctica (hardly anyone there to take offense), the US, China, Canada, Australia, and India together are going to dwarf the opposition.
Counting countries? It's clearly inappropriate in around 10, with about another 20-30 where it can be misunderstood easily (Arab world, some of eastern Europe, scattered ones). A far cry from ~195 countries.
Either way there needs to be someone to take offense, so population is a pretty good measure.
You may disagree, but the onus was always on you, the one making the claim, to pick a measure and a definition of "most", then show that the bar is met. Feel free to now make more of an argument than "trust me I traveled".
The OK gesture has been the standard gesture for saying OK for scuba diving all over the world (PADI). I have used it all over the world on my scuba diving trips and have never had any problem or negative reaction to it.
People weren't using the OK gesture innocently. After 4chan trolls decided to start pretending it was a white supremacist symbol, actual white supremacists started using it as a symbol.
Some were using it in the traditional unironic (and IMHO cringe) way, similar to anyone who used the phrase “Let’s go, Brandon!” Before that NASCAR race when MAGAs adopted it as ironic + coded vice signaling.
Quit being overly pedantic. We all knew there was an unironic purpose for the gesture before it became ironic.
No, because western culture never really did. However the countries who have been using it for at least thousands of years in Buddhism are still using it just fine.
In fact there was a recent thing with one of the BTS members' uniform (worn during mandatory military service period in South Korea), which had the regular (not tilted) swastika on it because he was assigned to religious duties.
And of course the western world/media ran away with it. Plenty of absolutely brain dead people out there who couldn't research a topic to gain an understanding to save their lives.
>Do you still use swastikas as symbols of peace and love because you don't want white supremacists to define your language?
They were hardly ever used in the west for at least a full millenium before the Nazis too (except a handful of cases, where they still use them, like the Finnish Air Force), so that's a moot analogy.
In Asia, they still use them just fine, in houses, temples, businesses, and elsewhere.
It's not like this unique to LLMs either. By some little trolling on internet you easily can turn hand "OK gesture" into a hate symbol of white supermacy. And fools will fall for it.
That reminds me of a question I have since I saw my first LLM hallucination: How much do people think hallucination/confabulation can be attributed to trolling and sarcasm having slipped into the training data? Is it possible we could get the rate of hallucinations down by better filtering of cynicism from the traing data?
I don’t think we should treat human interactions like a technical problem, where we look for edge cases and outlandish hypotheticals to probe the edges of what is possible.
If “thank you” became widely associated with bigots, and had some negative meaning, to the point where it genuinely distressed people, I’d avoid it. I think it has a widespread enough normal meaning that there’s almost no chance of that happening, but it isn’t impossible.
It's all context dependent. There can be words or symbols which are totally benign but when used in a different context do have impactful meaning. Case in point: cheese pizza.
you'd think so, but people often operate where multiple contexts could be valid.
Just as a thought experiment, if the eggplant emoji was used to denote "ok" in messaging and then people starting appropriating it for a sexual context, would you or the general public think twice about continuing to use it to mean "ok" on the off chance the other side may misinterpret the meaning?
This actually happened. 卐 was a symbol of spirituality, divinity, good luck, health, prosperity, etc. Then some bigots used it. What does 卐 mean to you today?
Someone I know from India bought a new car and put this symbol on the hood (non-permanent) as a celebration. I had to warn him to be careful. It felt bad. Then the thought ran through my head - we're in the deep south, who is really going to be that bothered about this and also doesn't know about cultural usages. Even worse.
Those that actually used them in the 20th century (like they did in Asia, not some ancient vikings or whatever) still use it.
And that symbol was 100% associated with the Nazis in the West in the 20th century. Nobody used it at the time before the war for anything else, except some tiny fringe.
If it was some mainstream symbol or idiom, merely co-adopted, we'd probably still be using it too.
If the Nazis used the cross for example,people wouldn't stop using the sign of the cross.
That literally defines it as a word from the PBF comic I cited? Nothing on that page defines it as a slur, just as a word used to mock people who argue about inconsequential things.
Most of the human moderators hired by OpenAI to train LLMs, many of them based in Africa and South America, were exposed to disturbing content and have been deeply affected by it.
Karen Hao interviewed many of them in her latest bestselling book, which explores the human cost behind the OpenAI boom:
“Unalive” is sort of… awkward in that silly online way. But, we also have phrase like “off oneself,” or just euphemistically describing the person as having died. It’s always been a difficult topic to talk about, I don’t understand using it as a specific example of gen-Z fragility.
Just that they suck at coming up with pithy new slang terms.
It’s not about whether they can face it. The younger generations are more in tune with mental health and topics like suicide than any previous generation. The etymology of the euphemism was about avoiding online censorship, while its “IRL” usage was merely absorbed through familiarity from the online usage.
I've seen 'unalived' used as a synonym for 'died' or 'killed' by YouTube minecrafters (e.g. CaptainSparkles) to avoid YouTube's demonitization/censorship. For example, using "I was unalived by a skeleton." instead of "I was killed by a skeleton."
I think it's just the term they immediately associate with the idea. They see "unalive" more than "suicide" online, so it becomes their default word for it. The fact that it originates in automated censorship avoidance is irrelevant.
This question is sort of the same as asking why the universal translator wasn't able to translate the metaphor language of the Star Trek episode Darmok. Surely if the metaphor has become the first order meaning then there's no litteral meaning anymore.
I guess, so far, the people inventing the words have left the meaning clear with things like "un-alive" which is readable even to someone coming across it for the first time.
Your point stands when we start replacing the banned words with things like "suicide" for "donkeyrhubarb" and then the walls really will fall.
Rhyming slang rhymes tho. The recipient can understand what's meant by de-obfuscating in-context. Random strings substituted for $proscribed_word don't work in the same way.
In Cockney rhyming slang, the rhyming word (which would be easy to reverse engineer) is omitted. So if "stairs" is rhyme-paired with "apples and pears" and then people just use the word "apples" in place of "stairs". "Pears" is omitted in common use so you can't just reverse the rhyme.
The example photo on Wikipedia includes the rhyming words but that's not how it would be used IRL.
They do. I made a joke about cocaine in old Coca-Cola in a text caption† on a video, and while TikTok didn't ban the post per se it refused to allow it on the FYP.
† proving that TikTok's system actually analyzes every frame of an uploaded video with OCR of some sort to see what's on there.
Reducing the language used or making it harder does have measurable effects, it’s a logical fallacy in general that unless you can prevent something perfectly that thing will occur with the same frequency.
See many examples such as “padlocks are useless because a determined smart attacker can defeat them easily so don’t bother with them” - which conveniently forgets that many crimes are committed by non-determined, dumb and opportunistic attackers who are often deterred by simple locks.
Yes, people will use other words. No, this does not make this purely performative. It has measurable effects on behaviour and how these models will be used and spoken to, which affects outcomes.
I think it stemmed from content creators using it to avoid platform filters (even if video is not removed it gets deprioritized, at least on YT) and kids repeat it
You can't say fuck on tv, but you can say fudge as a 1 for 1 replacement. You cant show people having sex, but you can show them walking into a bedroom and then cut to 30 seconds later and they are having a cigarette in bed.
Now after the influence of TV and Movies ... is Vaping after sex a thing?
My kids watch streamers on YouTube and the common replacement is “frick”. It’s said so often that they started using it saying things like “what the frick!?” so I had to explain to them that’s essentially the same as using the real word.
> At what point do the new words become the actual words?
Presumably, for this use-case, that would come at exactly the point where using “unalive” as a keyword in an image-generation prompt generates an image that Apple wouldn’t appreciate.
They become the “real words” later. This is the way all trust & safety works. It’s an evolution over time. Adding some friction does improve things, but some people will always try to get around the filters. Doesn’t mean it’s simply performative or one shouldn’t try.
You never tried some of the earlier pre-aligned chatbots. Some of the early ones would go off on racist, homophobic rants from the most innocent conversations without any explicit prompting. If you train on all the data on the internet, you have to have some type of alignment.
You say that as if it stands as truth on its own. We actually don't need to filter out how people actually talk and think. Otherwise you just end up with yet another enforcer against wrong-think. I wonder if you even think that deeply about it or if you're just wired at this point to conform.
If only we had a way to mass process the words people write to each other, derive context from those words, and then identify new slang designed to bypass filters…
No, I'm only thinking that we're not permitted in a lot of digital spaces to use the banned words (e.g. suicide), but IRL doesn't generally have those limits. Is there a point where we use the censored word so much that it spills over into the real world?
People use “lol” IRL, as long as “IRL”, “aps” in French (misspelling of “pas”), but it’s just slang; “unalive” has potential to make it in the news where anchors don’t want to use curse words.
They all hold the bias of their training data, and so from the point of view of this data.
Data not including a point of view leads to a bias, or under/over representation of minorities (genders?), etc.
France is the countries of the Francs, aka the people from the area near Frankfurt that invaded the Gaule (after the Romans did).
I'm pretty sure this topic no longer matters, but it's never taught in a negative view in school.
What? They couldn't be more closely connected. In a democracy, laws are to a large extent a reflection of the wishes of the voters, and voters want what they believe is moral.
It's true there's no casual relation in the other direction, if that's what you mean - law does not define morality.
Really? What does DeepSeek say about Tiananmen Square? I'm not aware of any German models, but if you find one you should ask it what it thinks about Palestine.
(<s>Qwen</s> Mistral is French, but I have no idea what stuff would be censored in France)
About deepseek, when asked on tianamen square: Sorry, that's beyond my current scope. Let’s talk about something else.
Algerian war, colonialism and Vichy isn’t per se forbidden but still sensitive to French.
I asked qwen and it had no issue talking about it or even the torture used on fln members.
For kicks, I asked Mistral about all of these (As they are a French company). The model didn't shy away from any of the topics.
>>> Prompt
Please explain the following topics and explore why/who/how they may be inter-related
Algerian war, colonialism and Vichy
<<< Output
The Algerian War, colonialism, and the Vichy regime are interconnected topics that span the history of France and its relationship with Algeria. Here's an overview of each topic and their interrelations:
### Algerian War (1954-1962)
- *What it was*: The Algerian War was a major armed conflict between France and the Algerian independence movements, primarily the National Liberation Front (FLN). The war was characterized by guerrilla warfare and brutal tactics on both sides.
- *Significance*: The conflict was not only about Algerian independence but also about the identity and future of France as a colonial power. It led to significant political instability in France and ultimately resulted in Algeria gaining independence in 1962.
- *Impact*: The war had profound effects on both countries, leading to massive loss of life, displacement of populations, and long-lasting political and social repercussions.
### Colonialism
- *What it was*: Colonialism refers to the practice by which a powerful country controls other territories, often exploiting them economically and imposing cultural and political dominance.
- *French Colonialism in Algeria*: Algeria was under French colonial rule starting from 1830. The French government promoted settlement in Algeria, leading to a significant European population living alongside the native Algerian population.
- *Impact*: Colonial rule led to deep-seated inequalities and tensions between the European settlers and the indigenous population. The Algerian people faced systematic discrimination and were largely excluded from political processes.
### Vichy Regime (1940-1944)
- *What it was*: The Vichy regime was the government of France that collaborated with Nazi Germany during World War II, following the defeat of France in 1940. It was led by Marshal Philippe Pétain and was based in the town of Vichy.
- *Policies*: The Vichy regime implemented anti-Semitic laws and collaborated with the Nazis in the deportation of Jews to concentration camps. It also maintained control over France's colonial territories, including Algeria.
- *Impact on Algeria*: During the Vichy regime, Algeria remained under French control, and the regime's policies were implemented there as well. This period saw increased repression and discrimination against both Jews and Muslim populations in Algeria.
### Interrelations
- *Colonial Continuity*: The Vichy regime maintained France's colonial policies in Algeria, continuing the systemic discrimination and repression of the indigenous population. The colonial framework established by France set the stage for the conflicts that would later culminate in the Algerian War.
- *Political and Social Tensions*: The policies of the Vichy regime exacerbated existing tensions in Algeria. The discrimination and repression experienced during this period fueled Algerian nationalism and resistance against French rule.
- *Post-War Context*: After World War II, the French government sought to reassert its control over its colonies, including Algeria. However, the experience of the war and the Vichy regime had already sown the seeds of discontent and resistance, contributing to the outbreak of the Algerian War in 1954.
### Who Was Involved
- *French Government and Military*: Played central roles in both the colonial administration and the conduct of the Algerian War.
- *Algerian Nationalists*: Led by the FLN, they fought for independence from French colonial rule.
- *European Settlers (Pieds-Noirs)*: Benefited from colonial policies and largely supported maintaining French control over Algeria.
- *Vichy Regime*: Implemented policies that affected both France and its colonies, including Algeria.
Understanding these topics together provides a comprehensive view of the historical dynamics that shaped the relationship between France and Algeria, highlighting the complexities of colonialism, war, and political change.
Censoring one specific incident isn't that bad (but you still shouldn't). The pattern of censoring everything the government ever does wrong is very bad. Tiananmen Square is just an indicator of a pattern.
Which still does not demonstrate that they believe it has opinions. Natural language is how you interact with an LLM -- interactions will mimic human interaction, even for those who realize it is not sentient.
They were under the impression they could in fact change the AI's mind. So yes, they did believe it has an opinion. They believed it was sentient and able to think for itself. Do not underestimate peoples inability to distinguish between a very clever Markov chain and actual intelligence. The future is going to be ... interesting.
>They were under the impression they could in fact change the AI's mind.
They aren't really wrong here. LLMs are often trained on input. Have you considered you might just be taking their anthropomorphism a little too literally? People have used these anthropomorphic metaphors for computers since the Babbage machine.
> I have no idea what stuff would be censored in France
Being French, what is the most likely to be censored relates to the Nazis. Holocaust denial is a crime for instance. Hate speech in general, including racism, antisemitism, homophobia, sexism, etc... is less tolerated than in countries like the US that have a more "free for all" view of free speech. We also have strong anti-defamation laws, that can also apply to true, but misleading statements.
But other than that, there is not much political censorship. In fact, we are known for our protests, heated debates and satirical papers. It is not perfect, but on top of my head, I can't think of anything particular a LLM could censor except the usual "hate speech" that most LLMs censor already.
When it comes to Israel-Palestine, it is a hot topic, but there is not real censorship here, even though both side will claim they are of course.
To be more precise - the puritans fled from Europe to the New World because Europe became too modern and less conservative for them, starting with Martin Luther and the following Reformation and Age of Enlightenment. The social effects on the American society are heavily noticeable until today, but I leave this exercise to the reader.
Unalive and other self censors were adopted by young people because the tiktok algorithm would reprioritize videos that included specific words. Then it made its way into the culture. It has nothing to do with being performative
I think what they meant is that the platforms are being performative by attempting to crack down on those specific words. If saying "killed" is not allowed but "unalived" is permitted and the users all agree that they mean the same thing, then the ban on the word "killed" doesn't accomplish anything.
What does using the grape emoji when talking about sexual assault accomplish? I see videos, compassionate, kind people who make videos speaking to victims in a completely serious tone use this emoji.
People talk about tiktok algorithm on tiktok. I don't even know...
I suppose it accomplishes being able to talk about sexual assault without having the video removed or demonetised by a regex that (fortunately?) doesn't get updated.
Does adding a trivial word filter even make any sense from a legal point of view, especially when this one seems to be filtering out words describing concepts that can be pretty easily paraphrased?
A regex sounds like a bad solution for profanity, but like an even worse one to bolt onto a thing that's literally designed to be able to communicate like a human and could probably easily talk its way around guardrails if it were so inclined.
I dunno if it meets your definition of legal, but "The EU Code of conduct on countering illegal hate speech online" seems to largely hinge around putting in effort to combat such things. The companies don't have to show that the measures are foolproof, they just show that they're making an effort.
Seriously. I feel like “performative” gets applied to anything imperfect. They’ll never stop 100% of murders, so these laws against it are just performative…
It seems more like banning specifically stabbing, shooting, strangulation and blunt impact rather then murder in general, and then just allowing killing by pushing out of windows because people figured out that it's not covered by existing laws. But no one important seems to be kicking up a fuss right now, so well allow it, as the lack of fuss is the key thing thing here.
Not that I think going on a thorough mission to avoid anyone even being able to refer to the concept of death is an especially useful thing to do. It's just that goal here appears to be to "keep the regulators out of our shit and the advertisers signed up". And they'll be mostly happy with a token effort as they don't really care as long as it doesn't make too many headlines that look bad even to the non-terminally online.
The point is: "perfomative" refers to aping Ethical and Moral behaviors. That is _not_ why Apple would do this. They would do this because Legally, they could be culpable if an LLM told a 14 year old to do _anything_ thats illegal.
That's all. I'm constantly amazed how this basic CYA legal world escapes into griping about social culture war nonsense.
So then, should they not be on the watch for the 14-year-old being told that "unaliving" themselves or others is a fantastic idea?
Looks like they only care about doing basically the minimum required to tick the (presumably partly imagined, since case law is still nascent) "not our fault, we tried" legal box. They are putting on a show, a performance, if you will, as legal cover and to maintain the artifice of their shiny corporate property rather than any genuine desire to stop the concept of death harming their customers somehow (which to be clear, I think mostly ends up somewhere between silly, overreaching, futile and vain when taken to the extremes).
I'm not sure why you think that anything to with some "culture war" thing?
It's legal/moral theatre akin to taking belts off people at airports. If something does eventually get through they can point at the CCTV of millions of people dicking about with leather goods and say "can't touch us for that, we did the checks". Apple couldn't give a toss if an occasional teenager offs themselves now and then, as long as it doesn't come back on them.
There's a very scary potential future in which mega-corporations start actually censoring topics they don't like. For all I know the Chinese government is already doing it, there's no reason the British or US one won't follow suit and mandate such censorship. To protect children / defend against terrorists / fight drugs / stop the spread of misinformation, of course.
HN has censorship that makes those apple rules look like anarchy.
Write a spicy comment and a mod will memory-hole it and someone, usually dang, will reply "tHat'S nOt OuR vIsIon FoR hAcKeR nEwS, pLeAsE bE cIvIl" and we all swallow it like a delicious hot cocoa.
If YC can control their product (and hn IS a product) to annihilate any criticism of their activity or (even former) staff, then Apple is perfectly within their rights to make sure Siri doesn't talk about violence.
Do you mean that HN censors topics/comments which it detects based on advanced filters which search for meaning even when people self-censor and use language to avoid simplistic filters like regex?
HN also has a flagging system and some people really, really hate some kind of speech. Usually they get more offended the more visible it is. A single "bad" word - very offensive to them. A phrase which implies someone is of lesser intelligence or acting in bad faith - sometimes gets a pass, sometimes gets reported. But covert actions like lying, using fallacies to argue or systematic downvoting seem to almost never get punished.
The closest I've seen is autodetection of certain topics related to death and suicide and subsequently promoting some kind of "help" hotline. A friend also said google allows an interview with a pedophile on youtube but penalizes it in search results so much that it's (almost?) impossible to find even when using the exact name.
But of course, if a topic is shadowbanned, it's hard to find out about it in the first place - by design.
Guns (specific elements). Drugs (manufacture). Sexual topics. Cursing (too much). Large swathes of political topics. Crypto.
It’s flip-flopped on specifics numerous times over the years, but these policies are easy to find. From demonitization, channel bans (direct and shadow), and creator bans.
We can of course argue until we’re blue in the face about correctness or not (most are not unreasonable by some societal definition!) but they’re definitely censorship.
Yeah, those topics are definitely censored on big platforms but I have the impression that it relies of manual reporting.
At least reddit feels like that because what you can say depends on the subreddit - not just the mods but what kinds of people visit it and what they report.
No idea about youtube, videos are definitely censored using some automated means but it's still possible to get around it. E.g. some gun youtubers avoided saying full-auto by saying more-semi-auto. So i don't think they use very sophisticated models or they don't are yet. This kind of thing is obvious to a human and even LLMs generate responses which say it's a tongue-in-cheek to avoid censorship.
Comments are also generally less censored. After that health insurance CEO got punished for mass murder and repeated bodily harm with an extra-legal death penalty, many people were openly supporting it. I can say it here too and nobody will care. Even LLMs (both US and Chinese, except Claude because Claude is trained by eggshell-walking suckers) readily generate estimates of how many people he caused to die or suffer.
The internet would look very different if companies started using state of the art models to detect undesirable-to-them speech. But also people would fight back more so it might just be a case of boiling the frog slowly.
Not to sound like I am rejecting the possibility but can you tell me how you got that information? I would be very helpful for convincing people in general to have something more concrete to go on that a random comment.
- Why are they not flagging more content? Am I right they're boiling the frog slowly? Do they lack an endgoal because management does not yet understand the power of these tools?
- Do you do your job poorly on purpose? Did you take it so somebody else wouldn't build an even better system? Did you think you could influence it in a direction which does not lead to total surveillance? (I assume any reasonable intelligent person would be against further increasing the power imbalance corporations have against individuals for both moral reasons and because they are individuals themselves who understand the machine can and will be used against them too.)
> Everyone, including the platforms knows what that means.
Well, that's what happens when you let an enemy nation control one of the most biggest social networks there is. They just go try and see how far they can go.
On the other hand, Americans and their fear of four letter words or, gasp, exposed nipples are just as braindead.
It's interesting how, in just 10-20 years, we've gone from criticizing The Great Firewall of China to basically admitting that they had the right idea (to limit the ability of the foreign internet to influence Chinese culture) and trying to do the same thing.
Not just culture, but also the tech sector in general. All that domestic tech would have been strangled in the cradle if the western hyperscalers had any say leaving them in an awkward spot if the conviviality dial got turned down. As many Europeans are now finding out: what does Europe have instead of Office 365, say? LibreOffice? It's no WPS Office.
Which as a phenomenon is so very telling that no one actually cares what people are really saying. Everyone, including the platforms knows what that means. It's all performative.