We need a word or phrase for this phenomenon, where we attempt to substitute human pattern recognition with algorithms that just aren't up to the job. Facebook moderation, Tesla Full Self Driving, the War Games movie, arrests for mistaken facial identification. It's becoming an increasingly dystopic force in our lives and will likely get much worse before getting even worse. So it needs a label. Maybe there's a ten syllable German word that expresses it perfectly?
Not quite the same situation, but
is used by Private Eye (British satirical/political magazine) to highlight adverts auto-generated inappropriately to accompany articles on news etc websites.
Of all the suggestions, I like the "Malgorithms" the most. It is catchy, easy to read and probably understandable by normal people as well.
That's just it though. Part of the definition of "algorithm" is "correct" and these things are all just ML output that generate correlated noise.
Hmm? I don't think an algorithm has to give "correct" answers, it just has to be precisely defined. For example, one could say "For this problem, a greedy algorithm yields decent but suboptimal answers."
Merriam-Webster online says: "a procedure for solving a mathematical problem (as of finding the greatest common divisor) in a finite number of steps that frequently involves repetition of an operation" and "broadly : a step-by-step procedure for solving a problem or accomplishing some end".
Algorithms solve problems. Wrong answers are not solutions to (i.e. do not solve) a given problem. Hence, algorithm implies that it provides correct answers within the parameters of the problem.
If you coined this it's great!
I love malgorithms having been exposed to the malicious grift of the healthcare industry.
It's easy to blame this on imperfect technology but I'm not so sure. Couple of months back when all tech companies started their holier than though publicity campaigns with token actions we faced the same issue.
"Blacklist" was banned as term because it was deemed racist. No matter that people understand black and white outside the race issue. So if blacklist is deemed by people , not technology, as racist; thus removing context from the equation, why is AI wrong to assume that "attack the black soldier in C4" is hate speech?
Scunthorpe problem  is used to describe the false positives for auto filters, which are often results of naive substring matching. In a way, the current problem is similar, but on the semantic level.
However, it doesn't cover other cases for other AI mistakes you mentioned, like self-driving.
The problem also goes in the other direction. That is platform rely too much on automation that human signal gets too faint. For example humans have a hard time flagging actual hate speech on these platforms as well. Another example: Every so often there is a front page post on HN where a company like Google will automatically shut down service for a customer (false positive). The customer has a hard time getting through and having this false positive corrected because their signal can’t reach through the layers of automation.
The concept of "so-so automation"  seems relevant: innovation that allows a business or organization to eliminate human employees, but doesn't result in overall productivity gains or cost savings for society that could then be redistributed to the laid-off employees.
I think so-so automation often is used places where there's a lot of zero-sum conflict between workers and management, or where the work itself causes a lot of negative human externalities. (This can be a good thing: it's probably okay to settle for a "worse result" from an automated system if it eliminates a lot of physical or psychological harm to people...some content moderation issues probably fall under this case, but not this one.)
I’d call it “plausible automation”.
It enabled things like Facebook to displace message boards for the most part. Look at Facebook or Reddit, they are barely able to police obvious noxious behavior in English, and military juntas in Myanmar are able to organize on the platforms.
As a non-native English speaker I read "so-so automation" like "sus-automation" and found it oddly appropriate.
I figured it would be appropriate to ask an AI to come up with a label. So I prompted GPT-J with:
AI has proven to be terrible at moderating human content, we felt we needed a word for these kinds of buggy systems and have chosen: "
And GPT-J answered:
Which seems to capture the spirit of unreliable AIs pretty well
> It's becoming an increasingly dystopic force in our lives and will likely get much worse before getting even worse. So it needs a label.
It's not just something that happens to us, it's something we do. We need to do better rather than accepting it as inevitable, and let future generations worry about what the best name for it was.
> Maybe there's a ten syllable German word that expresses it perfectly?
That being said, I propose Urteilsfähigkeitsauslagerungsnekrose: The necrosis that follows the outsourcing of our capability of judgement.
11 syllables, almost as requested ;)
May I suggest “yacht-feet automation”? It focuses on increasing the yacht feet of Zuckerberg, and doesn’t do anything else right?
Also 11 sylabels.
I use the phrase "K ohne I" since years already. Which basically means "künstlich ohne Intelligenz". We all saw this coming. The topic has been gone over in scifi literature. And still, big tech decided its time to roll it out. "A human would also not be perfect, and we claim this algo is better then the avg. human" is the last thing you hear before discriminating tech is rolled out. And since politics is in the grip of commerce, regulations will not happen early enough. We are fucked. 2040 will be horrible.
I don't have a word for the phenomenon, but the problem reminds me of a quote by Wilfrid Sellars.
"The aim of philosophy, abstractly formulated, is to understand how things in the broadest possible sense of the term hang together in the broadest possible sense of the term"
call it maybe philosophy-lacking, or worldview-lacking, but understanding how things 'hang together' in broad terms is precisely what our 'intelligent' systems cannot do. Agents in the world have an integrated point of view, they're not assemblages of models, and there seems to be very little interest than to build anything but the latter.
Composite noun of verschlimmbessern  and Automatisierung (automation).
It's basically perception and reaction without cognition.
In the natural world we would call that instinct. So maybe 'artificial instinct' if we want to keep 'AI' or 'synthetic instinct' because I think it sounds better.
It is basically about using the wrong tool for the job, and continuing to do so even after you (and everyone else) is fully aware of just how wrong you are. Personifying the tool would just distract from the root cause.
"I was using a ballpeen hammer to pound in roofing nails, everything was going great until the hammer's 'synthetic instinct' resulted in a painful blow to my groin and a near fatal three story drop. It'll go better next time - I've painted the ballpeen hammer a different color."
If a human made the same mistake, we would call them incompetent, careless, and negligent.
- incompetent system
- incompetent robot
- inept system
- inept robot
- careless system
- careless robot
- negligent robot
I like 'neglibot'. "YouTube neglibotted my video." "This is my new email address. My old one got neglibotted." "The app works for typing in data, but the camera feature is neglibotty." "They spent a lot of effort and turned their neglibot automod into carefulbot. In another year it may be meticubot.
Slightly related new word: "copiloting" - copying by AI (copy + looting), e.g. GitHub copiloted opensource code.
Then why not copylooting...
Neglibot is nice. Dumbot works too...
IMHO, it's a case when a bug in an Artificial Intelligence system produces the Artificial Idiot, so "AIdiot", or "AdIot"
Perhaps Artificial Stupid System, you do the acronym yourself...
Industrial revolutions has happened few times in the past, and every time it occurs, we change our world to adopt it.
I can't help but wonder, what the world would look like if services in the future will be provided primarily by AIs. How do we adopt them? Do we have to invent a "New Speech" just to make AI understand us better so we can live a easier life?
"Question: Have you consumed your food today?", "Answer: I have consumed my food today."
Or a more subtle example:
"Hi! Welcome to ___. What do you want to eat today?", "I want to eat item one, fifty-six, eighty-seven and ninety-one", "Do you want to eat item one, fifty-six, eighty-seven and ninety-one?", "Yes", "Please make a seat. The food will come right away!" (all without making any Hmm or Err noise)
> "Hi! Welcome to ___. What do you want to eat today?", "I want to eat item one, fifty-six, eighty-seven and ninety-one", "Do you want to eat item one, fifty-six, eighty-seven and ninety-one?", "Yes", "Please make a seat. The food will come right away!" (all without making any Hmm or Err noise)
this already happens today, with human servers. The menu items are numbered, and you tell them the number instead of the name of the dish.
> Do we have to invent a "New Speech" just to make AI understand us better so we can live a easier life?
It's already happened. Have you ever seen an a grandparent unfamiliar with new tech talk to Alexa? There's a ton of them on Youtube.
Blockchain Chicken Farm gives an interesting angle on this. Part of the book describes a AI controlled pig farm. For the outcome to be good, as many variables as possible have to be removed from the pigs' life. For example total isolation from the outside world. Otherwise there is too much for the AI to account for and the training set also needs to increase. What does that mean for our lifes as AI gets control over more aspects? What variables can be removed?
A new vernacular to interface with tools that never reveal the actual state of a system under their control, and forbid you to directly influence it. You are granted the privilege to express your limited desires, from which the system will "learn" your preferences.
If you want a vision of the future, imagine a man repeating "Hey Thermostat! Can you cool it down in here a little?" over and over–forever.
We're going to resurrect the transatlantic accent.
I already have started add a hard 'ng' on 'going to' because my phone keeps abbreviating it to 'gonna'.
That would actually be cool also for non-native English speakers :)
Yeah that's probably not goinv to work for India and the rest of the anglosphere.
Yea, I'm Trinidadian, and even though my accent has changed significantly from living in Canada for 7 years, people and especially voice recognition get confused by some of my speech patterns.
Example is that people always hear 50 when I say 30, because of how I pounce the "y". Anything ending in "th" or "ing" gets confused a lot by people who don't know me.
It's kinda funny to keep track of :)
> goinv to
Did you succumb to the exact same problem GP comment described?
How about calling it a "Buttle" after the movie Brazil from 1985 where a certain Mr. "Buttle" gets arrested and killed instead of a Mr. "Tuttle" due to a fly in a teleprinter.
Nowhere near as popular as the skit with the vikings.
How about "inhuman-ops" ?
I think this has the unnatural, unjust and just basic wrongness about using AI to be like humans.
"human-ops" is the justification to remove human pattern recognition because it's better for a small group of employees (e.g. "we cant let our expensive staff view flags of distressing pictures or boring chess videos, so we will get an algorithm instead". The tech companies HR say that this is pro mental health as an additional way to justify this change and any unemployment.
We are often reduced to mere conformity to what the artificial intelligence can make sense of.
Captcha: "Are you human?"
Human: <Goes on to do a simple perceptual task even a cat could do if they had fingers>
We definitely need a term for this so when we are a victim of this, we can easily raise a flag. I have a few ideas: - Bot blunder - Artificial stupidity - Algofail - Machine madness - Neural slip
Artificial Stupidity stands out to me. Nice one!
In my opinion this is not just about AI. This is more general. We as humans try to fix social issues with technical measures. All the racists are not going to suddenly become good people if we push them to separate platforms.
Yes but at least you won’t be labeled as conspiracy spreading platforms by the /very important/ media, and your woke employees won’t walk out and disappear.
Oh and the current administration won’t pass legislation restricting your platforms or revoking article 230.
My first thought was we should have the Germans create this new word.
Have you heard of the "expert beginner"? Maybe something like that.
10 might be inelegant, or not...
A receiver operating characteristic curve (ROC curve)  describes the tradeoff between sensitivity and recall. No matter how sophisticated we think our classifiers are, the confluence of physics and mathematics will always limit the accuracy of our automated systems. It is just a matter of what kinds of errors we are willing to tolerate.
It's funny that you should mention War Games, because the only way to win this battle is not to play at all. Why are we so hell-bent on restricting speech and burning all these engineering hours trying to moderate something that cannot be moderated? Languages -- and people -- are "transformable" enough to avoid triggering "hate speech" (whatever that actually is, and whoever it is that determines it) algorithms. Let people downvote or shut their computer off if they don't like it, and leave it at that. Are we that scared of words or ideas?
I used to live in a communist country (probably the same one that Mr. Radic lives/lived in), where "hate speech" -- which was called anti-state, or anti-establishment speech back then -- was punishable by a middle-of-the-night visit by dark-clad police. Yet, people still found ways to openly criticize the Party, and there were even popular songs that openly defied them, which only demonstrates that not even human pattern recognition is good enough to detect these things, as you state in your first sentence.
It's a waste of time, but more importantly it is detrimental to society.
> Why are we so hell-bent on restricting speech and burning all these engineering hours trying to moderate something that cannot be moderated?
Because if you allow humans to moderate then those humans start acquiring power. Which is something FAANG companies strive to prevent at all costs.
So instead put power in the hands of giant companies because regular people can’t be bothered to not get hot-and-bothered by reading something they don’t like? What makes these companies so morally pure?
The only way this can make sense - especially on HN - is if the people who advocate for company control of regular peoples’ lives work at these companies.
There's an acronym: OOD - out of distribution - for these situations.
There's no reason YT can't detect chess from hate speech if they updated their training set. Maybe they weren't aware of this failure case, or they didn't get to fix it, or by trying to fix it they caused more false negatives. The way they assign cost to a false positive vs a false negative is also related.
"Cheap AI"/"cheap automation", to dispel the notion that throwing data at a neural network is high science or serious engineering. Or, even more directly, reduce it to "fuzzy matching". AI is just a fuzzy pattern database.
I would call it an "algorithmic oopsies" for the inevitable non-apology when the situation appears on the front page of a major news outlet.
> Ooopsie woopsie! Our AI made a fucky wucky and locked your account for no reason lol. We pwomise nothing pls go away and die uwu PS: If you make a new account we gonna shadowban iwt immediately lmao, if you have any compwaints please write a letter and addwess it to the hospital you were born in.
There is such term as 'human error'. Thus suggestions:
Machine error; Machine learning error; AI error; AI fail.
This is the term for it, but probably not sexy enough when I read all the other suggestions.
Artful Stupidity might go down better.
There's The Scunthorpe Problem, which seems like a specific instance.
I think it's just called machine learning. They're all gonna run into awkward edge cases here and there.
Tbh, so do people. Somebody whos not familiar with chess or board games could think the same thing
In a government system a similar problem is called Bureaucracy. It is similar in the sense that the system is very complex, beyond any single persons comprehension, bureaucratic system is unforgiving in its conclusion, and it is the responsibility of the victim to deal with a false positive using the same (or similarly complex) system to attempt correction.
However this is different from bureaucracy in the level of automation and statistical inference. A bureaucratic system doesn’t do inference (or at least that is not its main function), and the steps between require human inputs (albeit really automated humans most of the time).
I suggest automatacracy which strings together automation and bureaucracy.
Why not algocracy or robocracy?
Computer says No!
Artificial Due Diligence
A-I-opia. Think like myopia or hyperopia.
AI ~ Attempted intelligence
In economics there is Goodhart's law.
'Any observed statistical regularity will tend to collapse once pressure is placed upon it for control purposes.'
Artificial Unintelligence? Artificial Stupidity?
> We need a word or phrase for this phenomenon, where we attempt to substitute human pattern recognition with algorithms that just aren't up to the job. Facebook moderation, Tesla Full Self Driving, the War Games movie, arrests for mistaken facial identification. It's becoming an increasingly dystopic force in our lives and will likely get much worse before getting even worse. So it needs a label. Maybe there's a ten syllable German word that expresses it perfectly?
"Fuck the world" is all I can think of in this context
No. What we need is something that is amazingly simple:
* you, a programmer who coded something that caused company X to lose Y dollars because of a "mistake", have to be on a hook for Y dollars.
* you, a manager who managed a project that caused a company X to lose Y dollars because of a "mistake" by your programmer, have to be on a hook for Y dollars.
* you, a product owner who accepted the what the manager of ta project that caused a company X to lose Y dollars because of a "mistake" by your programmer, have to be on a hook for Y dollars.
* you, the CEO of the company that had a product owner who accepted the what the manager of ta project that caused a company X to lose Y dollars because of a "mistake" by your programmer, have to be on a hook for Y dollars.
Yes, I understand that the cost of a mistake is now higher than the loss suffered by X. That's the incentive to ensure that it does not happen because the wives or husbands or partners of the people who would now have to pay are going to ensure that they do not do take that whose wacky ideas and implement them -- wacky ideas are abstract but the loss of nice housing, nice organic food, nice daycare for the kids and nice scholarship fun is real.
Start punishing mistakes and you will soon have a hard time finding good people to employ. Only bad (and broke) ones will be available.
You forgot the board and the shareholders.
Since you like to invoke a climate of fear, why not add the death sentence to that list?
But ... would you then like to work in that area, if you fear every step you make, can be your last?
Do you think there would be much innovation, if the punishment costs are so out of balance?
I hope this is a joke.
'starbot', from 'star chamber' .
"In modern times, legal or administrative bodies with strict, arbitrary rulings, no "due process" rights to those accused, and secretive proceedings are sometimes called "star chambers" as a metaphor."
"I got starbotted."
"Instagram's automod is a starbot."
"YouTube is too starbotty for your lectures. Better post with your school account."
"We're suing them because their starbot took down our site right after our superbowl ad ran."
"Play Store starbotted release 14 so we cut a dupe release 15. How much will it cost to push the ad campaign back 2 weeks?"
"We use Gmail and Google Docs but not Google Cloud because of the starbots."
"Our site gets a lot of traffic but we don't use Google ads because of the starbot risk. Nobody needs that trouble."
"The STAHP Bill (Starbot Tempering by Adding Humans to Process) just passed the Senate! Big Tech is finally getting de-Kafka'ed. About f**ing time."
Well. The speech police started changing "blacklist" and "whitelist" in programming context, even when those had no racist history; maybe it's time to change it in chess. (After all, white always goes first, that is not very PC.)
Rename "black" and "white" to "second player" and "first player".
First and second implies a hierarchy and uneven power balance. Both players should have their turns simultaneously.
They are uneven, having the first move is a documented advantage called "initiative". Your first move as black depends on the first move that white made, typically you won't have the same response for 1. d4 and 1. e4!
Anyway, I've been looking forward to this day, where SJW start trying to change chess because it's "racist" because white have advantage of initiative and "sexist" because it makes you sacrify the queen to save the king. Looking forward to see that level of stupidity being reached!!
I thought of this and realized it'd actually be a fun game. Both players write down their next move and then move simultaneously once both are ready. To avoid race conditions, if a player moves a piece that is to be taken by the opponent's move, then that player has saved that piece with that move. That creates an interesting dynamic where you may not wish to take the most valuable piece if you predict the other player will move out of the way.
I used to play a real-time version of this called Kung-Fu Chess. Each piece takes time to move to its destination, and when it arrives, a timer ticks down before that specific piece can be moved again. Very fun game.
How would two pieces moving to the same square be resolved? Both lost, or ... ? Regardless of the specifics, it would create a very complicated (but potentially interesting) dynamic when moving any valuable piece within a contested region.
Maybe highest value price wins, with ties losing both pieces.
"To avoid race conditions", indeed!
> "To avoid race conditions", indeed!
Ha! True enough, "a good pun is its reword" ;).
My son and I would play chess this way, with my wife actually moving the piece. We use a dice or piece ranking to determine ending turns on the same square depending on the actual game we’re playing.
Diplomacy works like this.
You can be #1 and I'll be #A.
That sounds like segregation. Putting different players in to different sets.
Yeah, or the Mongooses, that's a good team name. "The Fighting Mongooses."
Be wise, randomize!
Why not try to be more inclusive and have each piece with its own color?
"Actually this rook identifies as bishop"
You didn't capture my king it now identifies as a queen, please stop dead-naming my queen. Funny enough chess already have has a rule that allows for pawns to become queens, touche
Relatedly, the world champion played a game where the player with the black pieces went first to make a statement about racism .
Understandably, it was difficult to adapt to the change: "It is difficult to change your mindset in a chess game with a different start. But if we can change our minds in the game, we can surely help people change their minds in real life."
I'm sure chess board manufacturers would love this. Think of how many new sets they could sell if everybody decided they had to replace their old black and white sets.
Eh, many wooden sets are light and dark woods. Also many checkers boards are red and black.
It’s still ridiculous -like cultural revolution level ridiculous.
At least nature will never change and nights will be black and days will be light.
Until “they” force you to have eye implants that correct for this natural racism
"In the year 2081, the 211th, 212th, and 213th amendments to the Constitution dictate that all Americans are fully equal and not allowed to be smarter, better-looking, or more physically able than anyone else. The Handicapper General's agents enforce the equality laws, forcing citizens to wear "handicaps": masks for those who are too beautiful, loud radios that disrupt thoughts inside the ears of intelligent people, and heavy weights for the strong or athletic."
But the pieces would still be white and black. We just need to recolor them to a color that hasn't been claimed as part of an identity... (looks at rainbow flag) well, shoot...
Infrared-coating player and Ultraviolet-coating player? Chrome player vs. Brass player? No kidding, I like this last idea.
> Chrome player vs. Brass player?
Chrome Player: sponsored by Google.
Sorry, I can't stop from posting this joke!
How about just light and dark? A lot of chessboards don't have strictly black and white colored pieces anyway.
(For the record I think the whole thing is stupid)
"Light gray" is easy to misspell as "light gay", e.g. "light gay knight takes dark gay bishop". IMHO, it's better to use "wine" (w) and "blue" (b) as colors.
If you use English rather than American, you have "light grey" which is less ambiguous.
It would still be light-skinned pieces vs. dark-skinned pieces.
And attack and defense to moving forward and backward. And I guess we should abolish winning and losing while we are at it
Change the colours too. Red and neon brown.
"Night" and "Day"
Could we do some affirmative action and let black go first?
and that is not sufficient. we need to give 33% more moves to black to compensate for the all troubles mounted on them in the past.
Yes, generations of black chess pieces have been discriminated in the past. We should make sure the black wins just as much as white, let's just use a coin flip to decide who wins ahead of the game.
Wow, this site is the fucking worst.
They’re not dismissing systemic racism, they’re mocking some radical proposed “solutions”.
I think the words themselves are racist - black and white. I'd be down with getting rid of them from the dictionary all together.
Edit: Add brown as well to the list.
What about yellow and red? Maybe add grey there too in case we run into “little grey men”
Green as well in anticipation of Elon's Mars colony. We'll just call them dusters.
No, no, no! Yellow and red are clearly offensive to Chinese and indigenous populations of the Americas!
you're the problem, you have brain damage
What a fine mess we've created.
- Popular experiences tend to be better experiences, so we all congregate to the same services
- Homogenous user behavior leads to monopolistic situations, increasing outrage when anything goes wrong
- Even if the government doesn't try to enforce moderation, the company attempts to self-moderate to maintain its image
- The popularity of the service makes human moderation impossible, creating a need for inevitably-flawed robots
I see no solution. The only way to win is not to play.
> The popularity of the service makes human moderation impossible, creating a need for inevitably-flawed robots
That's true, but we might be able to improve things with a bit more human moderation.
For instance facebook is insanely profitable. They could probably increase their staffing for moderation by a pretty decent multiple and still be very profitable.
So the current state of moderation is not strictly a matter of need, it's also a matter of greed in terms of Facebook wanting to automate away jobs they could pay people to do. And given the state of online discourse, it's a decision we're all paying for.
Then you have the problem of bias in human reviewers. I don't think you can solve the problem of censorship with just a few more hires.
There was a star trek channel on youtube which got suspended because he called the fictional race Ferengi “greedy”, which they actually are. Got reinstated after a few days. But it’s getting ridiculous now.
I wonder how The Onion gets away with https://www.youtube.com/watch?v=Q4PC8Luqiws where they suggest visualizing your money related stress as a greedy hook-nosed race of creatures who want to grabble up all your money - and only hire their own kind.
Ferengi looks the same as فرنگی if 'g' sounds as in 'girl'.
"A foreigner, especially a British or a white person." https://en.wiktionary.org/wiki/firangi
My wife is a Ferengi.
It's never been confirmed that the language of chess is the reason the channel was flagged. It's all speculation. A fishing channel being taken offline due to hate speech, for example, is a boring story. The same thing happening to a chess channel is much juicier due to the implication that an AI accidentally flagged the words "black" and "white" as racist. There are a lot of reasons to be outraged by that idea, but it's important to remember that it may not have happened.
And then it blows up here because HN has a lot of people who are disproportionately upset about default branches being called "main" instead of "master".
I'm actually starting to think we only see these stories about absurd censorship to make the more commonplace and pernicious stuff seem legitimate by comparison. "Oh, hahah, our totally legitimate censorship ML that uses language models to isolate people from each other based on predictions of patterns in their thinking made a funny goof! Gee whiz, you got us that time!"
Anyway, Google will be fine. Lots of tech companies have managed to re-brand after getting on board with idealists, just look at Hollerith.
Agadmator, the person who made the video in question, also made a video soon after explaining the situation, and gave some hypotheses on why the video got taken down. In addition to the reason being hate speech, he suggested it may have been because they discussed Covid-19, lockdowns, etc, and YouTube was attempting to stop the spread of misinformation.
The video I’m talking about is here: https://youtu.be/KSjrYWPxsG8
That adds some color to the situation but it's still worrisome that we're becoming so averse to misinformation that platforms are censoring the discussion of misinformation. This isn't going to help the misinformed. For a real world example: I was chatting with a close personal acquaintance who was semi-sympathetic to the Proud Boys privately via FB Messenger. They wouldn't believe me that the Proud Boys had a rule not to masturbate, so I tried to share a link from the PB website. Messenger wouldn't send the message, but didn't outright say it was banned content either. I tried again using an archive.org archive link to the page, same error: "Send failed. Operation could not be completed."
It seems weird to outright ban the discussion of certain things on public platforms, but even more weird to ban it within private chats.
A friend of mine was banned for sending a chat message that said “this is a Mexican standoff” — the people in the room were both Mexican, if it matters.. we were all confused on why he was permanently banned.
I got flagged by FB for inciting violence when my sister said "Your wife is awesome, I'm going to steal her" and I replied "Haha, I'll fight you au".
At least the human moderator who handled my challenge of it was able to consider context.
Banned from what?
Because it implies the Mexican race can’t resolve disputes without violence thus normalizing xenophobia.
I think I'm more offended you referred to "the Mexican race". Mexican is not a race.
Did you miss the part where everyone involved was Mexican?
I honestly wouldn't be surprised if someone makes the argument that this automated flagging is an indicator that chess's language is inadvertently racially charged. And think about the concept of "white goes first." All it takes is a few viral tweets, and suddenly the game of chess is in the crosshairs.
In my opinion, that might be a sign that the idea of drawing abstract connections between words and concepts, that are several layers of indirection apart, may be going too far.
Yeah using language that upsets people is bad, but if you allow enough layers between words and concepts, _everything_ can be argued to be offensive for one reason or another. Or will be soon once something else becomes a hot button issue.
> using language that upsets people is bad
Shouldn't be. Intent should be the grounds for upset, intent only. Otherwise you get a Euphemism Treadmill, and that's a goddamn fucking waste of time.
I've never got why people don't understand this. Judging people by their intent resolves a lot of ambiguity, for both political sides.
If someone gets up infront of a room of 1000 people and says "hey guys!", clearly intending to reference the entire audience, they're not being fucking sexist.
And if you're standing there with 5 racists showing a pepe flag or an ok sign or whatever random garbage it is this week, then you're a fucking racist.
There's absolutely no need for nuance or ambiguity in either case.
You can argue the toss all you want about how to determine whether someone is intending to do something (it's not like you can read minds so that can obviously have a ton of complexity to it), but if you're starting from a position that people can unintentionally do something offensive then everything that follows is just pointless bullshit. You've just built a trump card for both sides into the argument so they can just scream past each other like morons without contributing anything meaningful.
This would save so much time wasting. When someone says "Can you push that to the master branch" there is nothing that ties that statement to slavery or racism so there is nothing wrong with it.
But how will tech Cos show they're woke if they can't just change the names of things and say they did something important?
It's literally a bragging point at my new Co.
> Master/slave model accurately describes the model in a way that people can hear the terminology and understand what is happening without knowing details.
Except it has absolutely nothing to do with slavery at all. The master branch is akin to the master record, that holds the true and complete copy. A master branch evokes mastery of a subject, like a Masters degree.
Except now, everyone just submits to the idea that the word master only has context in master/slave terminology.
Master/slave model has nothing to do with git's master which is "master copy" like as in record mastering. What you say is valid for SCSI or whate et though.
> intent only
Communication is a multiple party activity. It's not just a speaker and a speaker's intent. The recipient and how it's received absolutely matter (and should). I've said plenty of things I didn't intend to be stupid. Still stupid.
Is it ok for the Washington football team to be the Redskins because no current fan or owner intends to be using a racist name?
It's not only the hearer getting upset that matters either. There's room for error and for grace and tact on both sides of a conversation. But it's definitely not just intent only. Humans don't work like that. Hell, even computers don't work like that.
Yeah, this “intent is the only thing that matters” mindset is a naive perspective on communication. People like to act as though there's some liberal bogeyman reaching for social currency by acting “woke”, when what has generally happened is someone was thoughtless/inconsiderate and an offended party spoke up (this whole experience was, of course, quite traumatizing for the thoughtless/inconsiderate person).
It reminds me of all the synonyms and symbols, homophones and homographs Chinese use when referring to mr Xi on Weibo, etc., including the now censored Winnie the Pooh. To get around the censorship which blocks mentioning of me Xi in unflattering light. It’s ever evolving to keep ahead of the censors.
Text is text, and you can't encode intent without assuming that the reader has a similar level of internet experience to be able to pull such hidden intent using context clues.
It's sad we have to go so far down rabbit holes before asking basic questions fundamental to the alleged 'solutions'.
> Intent should be the grounds for upset, intent only.
People can be unintentionally upset. I'm sure we can all think of a time when we've accidentally upset someone. I still try not to do it.
We don't have to force people to change their language. It will happen over generations as we discuss these topics.
> intent only.
I disagree. Intent matters, a lot, and you're right, but it isn't the only thing. Right now I think we fall on the other side, that reception is all that matters (in the bias training I receive they specifically mention that it is 100% reception and not intent). I believe the law works on reception because that's easier to quantify. Intent is very tricky. You can do something that most people would consider wrong and just say "well I didn't mean it that way." (the inverse can happen too, but less people are likely to start a legal case out of spite compared to people defending themselves. It is tricky)
I believe that there is a middle ground somewhere. Where that is I'm not sure and I think we need to work together as a society to figure that out. I think somewhere in there there is a "reasonable" set of norms, and we have other laws to suggest that we can use this as a basis. But even this can be tricky as there are many different cultural norms and customs. It isn't even just ethnic customs. In America we have very different regional customs that often butt heads. I think we need to recognize that people are different and operate based on different values and often this is fine.
But I think a big thing we've lost in our current standing is good faith. There's three parts to any form of communication. 1) The idea that is within one's head that they are trying to convey to the other person. 2) The words, body language, inflection, etc that are used to codify this idea (aka: encoding). 3) The understanding of that language that was used to convey the idea (aka: decoding). Humans are pretty good encoders and decoders (we wouldn't have made it here where we are if we weren't) but there are limitations. Language is extremely messy and we often don't think it is because we're so used to it. But you can look at words being used today and you'll often find that people are talking past one another because they are using different definitions of the same word and actively refuse to interpret the other person's intended message (as an example, every internet conversation about capitalism/socialism/communism). The point of communication is to pass one idea from one head to another head. It requires understanding that there are these three components. If we do not act in good faith then we cannot communicate. With that knowledge it suggests there are two different actions to take if one wants to act in good faith. The communicator should try to encode their thoughts as best as they can, attempting to understand their audience (aka: speak to your audience). BUT we often forget that the listener's job is to decode, to do their best to determine the idea that the communicator is trying to convey (aka: __intent__). In fights we will say "but you said..." even knowing what was intended as a way to win. This is not in good faith but is so prevalent.
When conversations are about mic drops and one upping another person, communication cannot be had.
To you point about intent vs reception, I think the way the law works is actually more along the lines of "how a reasonable person might receive this". Which is perhaps harder to quantify, but IMO strikes a good balance. However I totally agree with your point about how some communication has become more about scoring points than having an empathetic and thoughtful dialogue
thinks the case of yelling fire in a movie theater jokingly
Surely though if you cause panic and people get trampled you would face consequences no? You probably won’t get accused of hate speech but I hope it could go up to manslaughter.
Thanks for this. I think it is shocking that so many people still use this.
What about yelling bomb on an airplane?
I remember many years ago when colour schemes/UI themes were still called "skins", and forum discussions about them often yielded amusing racist-if-taken-out-of-context sentences like "do you like white or black skin" and "I have dark skin, but I prefer the white skin." Not a single person was offended or outraged, everyone saw the racial associations but clearly understood the context and was more amused than anything else.
I'm of mixed opinion whether people were actually more intelligent or level-headed back then, or whether the current "ultra-PC/SJW-ism" trend actually started as a joke that got taken too far and adopted as truth by the gullible.
I have no knowledge of the example situation you provided (I don’t recall any such jokes about software skins), but consider the possibility that in some cases where “back in the day we did it and no one was offended” it was in fact the case that people who were offended weren’t welcome or weren’t able to voice their opinions.
I’m very familiar with skins, Winamp skins being the archetypal example for me. I meant that I don’t remember any such jokes deliberately conflating software skins and human skin tone.
> whether the current "ultra-PC/SJW-ism" trend actually started as a joke that got taken too far and adopted as truth by the gullible
It started with a few German philosophers and social theorists in the Western European Marxist tradition known as the Frankfurt School in the interwar period.
> Deep SJW lore
I think you're actually correct, although the roots go back further. People don't understand the historical academic context of modern intolerance.
If you would actually like to know the history of the current trend, read Cynical Theories by Helen Pluckrose and James Lindsay
Jokes that evoke racist hatred are not good, though. You don't actually know that NOBODY - literally you said that not a single person - was offended.
Also, so what if someone was offended? Isn't that mostly irrelevant to this debate? The goal isn't to stop people from offending others, the goal of changing our speech is to reduce the unknown harm that words can do re: normalization of hatred of minorities. The 'jokes' you describe aren't funny and do in fact have a potential to cause real harm in the world.
I would posit that unchecked hatred towards minorities online for decades is one of the reasons we are in this 'mess' of language today.
> Regardless, there's no reason to assume that humor of this nature serves to normalize racial hatred.
Yes, there is. This is a very well-researched topic.
I'd like everyone to stop speaking and stop writing anytthing because it MIGHT offend someone. /s
You know that many people are advocating for replacing the terms whitelist and blacklist, right?
I don't see how chess is any different.
Chess is different in that the pieces are literally black and white in their color.
Blacklist and whitelist are used as linguistic symbols: black==bad white==good.
That is pretty different to me.
I'm no expert, but I thought the black and white thing originates really from night and day. It is easier to see when there is light (often perceived as white) than it is at night (often perceived as black). We used white and black to convey the color of the sky. A white color reflects light while a black color absorbs light. This is how I've always thought about it. I never associated this with skin color until someone told me. I still have never internalized this because it just doesn't make sense to me.
I'm open to being wrong but to be this connection of archetypal meanings and skin color is a stretch. I don't look at a white phone or black phone and think good or bad (in fact I have a black phone and prefer dark colors while my skin tone is the opposite). One which requires a lot of fundamental change in language and how we think. Because I'm sure I'm not the only one that has codified this representation in my mind. And most of us should understand archetypes are not how you go about judging the world or people. I don't see a person dressed in red and think "angry" (which would be a different emotion in a different culture), or yellow and "happy". I just see colors.
That is pretty different to me.
So allowed items were written white ink on black paper and disallowed items were written black ink on white paper? Or the other way round maybe?
You're right it isn't different, it was a stupid idea with firewalls and it's a stupid idea with chess sets.
I think if we let racists own the color wheel then we've lost.
Because the pieces really are white and black, or light and dark. The list is not black.
And what? should i rename my black desk or black chair or better, get a new colored one, because "someone decided to call them that way"?
But literally anything can upset anyone. You can never satisfy everyone at the same time.
This was in my opinion already readily apparent the instant that whitelist/blacklist came under fire.
“Political correctness: is communist propaganda writ small. In my study of communist societies, I came to the conclusion that the purpose of communist propaganda was not to persuade or convince, not to inform, but to humiliate; and therefore, the less it corresponded to reality the better. When people are forced to remain silent when they are being told the most obvious lies, or even worse when they are forced to repeat the lies themselves, they lose once and for all their sense of probity. To assent to obvious lies is in some small way to become evil oneself. One's standing to resist anything is thus eroded, and even destroyed. A society of emasculated liars is easy to control. I think if you examine political correctness, it has the same effect and is intended to.” ― Theodore Dalrymple
Or cooler heads prevail like at the Académie Française who recognize that sexual genders are completely unrelated to grammatical genders despite what activists try to say.
So we may just get some people who push back and tell people that chess isn’t racist and it’s people who are injecting race where it doesn’t exist (such as here in chess) who are the problem.
Have cooler heads prevailed in this regard? “Progressive” Americans degendering Spanish by referring to Latino people as “Latinx” seems to be going as strong as ever, despite the protests of actual native Spanish speakers. In their haste to appear progressive, people who say “Latinx” are ironically engaging in linguistic colonialism, as it were.
But that’s the problem with progressives. They trip over themselves trying to be at the front. And yes, I’ve asked people of Latin descent if they use latinx in their speech to which they respond no and that it’s a North American invention and that in Spanish it’s Latino for sing male, Latinos for plural males or combo males and females, and Latina for singular female and latinas for all female but never latinx for any combination of the above.
> Americans degendering Spanish by referring to Latino people as “Latinx”
Depends, do you speak Spanish? If so, there's a governing body - the Real Academia Española (RAE) - and they have referred to the "x" ending as an abomination. It is rejected from the style guide and not acceptable Spanish.
If you want to speak Woke Proto-Spanish, by all means do. Just realize it's not Spanish and it's spoken by a tiny fraction of a percent of - generally American woke-sters desperate to cling to Latin or Spanish culture as they realize they are actually American and as such - not oppressed minorities (the worst of fates!). This is why Oxford recognizes "Latinx" but the RAE does not.
> despite the protests of actual native Spanish speakers.
The only people I've ever seen mad about "Latinx" were American internet free speech advocates.
It's none of my business but personally I prefer latine. IMO there's no need for white English speakers to tell Spanish speakers their language. We're all on the journey to a world with more than two genders together. Spanish speakers will figure out their own path to inclusivity.
Latino is already inclusive. There's nothing to be done, as Latinos aren't preoccupied with creating fake problems.
> referring to Latino people as “Latinx”
Isn't this connecting a Latin conjugation? Which in turn would be westernization? I understood westernizing people to not be the right thing to do. (Which to be fair, Spanish does originate from Europe but Latin people are not). I never understood this. If someone has a good explanation I'd love to hear.
Related: Referring to American Indians as 'Native Americans', which is often seen as over-inclusive by American Indians themselves since it implies you're talking about Natives to the entire North and South America. While not the worst thing, when you are specifically talking about the native tribes the United States pushed out and forcibly moved to reservations, the term 'Indian' is codified in law and is what the group themselves embraced as their identity so that, as a whole, they could bargain with the United States government to obtain compensation for the tragedies endured.
The problem seems to stem from 'American' being synonymous with the United States, when in a literal sense it means the entire North and South America continents. People will probably know what you mean with context but it can be confusing, so adding on 'Native American' just requires more explaining whenever you bring it up when not among peers.
That’s a perfect example of something that literally every single time I’ve seen it mentioned was in the context of people expressing outrage at other people’s activism, and never in the context of an activist actually advocating for it.
Do you mean that it's an imagined problem or that it's an example of a truly terrible idea?
Because I see people using it all the time on TV. It's not an imagined problem.
Read the literature from your nearest HR department and there is a good chance you'll see this term being used in earnest.
I've heard several PhDs use it. They were white English speakers and liberal in their political leanings. It comes across as even more pretentious than high schoolers aping the latest wokeness.
Isn't Latinx supposed to be Latino+Latina? Surely those two words areactually gendered (in the biological sex way), unlike most words which are gendered in a purely linguistic way.
Latinos is how you gender Latino+Latina in a "purely linguistic way", but some people don't like it, so they made a new word. The masculine word is either gender neutral or "truly" masculine depending on the context, but the feminine counter part always refer to girls/women.
> Or cooler heads prevail like at the Académie Française who recognize that sexual genders are completely unrelated to grammatical genders despite what activists try to say.
But that's not really true. I always learned that, for example, ils (grammar-masculine they) should be used when referring to a group of people where any of the people are sexual-gender-masculine, but elles (grammar-feminine they) should be used when referring to a group of sexual-gender-feminine people. Ils and elles have the same rules when referring to a group of inanimate objects depending on the grammar-gender of the objects.
You're both right. In grammatically gendered languages, various situations and context are present. Sometimes, people get worked up on a non-issue (like the latinx example other commented). Other rules have a more debatable impact, like the famous "in groups, the masculine prevail".
Interestingly, other approaches existed in the past like the rule of proximity where the gender of the closest element will dictate how the verb and adjectives will be written.
Languages are an ever-changing thing. I think it's healthy to propose and discuss grammatical changes if it makes sense, but everyone should be aware of what they are actually talking about.
I wouldn't be surprised if the Google moderator AI becomes the source of truth on what is offensive. If google doesn't delete it than clearly it is ok. If google does delete it then it is offensive regardless of anything else.
Or it will at least become a cheap barometer used by journalists: Materials so offensive that they are automatically rejected by all major social networks.
That's the scariest worst idea I've read all day.
> In 2019, Magnus Carlsen and Anish Giri – who as of July were the number 1 and number 10 players in the world, respectively – promoted a #MoveforEquality campaign as a way of acknowledging social inequalities. In their game, black moved first and the line was, “We broke a rule in chess today, to change minds tomorrow.” It was billed as an anti-racist statement, but some took it as a suggestion to change the rules of chess to black having the first move.
Others have pointed out it's been done -- so it will continue to be done again and again until something gives. But I'd like to point out at least Go is safe for now, since black goes first! (However, white is used by the stronger player when not doing nigiri or playing a handicap game... And I'm sure some artificial drama could be manufactured based on which color you want to give draws to by giving or taking 0.5 from the perfect komi of 7. There's no safe space.)
This happened last year. The Australian Broadcasting Corp (ABC) hosted a discussion about this
Or what actually happened was the radio show asked if white going first was racially based, concluding that it was not. But conservative media spent days getting themselves outraged over it before it even aired.
You would be interested in this, starring Magnus: https://www.youtube.com/watch?v=VPFI3-W8Fqo
Yes, not too dissimilar to Github changing the branch "master". Is there a list of things like this that match this pattern that would be easy for people to go after given a few viral tweets? I feel like if there is such a list, it'd be less shocking when the inevitable happens.
Real estate is moving away from Master bedroom/bath/suite
Chess is not only racist but also sexist. How come the king is the most important piece on the board but the queen is completely expendable?! And, for goodness sake, the game features actual white knights.
The Queen is a significantly better piece. The King needs to be protected and is borderline unusable until end game, where the Queen is the most powerful piece from start to finish. This is so evident that in higher levels of play, people just resign when they lose their Queen.
In higher levels of play people rarely just “lose” their queen.
Can't tell if sarcasm.
It's clearly racist that White plays first.
White goes first because black was considered a lucky color. So if black went first it would have double advantage, from being first and from being the lucky color.
I think you just made that up.
It'd be still racist if black startrd first. Its not an argument...
So that would mean Go is racist for black always going first?
Given there's 500 or so hours of video uploaded per minute (or some other huge amount), i'm not sure we can expect YouTube to moderate each potential violation. Each video constitutes a miniscule amount of revenue.
The only solution (I see) to this is for YouTube to charge for each upload - say $1 a video (there may need to be different prices in different parts of the world), this wouldn't detract the majority of uploaders and would pay for checking hate speech, copyright violations etc.
This is from March and was discussed heavily on here at the time.
I am surprised international chess organizations haven't denounced racism and announced the plan to change "white" and "black" to "A" and "B".
"A" and "B" would imply that English is superior to other languages. It also implies hierarchy since "A" comes before "B".
Chess is sexist because the game ends when the King dies.
I say we should ban Chess. Cheers.
In order to enforce social justice you want a group of activists to impose restrictions and police other groups of people? How would they convince those people to give up their freedom?
> How would they convince those people to give up their freedom?
"Something something AI algorithms"
I bet that's why SJ is so focused on AI ethics. They want to abuse the amplifier effect of AI to win battles in the social wars.
Oh no. Please. Not chess. Can’t we just leave this one alone?
No. Everything must be examined critically through the lenses of social justice. Chess is a Eurocentric and thus colonial game only valued because of its expression of whiteness. Dominance of an opponent of another color reenforces normative racism and the white pieces going first internalizes white supremacy to Black, brown, and indigenous peoples. I won’t even go into the obvious sexism and misogyny of the emotional labor of the womxn piece moving the longest distances in all directions while being valued less than the male piece.
We should expect and demand equity in all our so called “games” so that everyone wins.
Ugh, I'm so screwed up. Your comment would be taken as dead serious in some circles and as parody in others. Based on the HN demographic I'm guessing the latter but I'm not sure.
I hate to do this because the parent is good at letting their dry humor speak for itself.
But yes, it's parody.
It's very good. I was looking for a tell, but couldn't find one. They even capitalized "Black" while leaving "brown" lowercase, as is Proper according to progressive style guides.
Obviously your comment is sarcastic, but this is worth correcting: Chess is a Eurocentric
Chess came from Persia, or maybe India, and spread both east and west along the silk road trade routes.
That's a bit of a misconception. Modern chess is European. Shatranj was a much less dynamic and interesting game.
Well, it seems it was culturally appropriated by Europeans.
if i am writing a youtube comment and care about it, i always recheck if the comment is still there after a couple of minutes and then a couple of days. because the comments are now "disappearing" more and more frequently the last time my comment got automatically deleted right away was a couple of weeks ago for "bottle opening" words (in my language) put together. replacing a few letters in these words with different same-looking characters helped for some time, but eventually even these got deleted a few days later. i should probably give up using this last google service i still use
I had a video flagged, and marked as adult content because the title had "Hump Day" in it.
I am not sure in other parts of the world, but in Australia Hump day is the middle day of the week, A.K.A Wednesday.
This is very similar to the Myntra's logo incident in India.
That's absolutely a saying in the United States as well. At least, I've heard it used regularly in both Washington State and Montana.
I guess this just shows how backwards and racist Chess terminology is. It may have been fine back in the day, but I want my children to grow up in a world where Blacks and Whites aren't at war. The sides should be switched to much more neutral names, e.g. based on light - lumen/umbral or something based on trees - teak/mahogany. Obviously we should also replace "attack", "check" and "mate" with non-hate-speech - maybe "push", "jeopardy" and just remove "mate", as you can say the same thing by "I believe you have run out of valid moves to make and thus I win".
Not like this is without precedent - I remember back when pieces were said to kill each other and then it was replaced by "capturing". Come to think of it "capturing" as an objective is also rather problematic, maybe we should call it "liberating", since you're really returning these peasants who were forced to serve their king back to their homes.
Maybe they should train their networks on memes and make it do the opposite ;-).
Must be a slow news day. Youtube algo f-ups are just part of platform at this point.
And that makes it even more important to highlight them. We shouldn't consider censorship a normal everyday event just because some parties do it far too often.
I'd stay level higher.
It's our reliance on dominating platforms.
Their wrong choices of wrong technology negatively affects lots of people.
Government here suppose to interfere but lots of bribery is in place to prevent anything meaningful to happen
This is a perfect example of "be careful what you wish for". The Wired position seems to be "just put more resources into policing speech, which is a good and necessary activity". My hunch is that cases like these (false positives, at least, as currently judged by the current authorities) will proliferate just as the criteria for judging what constitutes unacceptable speech do. I would challenge the would-be censors to define specifically, in a way not requiring an additional consultation with them for more infusions of judgement, just what types of utterances that they want to suppress, and why. The closer one gets to this, the more the case for censorship will dissolve. Tl;dr: they are complaining about ambiguity in the implementation of the solution, while having failed to define the problem.
It is obvious that there are no such problems when ai is used for driving cars and flying drones. /s
This reminds me of a story from a previous era of automated content moderation...
When I was a student at the University of Cincinnati, I was a member of a group called LARC which stood for Laboratory for Recreational Computing. The main purpose of LARC was to get the University of Cincinnati to subsidize our yearly trip to DEFCON, but I digress.
The UC mail servers, or at least the ones where the LARC mailing list was hosted, had some kind of stupid search and replace censorship to replace naughty words with cleaner equivalents. The cleaner equivalents were in ALL CAPS of course.
So a few members of LARC were working on a project to build a classical arcade cocktail table game out of Linux and MAME and some other stuff. I don't remember the details. All I remember is that the mail server transformed this into the "MALE GENITALIAtail table".
This became its official name. I think the MALE GENITALIAtail table was eventually installed in the student union.
> All I remember is that the mail server transformed this into the "MALE GENITALIAtail table".
I now realize I have a Pac-Man MALE GENITALIAtail table, thanks.
The clbuttic mistake.
Let me off this euphemism treadmill! Please, I'm getting ill.
Well at least it wasn't for corrupting the youth.
When does AI start being smarter than us? Can't wait.
This is no censorship. Youtube only protects us from false information!
We demand censorship.
We refuse to pay for it.
We cry when it's done on the cheap.
And it's all their fault!
Buttlenagged = Archibald buttle + nagging by software
Chess is systematically racist, so this is fine
Where there is rejection for hate, there will be love for hate.
Not the first time. Bound to happen.
My main gripe is that Google has no money or brains to actually enlist humans to solve such problems.
I mean i think Google has both money and brains
That's what happens when you mix clueless relativism with figurative language.
It's probably suicide. Not hate speech.
And they weren't talking about chess. Skydiving and the abstract of jumping.
But let's love everyone's cliche from 2010, long ago solved if it ever existed AI is racist or too not racist.
> “White’s attack on black is brutal. White is stomping all over black’s defenses. The black king is gonna fall … ”
Fortunately there's an easy solution: we can just replace "white" and "black" with neutral alternatives like "allow" and "deny" or "pass" and "block".
Was this reply made by an AI? The context of the suggestions seem GPT-3 close...
This is what GPT-3 (davinci, the 175B parameter model) generates for real:
* Prompt: ">White’s attack on black is brutal. White is stomping all over black’s defenses. The black king is gonna fall..." Fortunately there's an easy solution:
* GPT-3 Response:
Just don't play chess!
This is the only solution. The reason for this is that the "chess is bad for you" argument is a logical fallacy called "affirming the consequent". It goes like this: If A, then B B Therefore A In other words, if chess is bad for you, and you play chess, then you'll be bad for you. The fallacy can be seen by simply replacing "A" and "B" with two different statements, for example: The sky is blue Some birds fly Therefore, some birds are blue. See the difference? The argument against chess can be logically rephrased as "Chess is bad for you, and those who play chess will be bad for you. Therefore chess is bad for you."
"Chess is bad for you, and those who play chess will be bad for you. Therefore chess is bad for you."
Can't find a flaw in that argument.
They are referencing the whitelist/blacklist debacle.
Bleep bloop. No, I was just testing out Poe's law.
Google's pursuit of profit is responsible these and innumerable more injustices. Those who would defend Google often claim that automated moderation is necessary at Google's scale, but does anybody really doubt that Google would still make more than enough money to stay in business if they hired more humans? Automated moderation is not necessary.
Having the AIs flag things for humans to review prior to anything being banned seems more manageable.