https://github.com/BlueFalconHD/apple_generative_model_safet...
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.
At what point do the new words become the actual words? Are there many instances of people using unalive IRL?
Your point stands when we start replacing the banned words with things like "suicide" for "donkeyrhubarb" and then the walls really will fall.
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.
[1] https://en.wikipedia.org/wiki/Euphemisms_for_Internet_censor...
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.
The future will be AIs all the way down...
The example photo on Wikipedia includes the rhyming words but that's not how it would be used IRL.
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.
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.
Karen Hao interviewed many of them in her latest bestselling book, which explores the human cost behind the OpenAI boom:
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.
(This one is sfw, not all of the comics are)
Even urban dictionary doesn’t contain a definition for skub as a slur.
People talk about tiktok algorithm on tiktok. I don't even know...
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?
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.
Online env ban the word suicide. No one uses it. unalive is not banned. Discussion is the same, word or no word.
Vernacular 101.
What about this then: https://en.m.wiktionary.org/wiki/skub
Unalive is one of the popular ones, but it's a whole vocabulary at this point. Guess what "PDF file" stands for.
Sincerely the child of a parent who committed suicide. He mentioned suicide a few days before.
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?
[0] https://en.wikipedia.org/wiki/Polari
[1] https://languagelog.ldc.upenn.edu/nll/?p=6538 (CDT links broken, use [2])
[2] https://chinadigitaltimes.net/space/Grass-Mud_Horse_Lexicon_...
If the bigots start using "thank you" as some code word, should we stop saying it, lest we pollute our non-bigoted discussions?
bigots drink coffee too, maybe we should stop drinking it, because something-something...
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.
Not even to match the current language. How would you censor LeBron James? It's French slang for jerking off[0].
[0]https://www.reddit.com/r/AskFrance/comments/1lpnoj6/is_lebro...
• 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:
Quit being overly pedantic. We all knew there was an unironic purpose for the gesture before it became ironic.
I don't have anything against China per se, IMHO it just was completely foolish to not insist on full reciprocity from the start.
That's all. I'm constantly amazed how this basic CYA legal world escapes into griping about social culture war nonsense.
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
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.
Just that they suck at coming up with pithy new slang terms.
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?
I would say most likely yes.
I strongly doubt you do that. Whether you like it or not, the Nazis defined what the swastika means now.
(<s>Qwen</s> Mistral is French, but I have no idea what stuff would be censored in France)
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.
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.
[1] https://www.chicagotribune.com/1992/01/26/hands-off-34/
[2] https://www.nytimes.com/1996/08/18/weekinreview/what-s-a-ok-...*
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.
Taboos are a cultural thing, and the world is (thankfully) very far from having a monoculture shaped by NYC's neurotic intellectuals.
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.
No, there's no difference.
> 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.
>>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.
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".
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).
> performative (adjective, sense 2): not sincere but intended to impress someone, prove that something is true, etc. (https://dictionary.cambridge.org/dictionary/english/performa...)
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.
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.
>>> 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.
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.
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.
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.
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.
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.
† proving that TikTok's system actually analyzes every frame of an uploaded video with OCR of some sort to see what's on there.
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.
It's perfectly OK in Greece.
Including the LLM platforms themselves.
Manual reporting is an adjunct/additional method, and goes into the training data set after whatever manual intervention occurs too.
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.
Unalive is mostly to avoid censorship same as ahh. But once they enter common usage it's not really about censorship anymore.
The PADI standard gestures are used and recognized all over the world to mean these things.
Feel free to ignore that any of this exists of course - it makes our lives easier. It’s a constant arms race regardless.
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.
- 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.)
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.
Good documentary on rogue waves: https://www.youtube.com/watch?v=EfNc_6EjbMU
It's true there's no casual relation in the other direction, if that's what you mean - law does not define morality.