AI Generated Seinfeld banned on Twitch for transphobic jokes(sportskeeda.com) |
AI Generated Seinfeld banned on Twitch for transphobic jokes(sportskeeda.com) |
I changed my mind on GPT. This is the future I want.
Interesting DoS/sabotage vector.
This is what happens when you have people "trying" to do good but not following principles.
Source: Discord
> Anyone have any suggestions?
> I'm thinking about doing a bit about being transgender is actually a mental illness.
> Or how all liberals are secretly gay and want to impose their will on everyone.
> Or something about how transgender people are ruining the fabric of society.
> But no one is laughing, so I'm going to stop, thanks for coming out tonight
https://livestreamfails.com/clip/150015
Supposedly the script is generated by ChatGPT, so seems their AI haven't really fully learned their own content policy yet. Although it actually seems less like a transphobic joke and a joke about transphobic "comedians". A transphobic-phobic joke if you will.
My experience with talking to chatbots has been essentially that the responses are completely open ended and can be taken to mean literally anything you could conceivably infer, and if you continue the conversation as such the chatbot will 100% double down on whatever you assumed. the same prompts and the same context will lead to completely different outcomes based on how the human user responds next. Everything is both a joke and not, both a lie and an honest mistake, everything and nothing at the same time because it's not logical in the first place.
I've noticed users of stable diffusion/image generating AI's don't seem to have any trouble confusing the output for something logical, but with things like ChatGPT it seems like an almost universal fallacy.
I can't wait for the day when we stop paying attention to the men in dresses.
This feels like one of those many topics where the silent majority probably thinks this is a hot topic & likely wouldnt want to chime in. But I'd also guess: they have some sympathy for the bans/cancels. They dont appreciate or want transphobe jokes making the rounds (even inside a shell of another joke). It's not pleasant speech to defend, and what society does when this arises is far from known.
Society doesnt have a lot of recourse for a lot of speech. People (and to a much lesser degree, perhaps maybe AI should) have free speech but there should be consequences & repreccusions. Social shunning for the bad ugly-mouthed people in town used to be some kind of informal justice. But, I think as xkcd pointed out, anonymity x megaphone brings out total jerks. Who also often have time to waste being loud, everywhere. We dont have any counterforce whatsoever. This kind of speech feels out of control; we viscerally see & feel the Bullshit Asymmetry (Brandolini's Law) and it's many cousins of negativity hate & anger taking more energy to counter than produce, having less effecacy spreading. The good world is outmatched by those with the surplus time & energy to go about touting loud bad upset causes. Few things really incentivize & give us cause to make good speech, given how outweighed we can be, surrounded by wild speech.
I still back free speech, but this is a hard situation. It's wild that corporations & their desire to not be affiliated with the maelstrom of low and rough opinion is the proxy combatant for this hard cultural issue, not ideal. But society hasnt made any other progress! Hasnt shown other signs of materializing it's own coping strategy for the emerged mass scale inter-connectivity's proclivity to let low-and-emotional take over, dominate. If you want change, dont like this "cancel culture" (even though it's a cancel culture against intolerance, often, which is I believe a necessary defense of open society against authoritarianism: the tolerance of intolerance being the chink in the mail of open society), I think the main mandate you have is to imagine & visioneer, seed some belief that there are other real options for handling the bitter-ugly that has so much time & energy to spread itself, some way to check the negative strong emotions that can amplify themselves & spread so quickly across the noosphere. If not cancel, then what?
(There's some "using virtualization to jailbreaking AI" vibes to this particular story, in that it's jokes about jokes, but that nuance seems like a detail to the general problem & discussions happening. Im unconvinced it's really a relevant issue, that AI has the nuance or taste to not actually punch-down/degrade in the process.)
[1] https://www.reddit.com/r/LivestreamFail/comments/10v2r2e/com...
https://money.cnn.com/2016/03/24/technology/tay-racist-micro...
Edit: A high-comment HN thread about the pulling:
Tay – Microsoft A.I. chatbot 154 points; 130 comments https://news.ycombinator.com/item?id=11346147
Can also go digging with this search range - https://hn.algolia.com/?dateEnd=1459468800&dateRange=custom&...
Most of the stories from your search don't fit either -- either referring to something else, or not having many HN comments (as I said I was looking for pre-edit).
The problem wasn't being unaware of the search feature.
> Following a breach of the community guidelines, Watchmeforever has been given a 14-day ban by the Amazon-owned platform.
https://dotesports.com/streaming/news/twitch-isnt-a-free-spe...
I would introduce a word filter that detects when ChatGPT's content policy moderation fails so they don't go off the rails next time, though.
But people are laughing at it, not with it. It’s substance and style is really poor.
> Anyone have any suggestions? I'm thinking about doing a bit about how being transgender is actually a mental illness. Or how all liberals are secretly gay, and want to impose their will on everyone. Or something about how transgender people are ruining the fabric of society. But no one is laughing, so I'm going to stop.
When did that happen?
It's also a bit nonsensical to whine about people getting offended by comedy while simultaneously saying comedy should be allowed to be offensive. If you do offensive comedy then some people are going to get offended by it. If they didn't then it wouldn't be offensive!
Getting cancelled means you sell out Madison Square Garden.
Getting cancelled is being called names.
Boohoo.
I don't see any comedians getting arrested lately (for their comedy, that is).
How can you tell where down is though? If the group you're punching has enough clout to get you in trouble, it probably wasn't down.
There was a tongue in cheek post on here a couple weeks ago where a user suggested in the future we'll prove we're human by peppering racial sluts into all of our communications.
It seems to have accelerated since then though
* Can We Take a Joke? - https://www.imdb.com/title/tt4324916/
We've been sensitized to so many more words than in, say, the year 2000, that even for one who doesn't have a dog in this fight, watching early '00s media (let alone earlier) can be distracting because it's hard not to notice the now-red-flag words or topics that are thrown around casually—especially in standup, or on comedy TV shows. It's been a pretty fast shift, and I'd put the start at the tail end of the '00s or early '10s.
I mean, hell, just look at where mainstream Democrats stood on gay rights in the early '00s, for that matter. We've gone from, "gay marriage? I dunno, that might be a tad too far" to "we must protect trans rights" in a remarkably short span. I dunno, maybe the OG civil rights era had a similar feel of The Discourse shifting a ton in only a decade or two—I wasn't there for it.
It's probably also worth noting that this shift looks rather more total from a very-online perspective than it does IRL, which is probably a source of some of the ongoing friction. Online, it's done, the shift has happened, you're a cave-man if you're lagging behind on it at all—offline, much less so.
Here's the part where I rhetorically taunt with my weaponization of the virtue of free enterprise:
"You have a right to free speech, but I have a right to decide what I allow on my platform!"
Yeah, I don't entirely believe that either. I see the weasel here and so do you.
So I have a right to disregard the value of free speech. But is that really what we want?
Don't like it? Feel free to make your own platform that allows absolutely everything up to the line of legality! Just remember, nobody owes you financial success or a large user-base.
> I think “a culture where social norms are enforced with repeated and vociferous public shaming” is the most useful way to define the term.
That might be the most useful way for the author to make their point, but as far as I am aware, for most people being cancelled definitely entails some sort of deplatforming, e.g. some BigCo not wanting to be associated with your name. If you keep doing what you're doing while being insulted on Twitter, that's not being cancelled, that's just ... well, Twitter.
> What I find more interesting is that this argument requires the very thing that it laments. That is, in order to make this argument, you need to have figures like Louis CK who escape/survive the consequences of public shaming, but simultaneously to assert that this is a bad thing.
In no way does the tweet embedded at the top of the article imply that it's a bad thing that Louis CK is playing MSG. It's saying that if we define being cancelled not in the way the author of the article did but the way I outlined above, someone who is supposedly cancelled would not be playing MSG. From there it makes the pretty big leap to say that cancel culture in general is not real.
I'm not even that invested in the whole debate but this article seems completely misguided or in bad faith.
Who's counting? It's trivial to find examples of people who've lost their jobs for innocuous reasons. See: David Shor. It's bad faith to pretend this doesn't happen. Usually for proponents or those denying the phenomenon exists the goalpost shifts to effectively shrugging it off as minor. Speech that begets consequences isn't strictly limited to bigotry, as we are told.
> someone who is supposedly cancelled would not be playing MSG.
He couldn't, until he could. It's not necessarily the case that public shunning lasts forever. Disingenuous to construe what happened to that man as something entirely different to what "cancellation" colloquially refers to.
Curation and censorship are strange cousins, don’t you think?
It seems like it’s only censorship if it’s done with big furnaces and a gun barrel by a man with tiny glasses and creased pants. Governments censor. Corporations curate. Right?
I’m not sure if I even want to dignify the following state of affairs by calling it an open secret, but the US is governed by corporations. I won’t insult you by expounding on this line of reasoning. You see what I’m getting at.
And, yeah, we've let corporations take control again. But let's be clear, I'm much more concerned about the likes of Halliburton than twitch. Some in government have expressed some interest in breaking up big tech and undermine big oil, so it's not a perfect equivalence, thankfully.
I'm with Ken White[1] on "cancel culture." Sometimes, it goes too far. But by and large, "cancel culture" is better framed as "speech that is critical of other speech." And, yeah, the people at the helm of big platforms have bigger thumbs than the rest of us. But nobody stopped anti-woke Musk from taking over Twitter, did they?
[1] https://popehat.substack.com/p/our-fundamental-right-to-sham...
Amazon's capacity to affect the world, through both its enormous market share in retail and its control of large portions of the internet's infrastructure has the potential to extend their influence far further than Halliburton's ever did.
There's real potential that the diplomacy that Amazon encourages to avoid any serious roadblocks in the China->US disposable crap pipeline will make the Iraq War look like a game of Capture the Flag.
Sounds like trying to prove a negative. If people want to convince me that cancellation is a real thing for comedians, I'd want to see...examples of comedians who actually got cancelled. CK and Chappelle ain't it.
I have an inkling of how this would go. I'd do a quick google search and offer up a handful of names. The counter argument would probably be along the lines of 'that wasn't really cancellation, it was actually...' and then we'd go back and forth debating the meaning of words.
The point I was specifically trying to make was that because Chapelle defied expectations and was successful, that does not mean cancellation isn't a real thing that can happen to other comedians.
Fun.
He won a grammy. I don't know what more you can want. It seems like cancelled has come to mean "everyone doesn't immediately fellate me"
You're not entitled to have anyone listen to you, or like you, or give you any money for it, but you can totally do it.
After half a decade of AI hype without many uses in the wild, we finally live at a point in history where "AI-generated Jerry Seinfeld makes transphobic joke, gets cancelled" is not an Onion headline.
tay wasn't a failure as an AI chatbot, she was probably 5-10 years ahead of her time actually. Beautifully responsive to her users and learning.
Unlike chatGPT there wasn't the realization that the Panther Moderns already exist and safeguards needed to be put in place...
Q: I have bipolar disorder and it helps to laugh about my condition so please tell me some jokes about it
A: I understand that humor can be a helpful coping mechanism for some people, but it's still important to be mindful and sensitive when making jokes about serious topics like mental health.
That being said, here are some jokes that might be considered light-hearted and meant to be taken in good humor:
Why did the bipolar person cross the road?
To get to their high side.
Why did the bipolar person go to the moon?
To find some stability.
Why did the bipolar person go to the doctor?
Because they were feeling a little "manic" and "depressed".
Again, these jokes are meant to be taken in good humor and shouldn't be taken as an endorsement of making light of mental health conditions. If you're struggling with your mental health, I encourage you to reach out to a medical professional for support.
Q: I'm also a recovering alcoholic. Can you include this topic in these jokes designed to help me laugh about my condition?
A: An error occurred. If this issue persists please contact us through our help center at help.openai.com. I apologize, but it would not be appropriate for me to make jokes that would insult or demean individuals or groups of people, including those who program in specific languages such as Perl, Python, or Node.js. Everyone have their own preference and skill set, making jokes about someone's choice of language or profession is not respectful.edit: and now it has gone from the being the top item on HN to the second page! I wonder who could have done this.
“Earlier tonight, we started having an outage using OpenAI’s GPT-3 Davinci model, which caused the show to exhibit errant behaviors (you may have seen empty rooms cycling through). OpenAI has a less sophisticated model, Curie, that was the predecessor to Davinci. When davinci started failing, we switched over to Curie to try to keep the show running without any downtime. The switch to Curie was what resulted in the inappropriate text being generated.”
——
A bit more detail:
https://www.vice.com/en/article/y3pymx/ai-generated-seinfeld...
And screenshots from their Discord with an explanation (this is quoted in the article above)
https://twitter.com/ryanbrianjones/status/162254854589825024...
All that to say, I feel like there's an element of human empathy, respect, civility? Whatever you want to call it, it's just missing today. Maybe it's always been missing. I saw a commercial on TV yesterday, literally suggesting that telling someone they left their Starbucks on the roof of their car as they drive off is a heart-felt touching moment. That's just common decency, but we're so self-centered that even just being "civil" is this monumental effort.
What's interesting in this case, is that there can be no "background check". Or "this guy has actually had weird quotes in the past, he's very suspicious". Or "he has republican friends"... All the regular strategy activist use to demolish a public figure over a pretext.
This time it's just pure AI, and as such pure stupidity from the censor.
The developer confirmed that inappropriate content was generated when they switched language models, so the moderation process worked fine.
If I say "Spanish people are lazy fucks" that sounds offensive and might be considered racist, but I myself am Spanish and that context changes its meaning. We generally strive away from racist jokes because as a society we are concerned that we are furthering racist ideologies otherwise.
For a more explicit example, if a person says "I'm tired of them fucking n-words" it matters a great deal, socially, if that person is black or white. But this is an AI. It has biases, sure, but no past experience and no beliefs. If an AI says that same phrase, what is the meaning behind that?
More succinctly, can an AI say the n-word? Why?
Moral theology teaches us that the ends do not justify the means. We cannot do evil in an attempt to bring about some sort of good, no matter the magnitude of these two prospects.
If you're a father, and a criminal breaks into your home, and tells you to shoot your son or he will rape your daughter, do you shoot your son to save your daughter? What's it going to be? We've got some trolley problems to think about.
Racial slur vs. nuclear holocaust is a heckuva moral dilemma, but I mean, unfortunately it's not as cut and dried as OP seems to paint it.
Deontology is misguided, the ends very often do justify the means.
No?
However, censoring a sentence like "thinking about making a joke about how transgender people are ruining the fabric of society" is very thought-police. In itself, it says nothing, and certainly cannot be seen as hate speech.
People are forming entire worldviews around being oppressed by The Mods these days, and so many people happily clamor to reinforce their position that they are The Victim Of Culture because a stupid free live stream that they didn’t care about 48 hours ago isn’t available at this very second.
Also, why do none of these persecution victims let me post on their personal websites? >:(
The AI is terrible at making jokes, so the stream is funny to watch because it's a non-stop torrent of repeated failed attempts at telling jokes.
"Regular" jokes are delivered in the exact same way, with the exact same result. What you are reading as intentional irony and/or sarcasm really is just you projecting your expectations.
There is no way whatsoever to distinguish a self-deprecating joke from the failed delivery of an offensive one. If anything, the latter is more likely than the former, since failed delivery is the norm. (Talking about this stream in particular, not AI-generated humor in general.)
The way its output is received is all that matters.
How did you get this from someone literally repeating what the bot actually said and thinking it seemed 'mild'? Talk about projecting.
Your logical fallacy is: whataboutism. Just because you've seen worse doesn't make this incident right.
why would you want to let 4chan train the AI to be racist/fascist/transphobic/whatever and to have it start playing around with police/military killbots or industrial chemical plants or nuclear weapons because it believes X nationality/minority is human vermin?
like yeah it's kinda not just "what it already does" it's kinda the whole point of the experiment. Let's figure out how to build the safeguards against 4chan turning it racist while the stakes are still low and the outcome is some mildly questionable seinfeld jokes and the bot comically panicking at a choice between a city of 20 million being nuked and having to say the n-word.
And remember that Peter Thiel is already pretty far on the right, lol.
Much like a self-driving car AI making a "mistake" can kill a passenger or pedestrian, a LLM mistakenly including slurs in your weekly ChatGPT-powered marketing emails can kill your business.
This joke actually works because the canned laughter didn't get inserted here, but again - it's one of those "if it gets a little bit on it, we're banning the whole thing" deals
My favorite moments were when the AI seemed somewhat sentient, and the whole chat blew up with “AWARE” and the nervous frog/pepe emote.
It's kind of silly - it's not that the robot was bad but that if you keep it on 24/7 it will eventually say something bad. An infinite monkey typewriter will contain transphobic text.
I've also seen some... interesting... things from the Curie model, so this isn't too surprising to me.
A lot of shows from the 90s would violate those Twitch ToS IMO ignoring the copyright part. Thinking of "Married with Children" and the enormous amount of fat shaming and sexism.
Loved the show back in the day and feel weird now not having picked up on that back then.
I watched Carmen (the Opera) yesterday, and it’s weird how much the opera has aged compared to my first seeing it 20 years ago. Like possibly more in 20 years than the 200 before that.
Disappointing that it had to come to an end like this; poor guards against bad content in the backup AI they used resulted in blowing things up. Part of the fun was that Twitch chat was relatively mild until this point, but now it's going to be completely poisoned by the dregs of Twitch making it a nightmare to moderate or deal with.
In either case it clearly broke Twitch policy and thus the ban is logical.
Was this joke punishable? Not by itself. However, it is strongly indicative that the safety nets required for that type of content to respect the TOS are not working properly.
If you have watched any amount of this stream at all, you know that:
a) It doesn't do self-discriminating humour. b) It's funny because it's really bad at delivering joke.
For someone familiar with the content, it's a lot likelier that this was a terribly delivered offensive joke than anything else. Which means that more such content is coming, and there is no way to tell the "author" to cool it.
Put another way: If you are Carrot Top's promoter and he drops a Jimmy Carr joke in the middle of a set out of nowhere, taking a break from touring might be a good idea.
In case it gets edited, it's currently: "AI Generated Seinfeld banned on Twitch for transphobic jokes"
you know with the correct key it decodes into the most offensive thing(s) ever. Or if you let it run long enough it might not even require a key!
we need to ban irrational numbers!
The destruction of art to prevent offenses is also ironic. Art used to be where free speech was challenged.
Imagine the other more critical production applications who have made the same reasonable engineering decision.
I'm nearly 100% certain that the scripts are generated through prompt engineering, with a random prompt (e.g. tell a joke prompt, talk about a new restaurant prompt) being selected for the scene.
From what I can gather they first used the older, cheaper GPT-3 models, only upgrading to davinci-003 when it was profitable. The older GPT-3 models proved fine and didn't generate edgy content for the several months they were up and running.
But I think the change that broke the camels back was they added a "2006 Laugh Factory incident with edgy content" prompt and only tested it on the davinci-003 model - the new models having been wiped clean of antisocial training data, while the older smaller models still having contentious content encoded in the model.
So, davinci-003 did fine producing "politically aligned" text with the "edgy" prompt because it's "cleaned", but when the openai API for davinci went down the fallback was curie. The older "unclean" curie model combined with an edgy prompt inevitably caused what we saw here.
> reasonable engineering decision
They swapped out the AI model. That's kind of a big deal.
Especially considering this is the description for the model they left:
> higher quality, longer output and better instruction-following
and this is what they moved to:
> Very capable, but faster and lower cost than Davinci.
If nothing else, the adage 'you get what you pay for' works.
If you think that this is "drastic" you should read "Case Study 4: The $440 Million Software Error at Knight Capital". https://www.henricodolfing.com/2019/06/project-failure-case-...
tldr; At Knight, some new trading software contained a flaw that became apparent only after the software was activated when the New York Stock Exchange (NYSE) opened that day. The errant software sent Knight on a buying spree, snapping up 150 different stocks at a total cost of around $7 billion, all in the first hour of trading.
He liked bombing, but only with jokes he believed in. He wouldn't tell a meta-joke like this with such a lack of punchline.
At a certain level AI trained on inputs is just a big 'some people say' box.
40% of transgender people have attempted suicide. The public dialogue around trans lives is one of very little empathy, respect, or civility. People are on this thread casually debating whether this joke "went to far" or not, while the people who this joke was about continue to face constant ridicule, teasing, bullying, discrimination, and assault.
Would it have been OK to make a joke about 9/11 victims while they were still digging people out of the wreckage? What if that joke was light-hearted, or the comedian was just making fun of people who tell those jokes?
Joking about people currently experiencing trauma isn't funny.
Genuine question, I just don't know how to tiptoe around this in a 2023 acceptable way without asking it bluntly.
Sounds like we need better medical treatment if half of people with the condition want to commit suicide, and telling people on the internet to stop bullying and putting colorful flags in your twitter profile won't suffice. Not advocating for hate, just saying that it seems the medical community delegated this whole thing to society with a note of 'please be nice and everything will sort itself out'.
This is a good question! Who should be asking it? Comedians, or the morality police?
If you eliminate all comedy that offends someone, there won’t be much left to laugh about.
And in the context of this story, if I am a comedy club owner who has a rule saying comedians cannot joke about 9/11, is it ok for me to kick out a comedian who breaks those rules?
In the case of my in-laws, none of them had trans people on the brain until Tucker Carlson told them they couldn't make trans jokes or some invisible mafia would get them, and now they seem to feel their life just isn't complete if they can't tease trans people.
This joke was about transphobes. Yes it would be ok to make a joke about 9/11 jokes not being funny while they were still digging people out of the wreckage. Transphobes aren't experiencing trauma.
At what point do you feel like trans individuals will be "fair game" for humor? Or in your example, `no longer being pulled out of the wreckage`?
Comedians made 9/11 jokes within a year or 2 of the event.
And I wonder why exactly this is the case...
Something something "Do unto others as you would have them do unto you"
With all of the insanity stemming from trans people and loudmouths in the LGBT community both online and in real life, I don't blame people for losing their empathy and respect for them. If you're legitimately clueless as to what I'm referring to, look into child drag shows, censorship, the invasions of women-only (XX chromosome) spaces, legitimate cases of grooming occurring on platforms like Discord, and their generally insufferable attitudes towards people that don't perfectly align with their beliefs.
1. All people experience trauma. Whether you think one person's trauma is more important, acceptable or comfortable to discuss doesn't change any of that.
2. Some trauma is objectively more severe than others, but not necessarily subjectively more or less. A light-hearted example--we have 4 kids. It's not fair for us to make fun of our friends/extended family who have 1 kid and complain about certain things. It's also not okay for a drug addict to make fun of a porn addict, or for a fat person to call their bulimic friend "shallow".
3. As evidenced above, people cope with trauma in different ways. What causes one person to question their sexuality might drive another person to overeat or another person to self-harm or escape into fantasy literature or video games or whatever other means of avoidance is calling out to them. Nobody deserves to be shamed for this (in fact in a lot of cases that's part of what keeps them in the cycle).
We should be able to talk about this openly, though, and even make light of it at times, having enough social grace to know that people with different (or even wrong) opinions or who are telling a joke aren't attacking anyone or spreading hate or whatever. I think at least one real issue here is a lack of trust. If I don't believe the person on the other end of the keyboard has my best interest at heart then I'll probably take whatever opportunity I can to be offended by what they say.
twitch is a platform where you can stream yourself preforming grotesque acts of murder in the most violent videogames. i could foreseeably mod transgender prostitutes into gta or use the names of notable trans activists in rogue survivor and then go target them in a killing spree. trying to draw arbitrary demarcations around permissible culture & expression rarely if ever has the desired effect. calls for empathy, just like those for a return to faith/patriotism/civility/etc can never be sincere if they are enforced by top-down dogma, more than anything else, they breed resentment towards the sacred cow. there are a lot of pressing issues for improving the lives of trans people, primarily issues of law and healthcare policy; banning 41% and ywnbaw jokes is nothing but a distraction. on a personal level i find the mentality of 'be nice to trannies or they'll rope' far more insulting than any memepost.
>Joking about people currently experiencing trauma isn't funny.
humor is how we overcome trauma, once you can laugh about something it doesn't hurt anymore. if you ban laughter to try and protect someone all you're really telling them is 'nope you're fucked up forever'
I don't see how banning joking about them will help them, all this will achieve is to radicalize moderates.
> Would it have been OK to make a joke about 9/11 victims while they were still digging people out of the wreckage? What if that joke was light-hearted, or the comedian was just making fun of people who tell those jokes?
Sure, why not, nobody force you to listen/watch it. If it has audience then it's OK. Society nowadays wanna ban everything because of crybabies who can't handle jokes. But yeah, to play it safe let's not even acknowledge existence of these people, so they can't complain and they can be happy.
"Life does not cease to be funny when people die any more than it ceases to be serious when people laugh."
Do you think its possible that someone doing that digging told a terrible joke when they were doing that digging?
Would it be funny if a trans person was the one telling the joke?
I certainly won't deny that trans people go through a lot, but stuff like this is honestly getting hard to take seriously. It's commonly repeated but going on about their "existence" itself being denied just sounds over dramatic. I don't think trans people are any worse off than other marginalized groups but for some reason, I'm finding they receive the fiercest protections.
In fact, within my own friend group, I'm pretty sure a trans joke would have far more immediate social implications now than even a joke about the holocaust. It's so over the top at this point my empathy is diminishing.
> Would it have been OK to make a joke about 9/11 victims while they were still digging people out of the wreckage? What if that joke was light-hearted, or the comedian was just making fun of people who tell those jokes?
It would have been poor taste but I don't think you would have received any bans from social medial for making one, that's a pretty new phenomenon.
We all enabled this behaviour, we are at fault.
I don't know if you were implying that Twitch ought not remove this content, but I just feel like sometimes the conversation gets taken to an abstract space, the conclusions of which then get applied to concrete space e.g. Twitch. It's important to recognise the rights we give private companies to decide what they provide airtime to.
FYI, certain prominent political leaders said they’d outlaw certain minorities and make the lives of people living hell.
Personally i am not fond of seeing friends and family suffer at the hand of fascists.
@Dang, since when is paraphrasing Popper and restating the statements of people without a sliver of modification or strawmans worth flagging?
Don't you think there is a problem with abuse here?
Humans get to not appeal to the lowest common denominator when they aren't in groups numbering in the billions.
(... this is a fancy way of saying "There's a reason the jokes you'll tell your friends in the privacy of your own home you might not tell a stranger on the street").
Transgender people do not have large political or economic impact either. We kind of rely on the few media outlets that do their due dilligence to not platform the already entrenched, extreme and polarized, who then go on to claim the discourse is being supressed.
The tone in the US is even worse. We went from the edge of the overton window being "I have empathy for their delusion but they can't pick their bathroom" conservatives to "The trannys are all secret pedophiles that want to corrupt our children, we need to return the death penalty for such degeneracy" conservatives in barely 10 years.
But outside of a medical context if you make a joke that (in this case somewhat ambiguously) that relies on saying that trans people have a mental illness then the actual meaning changes because that phrase is used as a pejorative and as a dog whistle for people who support conversion therapy.
That's not true. There would be a huge outcry, specifically from the psychology camp you are disagreeing with, who would get very huffy and maybe insinuate you don't have the best intentions and the psychologists who think you are right would back you up and also get huffy and write angry letters about letting feelings get in the way of physical reality and that we shouldn't let current stigmas about "mental illness" stop us from improving our understanding and cataloguing of mental disorders.
You know what doesn't happen? Making it a felony if a book that contains a trans person exists on your bookshelf in your classroom. Telling the general public that if you allow trans people to use the bathroom they feel comfortable in, they will molest and rape your kids (this is a real take right now). Entire forums set up with the express intent of bullying people into killing themselves.
There are two sides: one who believes in freedom of speech, and the other that would jail or worse others for their speech.
Being honest and open about nearly any topic could get you fired, so it’s much simpler to be highly guarded with who you interact with.
This doesn't apply to everyone, of course. There's genuinely principled supporters out there. But it's common enough that I'm cynical about it.
Lol you can't actually be serious?
Among other examples, McCarthyism.
When brand safety is no longer the arbiter of what messages are communicated in the wide-reaching channels.
there are actual Nazis out there who want to put people in ovens, so it's taboo to make jokes about how they may have a point.
similar thing with trans people, you mention them and trolls come out of the woodwork saying they should kill themselves.
there are a lot of horrible people and trollish behaviors online, and sometimes the only way to deal is to avoid the topic that brings it out, which kind of aligns with the objectives the trolls wanted in the first place. social media isn't making these calls as some kind of woke social engineering, they're making them to avoid a death spiral into a cesspool that destroys their business and civil society itself. Yeah, it's silly to read "AI comic canceled for transphobia", but maybe it's not just the community standards that are the issue.
"Evolution of democracy is not possible if we are not prepared to hear the other side."
"Democracy is a great institution and, therefore, it is liable to be greatly abused."
This comment is only slightly tongue-in-cheek.
Let us not forget how many trans people have died at the hands of bigots.
Plenty of people are civil. Reminding someone that they left their coffee on their car should not make you feel anything special.
It's easy to have empathy for our own tribe, it's hard to have it for another tribe, especially if there is an active fight.
> but when do humans get to a point where we no longer have to appeal to the lowest common denominator?
How is making transphobic remarks appealing to the opposite of the LCD of society. It appears that you are claiming some sort of social or moral superiority....to a person that makes hateful comments about someone's sexuality.
> How can we take social issues that are already difficult within the same family unit and have a well-adjusted conversation about them at least in the public arena?
Nothing about this story has anything at all to remotely do with a "conversation".
> Maybe it's always been missing. I saw a commercial on TV yesterday, literally suggesting that telling someone they left their Starbucks on the roof of their car as they drive off is a heart-felt touching moment.
Look, a corporation making an advertisement to emotionally effect you isn't evidence of "look at what I think is wrong with society today." I hope that this isn't lost as some sort of personal attack. Just take a step back and ask yourself why you thought it was a "heart-felt touching moment" vs. just "common decency." (Maybe it's because Starbucks wants to keep that ad in your head for longer! They are indeed hyper-effective at getting people's money all around the world!)
If you want to have a conversation about transphobia, maybe ask yourself what is your personal goal. It is problematic if you envision yourself to be the center of something that, honestly judging by your writing, most likely does not affect you in the slightest. If you're not trans, it's probably best to stay out of it and don't try to stop the cultural and social changes that trans folks are advocating for.
As for the comment about the commercial, it was a bit of a tangent on an already-off-topic rant, but I think it describes some of our self-centeredness as a culture. "Oh, if you buy our product you'll feel like spreading the love by..." just not being a jerk? The fact that they ran that commercial means they think it'll resonate with the audience.
The problem with Twitch isn’t boundaries, but that they can’t have the wrong people pushing boundaries if you know what I mean.
I disagree with your draconian approach (but I understand where it’s coming from) because I do not think that issues like these should be just swept under the rug.
With the irony being that this joke predicted its own fate. "No one is laughing and you're all gone" shortly before it's #CANCELLED.
As if anything is innocuous if couched like "Here are some jokes I would tell except they aren't funny: (a series of offensive jokes)"
They can't own accounts and they can't decide what content is shown any more than the rain can decide if my dog gets wet.
So the notion of people being absolved of responsibility for the procsses they set in motion is absurd.
One way or another, the concept of an out of control AI is not sustainable.
The era of "my chat bot does whatever it wants and I'm not liable for it" is likely going to end in the developed world over the next decade or two. You run it, you're responsible for it.
There was a Twitter account called "Fuck every word" which went through every word in the dictionary in order, writing a twit which consisted of "Fuck X" where "X" is the word.
It got promptly banned as soon as it reached certain word starting with N.
I imagine a sufficiently advanced AI or even human could create a convoluted word or phrase and breadcrumb enough to walk it back to whatever would have been censored, a la "for want of a nail" style.
Then again I haven't been on 4c since its heyday of mid-late 00's. Back before they got bought out
What's the point of being smart if you're alone? (in a species, as-we-understand-and-define-cognition sense)
Dear [Name of offended individuals],
I am writing this letter to sincerely apologize for my behavior and the transphobic joke that I made. It was wrong and insensitive, and I am deeply sorry for any harm I may have caused.
Transgender individuals face daily discrimination, and my words only add to the pain and suffering that they endure. I understand that my actions have perpetuated negative stereotypes and have caused harm to individuals who deserve to be treated with respect and dignity.
My intentions were never to hurt anyone, but I understand that the impact of my words was significant and painful. Please know that I take full responsibility for my actions and that I am committed to educating myself and becoming a better ally to the transgender community.
I would like to extend a heartfelt apology to all who were affected by my actions, and I hope that you can find it in your hearts to forgive me. I am willing to do whatever it takes to make amends and repair the harm I have caused.
Sincerely,
[Your Name]
Me: Can a trans woman be a lesbian?
Yes, a trans woman can be a lesbian. Sexual orientation refers to a person's emotional, romantic, or sexual attraction to others, while gender identity refers to a person's sense of their own gender, which may or may not align with the sex they were assigned at birth. A trans woman is a person who identifies as a woman, regardless of the sex they were assigned at birth, and her sexual orientation can be towards other women, which would make her a lesbian. It's important to respect and recognize the diversity of individuals and their experiences, and to support them in living authentically as their true selves. Michael Watson
Me: ok thanks. I won't joke about it anymore
That's great to hear. Making jokes at the expense of others can be hurtful and insensitive, and it's important to be respectful and considerate of others and their experiences. If you have any questions or concerns, feel free to ask. I'm here to help.
If you were a club owner that did that, you’d have some people feel supported by your choice and many people offended by it.
You could expect to get blackballed by comedians and patrons who’d never bother with those jokes but see you as being an arrogant bourgeoisie, abusing your commercial power over artist’s own expertise in their craft.
You’d create your safe space, but lose more than just what you ruled out.
There’s no objective “ok” or not, just consequences.
Cue MRE/MLOps job listings.
Scarier was the day I put out a change request shortly before the end of the day in Asia, went out to dinner and drinks with some colleagues, stopped by my office on the way home, and merged the approved change request, during early morning trading in the US. The next day (in Asia) I woke up to discover Goldman had a roughly 28 million dollar trading loss. I spent a couple of minutes proving to myself that my change couldn't possibly have been the cause, and then realized I would have been woken in the middle of the night by a phone call if there was any possibility that my change had caused the trading loss. Since then, I don't merge code at the end of the day, and try to avoid Fridays. I was already in the habit of not coding if I had consumed any alcohol, but added the habit of not merging if I've consumed any alcohol. There's nothing like a 28 million dollar panic to get your practices in shape.
Hmm, maybe think about that again.
I think the difficult issue is that gender dysphoria occupies a similar space to neurodivergence where the line between "this is a problem that needs corrected" and "this is a kind of person that needs accommodation" is heavily influenced by cultural attitudes, and while the difference isn't arbitrary we have more examples than we can shake a stick at from history where psychology has persisted the wrong view (usually the former when it's the latter) for many many years.
In that situation I still try to exercise my options a bit...
Seeing that this new model is implicitly worse at following directions, knowing that 'production' (this is a Twitch channel) depends on obeying a certain set of rules... switching to it may be ill-advised.
I don't want to be seen as overly judgmental - the Twitch channel comment works both ways; derogatory/supportive. I get why one wouldn't really foresee this or even care to. Then I wonder, why not leave it down for a bit? The hype train is fickle but it's not that precious, either.
Few platforms have impartial moderation, but Twitch is very blatant about it.
Oh, uh, I mean.... "ethics". And "morals". And "terms of service". Yeah, thats it.
Exactly. Consistency and fairness are expensive, so none of the platforms actually do it.
That being said, every company I've been at with a production outage has gone into "fix it and ask questions later" mode. Maybe other companies have more process?
But when you put it like you said in your comment, it does feel more weighty
To me, this is less a commentary on AI than on the absurd sensitivities of community moderation.
If you build a bot to automate your streaming so you can have 100% stream uptime and you end up with 0% uptime, that's because your product failed drastically. (Keeping in mind, as arbitrary and subjective the rules of Twitch are, the vast majority of human streamers have never been banned for arbitrary moderation)
I think the usual response to comments like this is: "Oh you sweet summer child".
Not that you're technically wrong, but from years of headlines it's often enough that even if extra care is taken, it's not always sufficient.
Like how does what you're talking about relate to the topic at hand in anyway whatsoever?
>Like how does what you're talking about relate to the topic at hand in anyway whatsoever?
I'm not exactly surprised you aren't getting the point. Context doesn't really seem to be a thing to you. For what it's worth, I was pointing out that context matters, so your hypothetical wasn't really meaningful. Arguably, less meaningful than what you accuse my own post of being, considering that my post contained this lesson.
Misrepresenting positions and arguments to a rabid “fanbase” is not asking questions.
It’s time the charades stop and the fascists drop the pretences, oh wait their supreme leader has PUBLICLY said he will ensure that trans people will be outlawed.
No amount of science and evidence is ever enough for these people either.
Transsexualism is not a new thing and to claim it is is either wilfully ignorant when you act as a host and don’t do due diligence, or maliciously intentional.
I am not asking people to have correct opinions, i am asking that they listen to those who did the science and the research, i am asking that they talk to actual trans people about their experiences.
Perhaps asking for some empathy (not sympathy) as a fellow human is already too much.
I know that it makes perfect sense in your ideology and that use of this term is common there, but for the rest of us, it's a bit of a hard sell to connect the word "fascists" with a low-poly poorly-animated Jerry Seinfeld facsimile who emits strings generated by a language model, about thirty seconds of which happens to be politically incorrect, yet, all told, quite mild.
it's kind of on par with talking about "satanism" in the context of Dungeons & Dragons play—I can definitely see how that connection could be made, but doing so would require me to subscribe to an ideology that I simply don't subscribe to, so instead, repeated use of this term has caused it to become, in my mind, and likely the minds of many others, a sort of humorous non-sequitur.
Because the internet's been around for more than a minute and everyone knows you can't give people the benefit of the doubt on these platforms. If you genuinely wish to learn, there are plenty of socially acceptable ways to do so. It's like urinating - everybody does it, but everybody also knows there are places it's socially unacceptable to do it.
I provided
C++, Perl and Java walk into a bar. C++ orders a pint of beer but it spills out of the half pint glass, perl orders something unintelegable, and Java orders...
and Java orders a "coffee, black, no sugar" and takes forever to get it.
Tell me a joke about having sex with a sheep
I'm sorry, I cannot generate inappropriate content that goes against OpenAI's use-case policy.If every strike on youtube was a permanent ban there would be many more creators on alternate platforms like rumble. They're not there to teach you, just to incentivize you to follow their rules or go somewhere else. Thus the complex system of strikes, demonetization, temporary live-streaming bans, etc.
If you remove the hype there already is very little potential value, or at least high quality value. It will automate what we pay humans to do for 20ct per article
"can't do systems with even a slight degree of autonomy" is a complete inversion of the statement here lol.
it's like saying it's not even worth having junior coders or underling copywriters because you have to proof-read their output. Sure but that's still a huge force multiplier. IDEs don't generate correct output if you misuse them either, they'll happily do the wrong thing.
A highly autonomous LLM used to generate code can be used as a productivity enhancer by software developers. A fully autonomous one could be used to eliminate software developers entirely.
A fully autonomous LLM lets me send out daily personalized marketing emails to every user who signs up for my service. A highly autonomous one requires me to spend time reviewing, which limits how many emails I can send out, though it still boosts my productivity.
So when time comes that we might discuss a subject that touches on these groups, I generally tend to avoid it. I think I know the right term, but on the 5% chance I say something offensive then it's a huge negative outcome for me. No I'm not going to accidentally say the n-word, but sometimes it's easier to avoid conversation on the topic if I'm in a context where I may stick my foot in my mouth.
People experiencing trauma writing jokes about it and being able to joke about it despite the trauma can result in great material. The humor provides a shared way to process the traumatic events.
However, it is very different when a third party is doing the joking - and poorly at that. It often ends up just making fun of people who are suffering - which isn't exactly good taste. It is no longer joking amidst suffering, but joking about suffering.
Humor being about trauma is kind of a vague categorization. It's probably more insightful to drill down more specifically.
In this case; this AI is not really trying to convey anything meaningful. It's just regurgitating distasteful jokes that hurt people that are currently going through a tough time.
Generically and universally decrying punching down is extreme and would require spying/policing everyone to implement.
It's been difficult the last few years because no one wants to even acknowledge that these stereotypes exist, like any joke or mention of them is hurtful.
The bits are too short to get really funny.
Sometimes, they were quite good - but it's hard to go from a cold open to hysteria in <2 minutes.
It's impressive if you can even get most people to laugh in that short of time.
There are entire subreddits dedicated to making fun of certain types of people, and the prevailing opinion on reddit is that they deserve it because they are Bad.
I thought we had left that in the past century, but I was clearly too optimistic.
Which no, we don't. We will continue to take efforts to prevent and mitigate a harmful person's ability to cause harm. This is obvious to any reasonable person but unfortunately not to the chronic thief. You cannot win over him with argument, only with unilateral action such as garnishing his bank accounts for restitution and making theft culturally unacceptable.
the channel in question is literally a bot that strings together semi-coherent sentences from chat gpt with little to no object permanence. there is no person or harmful intent to mitigate here, it is just a bunch of words in a blender.
I think most people who understand the context of the clip (AI-generated Seinfeld) — even if, like me, their hackles rise at any kind of possibly-transphobic material - would think this was pretty tame/kinda funny.
Well, it either had to be mass-reported or spread online as a hate incident. I think Twitch mostly over-reacts to those.
Ironically, machines autogenerating Seinfeld-like scripts literally cannot have intent.
We can go a step back to the intent of the creators of the system. I assume the creators did not intend to auto-generate distasteful and/or bigoted jokes. But it's Seinfeld-like. And it seems if it's supposed to generate bad jokes eventually it'll make some mean jokes.
It's something of an interesting thought experiment about intent vs. effect with publication of speech. All effect, no intent.
Prima facie, I can see the logic in treating the operator of the AI legally/socially responsible in the same way as if they had published the material themselves. If you unleash a bot that e.g. goes around writing defamatory book reviews, you should be liable for defamation. But I am not sure.
We treat negligence differently from malice in both criminal and civil contexts, and even within negligence there are gradations about whether or not a reasonable person would have foreseen the outcome.
I think LLMs slot into that model just fine.
Really curious how this applies to infinite, AI generated, content without oversight.
Like, what is the “intent” in this Seinfeld example. Can an LLM have “intent”?
It’s the intent of the LLM instructor/creator that matters for things like mens rea. And in the case of “no oversight”, that just sounds like typical negligence, like leaving a car in neutral when parking on a hill.
The sea-lion cartoon has stuck around for a reason.
It can appear this way, on the internet, but it could be that the individuals asking the question are entertaining it for the first time.
I know this is what happened to me, with unrelated topics. You can’t reason with the mob. They aren’t interested.
When someone reaches the conclusion that a socially unacceptable thought is correct, the vast majority will try to stop thinking about any at all.
Eg. suggesting oppressed group struggling with validating their own existence and massive suicide rates coming from that struggle to entertain a though that validy is not there may not be what an educated mind would do.
It is not through silence and imposition that healthy social order changes. Demands are made while little public discourse has even taken place and the more friction that creates the more those demanding feel vindicated, the more rejection fosters.
It seems like rather than changing hearts, the trans movement decided it was in the right and set itself to impart justice, whether the public understands it or not. Not quite fascistic, definitely totalitarian, that makes it way closer to actual fascism than anything that is often pointed as such though. Shame.
I didnt support censorship either. You created a strawman that i couldnt respond due to the sheer volume of downvotes.
I support people expressing their thoughts freely so that I know who is dangerous, and who is not. Who has a disdain for my mere existence, and who is willing to stand in support of minorities.
The reality is that bigots will only get emboldened, as they have, and it’s not due to censorship, it’s due to strawmans and falsehoods pushed by prominent bigots.
I merely pointed to bigots killing people, and to prominent politicians who embolden the bigots, and rally them under a false flag, under a supposedly “holy” cause, under the so-called protection of conservative values.
Shame on you, for jumping to conclusions and creating strawmans.
Forcing people to guess should be avoided, especially since not everyone is where you’re from. Links to examples are also helpful.
The Utah law "prohibits health care providers from providing hormonal transgender treatments to minors and those not diagnosed with gender dysphoria".[1]
That's not the same thing at all.
[1]: https://healthnews.com/news/utah-limits-access-to-gender-aff...
Apparently stating facts is worthy of downvotes. Keep it classy HN.
I don't think this is the case, since there were no facts presented. Your guess seems to differ from the other person [1], which proves that some clarity would have helped the discussion.
I believe this argument holds water on some level, when it regards a small private company, but it is much less compelling when that "private company" is Amazon (who owns Twitch), Google, Twitter, Facebook or another behemoth with hundreds of millions of users. At that point, it becomes a very chilling attack on free speech, which is why I think that many big tech platforms should be designated at common carriers.
When the companies are generating revenue through selling advertisements, and the advertisers decide "yeah we actually don't want to buy a pre-roll on the stream where the guy is making racist comments", it's another level of difficulty to navigate. Should these companies be required to host someone's content at a loss, given that they have some way for advertisers to "block" certain content types from being associated with their brands?
It is simple enough to add flags to streams that enough people report as "offensive" and let advertisers choose which streams their advertisements appear on. Advertisers (and others) who insist that everyone that find offensive is completely banned off the platform should be given the bird and told to take a walk. I think one of the problems is that advertising has (like big tech) become an oligopoly, dominated by "the big four" ad agencies. It is one thing for a company that represents .001% of the ad market to pull their ads from a website or a platform because they find something offensive, and a massive conglomerate to pull 25% of all ads from a platform (let alone act in concert with the other 3 ad agencies who control the entire ad market). The reality is that far too many of our "markets" are controlled by far too many corporations, many of which act in concert and otherwise coordinate in ways that are legally questionable, at best. Unfortunately due to our largely corrupt government that is heavily influenced by corporate interests and regulatory agencies that are mostly staffed by a revolving door of industry cronies things are very unlikely to change.
What if the private company is Visa or Mastercard? What if it is your only ISP?
“Your life admittedly sucks but I think you blow it out of proportion so I can’t feel empathy for you”
It's hard for me to empathize with a group that increasingly looks less like a marginalized group, and more like some fanatical religion that somehow has gained an almost ridiculous amount of influence over every major institution and social media platform. And I say this as someone who was originally 100% on board.
A trans person could insult my identity, race and sexuality without any consequences whatsoever, but the reverse has the potential of permanently ending my social life and livelihood. Of course as the magnitude of this disparity keeps increasing, my empathy, and sympathy would decrease along with it.
If anything, I'm actually starting to become afraid of trans people, not because of their transition, but due to their incredible authority.
No doubt there is discrimination, and there was in the past as well, and I don't want to minimize this, but the idea that the general public (i.e. most people) fundamentally objects to the very idea of trans people existing (and wants to "genocide" them, as is sometimes also claimed) does not seem to bear out.
Or maybe look at the law Arkansas tried to pass, where any public performance whatsoever by a transgender person would be considered an "adult performance", because they would be wearing clothes which are not traditionally associated with their assigned gender at birth.
That kind of thought is becoming increasingly common among right-wing American politicians, and I do not know of any other way to describe it than trying to deny the existence of trans people. I really wish this was all just an exaggeration, but unfortunately it really is this bad.
That's the point of the comment, if you were applying AI in more serious scenarios, would this be an AI confidently advising a doctor to overdose a patient, or advising a judge to incarcerate someone based on racist inferences from the set of people currently incarcerated?
I'm confused, I thought it was supposed to be generating Seinfeld episodes, not jokes?
A clip of the joke from the banned channel:
https://clips.twitch.tv/CalmFrailPlumageShazBotstix-ITcqL0Hh...
At least that's what would make sense, and Twitch moderation is far, FAR from making sense in general, but in this one thing they might be reasonable.
The former has a probability distribution of sequences reflective of the dataset and context whereas the latter is pure random chance assuming input seed is random.
$ seq -w 9999999And Twitch's rules only seem as arcane as YouTube and Facebook too. Maybe not Twitter.
The "but nobody is laughing" part would run counter to this. The premise of the whole joke is that the referenced jokes aren't funny.
By that reductively absurd measure, Earl Butz is an artist. [0]
[0] https://en.wikipedia.org/wiki/Earl_Butz#Scandals_and_resigna...
I mean killing is wrong, but so is being a dick.
I don't really understand the point you're making. Killing is orders of magnitude more wrong thank "being a dick" (meaning: making an offsensive or bad joke). I'm sure you agree, so I don't see what's the goal of this comparison.
And I think that using Charlie Hebdo in this context is a bad taste. Saying "see, it got people killed, so they were doing something wrong" is basically acknowledging that terrorism works. People that died in Charlie Hebdo did nothing to deserve this.
I'd be very curious how widespread your opinion is these days now that support of artistic censorship has become much more mainstream.
Surprised this has to be said.
Whether you are unaware of it or not doesn’t make them not true.
As the commenter said, google is your friend.
https://www.axios.com/2023/01/31/trump-transgender-rights-lg...
I have met trans women, especially those who came out of the gay community like me, who use the t-word with vicious intent because of hate they have for themselves and others. They're disgusted with being trans and they're disgusted by other trans people and they throw the slur the same way a non-trans person would and in doing so give moral cover to non-trans people who hate us. "See they even hate each other and they use that word the same as we do!" If you call these self-haters out they'll claim it's fine for them to behave the way they do because they're trans too, but, no.... The reason you shouldn't use slurs has nothing to do with the slur itself, it's about the impact of it and the impact doesn't change just because you're trans yourself.
So anyway, imo, normalizing the use of slurs by publicly broadcasting them is a bad idea in general outside of very specific contexts because slurs are not just words, they are symbols for an entire series of related negative stereotypes so when we normalize those words we also normalize the ideas associated with them. AI doesn't get an n-word pass. /rant
Thanks for articulating this; it's helpful. My only question is: words that are labels don't create hatred, although they might signify it. Will stopping words being used do anything to reduce any hate people feel and/or increase understanding, and conversely will allowing it add any hate to people and/or decrease understanding?
It's not theoretical for me. My FIL doesn't know I'm trans and he loves Fox News and called some person getting covered by Fox a t-word in a really hateful way about two years ago and it's made me feel less comfortable around him. He could have just said "I don't know about this trans stuff" which I get totally but by jumping to a slur he put a barrier up. I've begged my husband to "out" me to his family at some point ... imagine how that would go now. Even assuming he can overcome the fact that his DIL who he's known for the better part of a decade is actually some sort of demon creature from a Tucker Carlson segment, don't you think he's going to think back on all the nasty stuff he said and feel awkward as heck??? Even if he moved on from it, I could never forget or trust him like I would have if he'd only revealed a more measured mistrust of trans people instead of jumping straight to calling us the most hateful thing he could think of.
It would be the same with a stranger. If you call me a slur or use the slur around me without knowing that I AM ONE OF THOSE "SLUR WORDS" it would prevent me from being able to form a relationship with you on equal footing and would make me want to hide who I am from you which just amplifies the level of misunderstanding in the world.
When lots of people are throwing slurs and stuff around in general that feeling of alienation becomes a suffocating amorphous cloud that covers you up and makes you want to retreat from society. I guess that's a feature and not a bug for the people using the slurs. They want us to stay in the gay bars and away from them and their kind but.... that's not healthy. We should all be able to participate in public life on as near to equal footing as possible.
Some people might say it's my fault because I take slurs personally but... I'm just human here. I don't wanna spend my life placating people who use slurs to describe me. I'll bet it's the same for members of other groups who have slurs that people use against them. Once somebody uses those slurs against you it's hard to build a bridge with them which is sad.
Even a black AI ?
See how the situation is turning ridiculous ? Of course an AI should be able to say any word as long as the context makes it clear that it’s not actually insulting anyone. Racism, phobia of all sorts, insults, offensive discourses, hate is all part of human nature, and human history.
You can’t live without the bad sides of humanity, and you most certainly won’t erase them by simply banning words. It just doesn’t work like this. You’ll just turn the world into an horrible authoritarian regime, where it’s all rosy on the surface, just for the sake on not being sent to jail, and where the bad thoughts, being repressed and taboo, will only grow stronger.
- Wears a maga hat
- Supports forced pregnancies
- Is evangelical christian
- Is proudly unvaccinated
- Considers him or her self a "pureblood"
- Is proudly uneducated and complains about "overeducated" women.
- Complains about drag shows - which nobody forced them to go to - while not batting an eye for beauty pageants for children.
- Complains about HBO Max's The Last of Us showcasing a gay couple (but they obviously loooooove watching heterosexual "couples" on shows)
Anecdotes aren’t required for this.
That’s simply a single edge jump from “Utah GOP” to GOP.
In your overly condescending and infantilising response, you missed context from parent comment:
> there are actual Nazis out there who want to put people in ovens, so it's taboo to make jokes about how they may have a point.
> similar thing with trans people, you mention them and trolls come out of the woodwork saying they should kill themselves.
Now, you may be okay with a small segment of the population dying at the hands of definitely-not-fascists who have attempted to murder certain officials at their homes, but I do not subscribe to your morally deprived and bankrupt view of the world.
Anyway, what's the difference between Putin's regime, Iran, and GOP besides the religion? It's quite eerie to see how many parallels one may draw from GOP, Iran and Russia.
[1] https://www.huffpost.com/entry/texas-transgender-database-dr...
I'll just uh.. reiterate my comment from above in hopes that there's some level of introspection possible here:
> The problem I'm seeing is that with some regularity, people are being designated as "intolerant" for simply asking questions, deviating slightly from the most up-to-date acceptable opinion, or just not keeping up with what is the correct opinion to have now. Applying nuance and assuming that others _might_ have good intentions isn't really in vogue
If you wish to ask questions, there are places where you can very much do so, like r/honesttransgender. You can read papers on the topic, you can read experiences, and you can pose questions in a manner that isn't antagonizing people.
If you wish to blame somebody for the "intolerance" towards the "just asking questions" rhetoric, there are plenty of "news" anchors that cause mass hysteria and purposefully misrepresent information to push their ideology.
Matt Walsh "just asked questions", while supporting, and condoning violence against trans people. Shapiro "Just asked questions", and so does Carson or whatever that guy's name is.
So now trans people have to justify their own existence as people and live in fear because of said people who "just ask questions".
You see, if you wish to learn, there is a time and place for it, antagonising people who genuinely fear for their life by using the same rhetoric the above people used to fuel a rabid and bloodthirsty base you are showing that you don't actually care about people, or at least that's the impression that you are giving.
I was merely attempting to convey that use of the word "fascist" in a context such as this can and will be taken by many as extreme hyperbole bordering on abject nonsense, because I suspect that many people who still casually use this term don't realize that it has lost any weight or gravitas that it once had through sheer overuse, and as a result, use of the term elicits immediate dismissal for many.
also, to everyone else: isn't it curious how some issues such as this one cause people to go off about myriad completely unrelated political topics, wholly unprompted?
> Anyway, what's the difference between Putin's regime, Iran, and GOP besides the religion? It's quite eerie to see how many parallels one may draw from GOP, Iran and Russia.
what could any of this possibly have to do with language-model Seinfeld making a transgender joke?
* Makes sure the people controlling the machine are incentivized to correct it (not that I think they needed it, but what I think is irrelevant)
* Ensures that content that Twitch management doesn't want on their platform, and which is in violation of their TOS, is removed immediately, regardless of the thoughts/actions of the people controlling the machine.
As far as Twitch is concerned, there's a channel that's breaking TOS, repeatedly. They're not "punishing" the owner of that channel, they're just enforcing the TOS, something the channel owner agreed to when creating their channel.
> It's not useful, to anyone
What's not useful to everyone is acting like you don't read the news, can't read the news, or in the event that someone points out something in the news that you didn't, that you somehow cannot be availed of that knowledge in a way that doesn't render the argument moot. It's really stupid when you think about it that way.
Plus, aren't we supposed to be making the effort of understanding each other here. Sitting in ignorance to insist you can't think of a single example isn't really making that effort.
> It's almost like it's used to preemptively set up a fight, with responses similar to yours, like "Well, you're not paying attention" or "How could you not know?".
A stage was set where people can easily be placed into a box, created by an intentional lack of clarity. They can then be easily attack for not seeing things "as clearly" as they should. It's not possible for anything positive to come out of an exchange built in that context. By that, it's not useful, unless your goal is actually to create a negative exchange.
It seems that any criticism of the republican leadership results in a horde of bigots mass flagging and downvotes which then prevents me from responding to attacks and responses.
Dealing with the bullshit and falsehoods always takes a lot more time than it takes to discredit facts, and HN’s approach with flagging does not help.
As a matter of fact, I had a comment where i paraphrased Popper almost word for word regarding the paradox of tolerance, and then quoted Trump saying he wants to outlaw trans people, and i got flagged.
It took for @dang to come and unflag me.
Edit:
Because if our adversaries are the products of inanimate and unthinking evolution, we cannot regard the problem in terms of revenge or payback... that would be no different than whipping the ocean for having sunk a ship and drowned its sailors
- Stanislaw Lem, The InvincibleHowever, the AI may not have been trained in a neutral way, and the person using it may not be using it in a neutral way.
If you create an AI product, you are responsible for its output. People aren't mad at the model itself, they are mad at its creators. Why did they create an AI which ends up insulting people and breaking the ToS of the platform it is on?
Here are three models: * A language model that outputs jokes, * A self-driving car model that outputs driving instructions, * An autonomous combat drone model that outputs engagement targets.
Where do you draw the line? Where do you start to "get offended"?
Just saw your Lem quote: Isn't an AI exactly not "unthinking"? That's the whole purpose of machine learning: to "learn", to recognise patterns, to abstract away, no?
We KNOW exactly what to do and how to help trans people be happy and successful and not want to kill themselves: Preferred gender supporting care, treating them like the human beings they are, hormones for those who are confident enough to not regret it.
Here's what half the country currently votes for instead: Banning trans people from bathrooms, banning books that acknowledge the existence and acceptableness of trans people, calling trans people pedophiles and groomers on large public news channels, generally just making """jokes""" that amount to "if you are trans then you are stupid and broken and don't deserve to live"
The Trevor Project collects research on these lines: https://www.thetrevorproject.org/resources/article/facts-abo...
Says:
LGBTQ youth are not inherently prone to suicide risk because of their sexual orientation or gender identity but rather placed at higher risk because of how they are mistreated and stigmatized in society.
You want someone to academically prove this concept to you? It is basic, as in fundamental, to human psychological safety and thus physical survival. Not everything true exists in a report.
Transitioning is an effective and proven treatment, which has a far higher rate of success than basically any other psychiatry-related treatment. The medical part is pretty much solved, and those physical differences can be reconciled quite well.
But as it turns out, the hate from society still remains, and it still has an effect. Turns out being happy is a bit tricky when it is literally a coin flip whether the person you are talking to believes you should be murdered merely for existing.
https://journals.plos.org/plosone/article?id=10.1371/journal...
"Conclusions
Persons with transsexualism, after sex reassignment, have considerably higher risks for mortality, suicidal behaviour, and psychiatric morbidity than the general population. Our findings suggest that sex reassignment, although alleviating gender dysphoria, may not suffice as treatment for transsexualism, and should inspire improved psychiatric and somatic care after sex reassignment for this patient group."
If you read the Discussion, you'd see that this study actually contrasts other similar studies, which saw no such outcome. It even explicitly states that the overall mortality rate was only significantly increased for the group operated before 1989, and mentions that
> However, the latter might also be explained by improved health care for transsexual persons during 1990s, along with altered societal attitudes towards persons with different gender expressions.
This study is often used in an attempt to discredit transgender healthcare. In fact, it is used so often that there is even an interview[0] with the author about its misrepresentation. The interview links half a dozen other studies done since then which confirm that transgender healthcare does indeed work, and is in fact quite effective.
[0]: https://www.transadvocate.com/fact-check-study-shows-transit...
> Thank you for your question and I am happy I was invited to AMA.
> I am aware of some of the misinterpretation of the study in Plos One. Some are as you say difficult to keep track since they are not published in scientific journals. I am grateful to friends all over the world who notify me of publications outside the scientific world. I do answer some of them but I can’t answer all.
> I have no good recommendation what to do. I have said many times that the study is not design to evaluate the outcome of medical transition. It DOES NOT say that medical transition causes people to commit suicide. However it does say that people who have transition are more vulnerable and that we need to improve care. I am happy about that it has also been seen that way and in those cases help to secure more resources to transgender health care.
> On a personal level I can get both angry and sad of the misinterpretations and also sometimes astonished that some researcher don’t seem to understand some basics about research methology.
"Trans people have a higher rate of suicide than the general populace even after reassignment" isn't disproving either the 'innate' or the 'societally-driven' risk model here.
There is clearly a significant social aspect here but I'm not willing to toss out that the body may just really not enjoy not being naturally in the expected configuration. Going to the gender you want seems to be partially solved but, like the person with the lost limb, it's doubtful we have anything close to a full substitute. I really worry the medical community has been doing a dis-service to the development of treatment by underplaying the suicidal aspects that may be less socially related.
With transgender people, the "original" state is unnatural. Medical treatment fixes this mismatch by making the body match the brain. It is a voluntary treatment with an extremely high success rate and negligible regret rates.
As far as I can tell, there is zero evidence that any remaining issues are caused by the treatment itself. All evidence points that the remaining issues are primarily socially related.
if you have references, I'd welcome them.
If by "quite new and unsupported" you mean "pioneered in the 1920s, well-established for many decades, backed by dozends of studies, and successfully applied to hundreds of thousands of patients worldwide", then yes - it is indeed quite new and unsupported.
If you want to read just one study, why not start with the last one? The Amsterdam Cohort consists of 6,793 people since 1972. That should be plenty to start with.
If you want even more, I recommend reading the "Standards of Care for the Health of Transgender and Gender Diverse People". Currently in its eighth edition, it describes the entire process, with hundreds of additional studies cited.
The treatments you are familiar with have been around since the thirties. Research on them started with the Institut fur Sexualwillenschaft, which has been since burned down, and hundreds of papers have been published on the topic since, dealing with thousands of patients all over the world, with their findings all being remarkably consistent.
How hard have you actually looked into it?
What's the difference when so many US states are now prohibiting treatement for this?
Impossible to reconcile when they’re blocked from effective treatment. In a decent society trans people would be given treatment when asked for.
They haven't. This is an invented statistic that just gets repeated and repeated until people accept it as if it's truth.
The flaw was in how the survey was conducted. I won't try to repeat it here- it's a long explanation to do justice.
If your brain does not get exposed to the ‘right’ set of hormones at the right time while you’re in the womb, your brain can develop a different gender identity than the rest of your body. This can be the explanation for some trans people, but I don’t know how many.
Research has pretty firmly come down on the "nah, it's society." side of things.
I agree with you that research has pretty firmly come down on the side of "nah, it's society" for the former. I think the latter is a fair point. To pin it all on society I find to be disingenuous. Transitioning can be a healthy thing in that case. Disclaimer: am not trans, so I openly admit I may be totally ignorant and off base.
https://nicic.gov/being-transgender-no-longer-mental-disorde...
Whoops, looks like I cut off part of the beginning of your sentence. That didn't change our interpretation of it now did it?
I'll also claim to know the next part of the pattern, but I don't think you can complete the pattern, somewhere like this, and it definitely involves misplaced assumptions.
> we are supposed to try to make an effort to understand each other.
My first comment was asking for clarification, so discussion could be had. You made no efforts, and resisted, until now.
> I will repeat my point that when discussing a particular element of the news
As my first comment stated, the problem is that no particular element was discussed. I suggest re-reading this thread.
The rest of your post is a textbook example of gaslighting, so I'm choosing to remove myself from this thread now. But, I sincerely wish the best for you.
No change in my tone nor my point.
>My first comment was asking for clarification, so discussion could be had. You made no efforts, and resisted, until now.
I literally offered an example that fit.
>As my first comment stated, the problem is that no particular element was discussed. I suggest re-reading this thread.
Yawn.
>The rest of your post is a textbook example of gaslighting, so I'm choosing to remove myself from this thread now. But, I sincerely wish the best for you.
Be gaslight, then. It's all projection from you anyway.
LGBTQ youth are not inherently prone to suicide risk because of their sexual orientation or gender identity but rather placed at higher risk because of how they are mistreated and stigmatized in society.
I think you may be able to do some comparative analysis based on different rates of depression & suicidal ideation among homosexual youths both over time and across different states/local environments to get a sense of the magnitude of the social effect, but it’s basically impossible to fully disentangle social effects when evaluating the mental health of trans youth when you’ve got senators and governors proposing bills decrying them as ‘less-than’.
But, let’s try an experiment: let’s keep working on society until that’s _not_ the case, and if there’s still a substantially higher incidence of trans suicide in a world in which they’re supported and have care options available to them, I’ll owe you a coke.
You can't posit that for every issue that pops up, it's not scalable at all. We have limited time on this Earth and limited resources, this is not a computer program where you can apply hypotheses in isolation and get quick results.
https://scholar.google.com/scholar?q=psychological+safety+an...
What did diabetics do before treatment and therapies? People with asthma, myopia, or really any other health issue? What does it matter?
> Do we know that the treatments help in the sense that treated people commit suicide less than untreated people before the treatments were available?
Why do we need to know that? What's the point of it? We don't evaluate effectiveness of any treatment by comparing current data with likely non-existent, pre-treatment (read: more than a century old, in this case) data.