This weekly roundup thread is intended for all culture war posts. 'Culture war' is vaguely defined, but it basically means controversial issues that fall along set tribal lines. Arguments over culture war issues generate a lot of heat and little light, and few deeply entrenched people ever change their minds. This thread is for voicing opinions and analyzing the state of the discussion while trying to optimize for light over heat.
Optimistically, we think that engaging with people you disagree with is worth your time, and so is being nice! Pessimistically, there are many dynamics that can lead discussions on Culture War topics to become unproductive. There's a human tendency to divide along tribal lines, praising your ingroup and vilifying your outgroup - and if you think you find it easy to criticize your ingroup, then it may be that your outgroup is not who you think it is. Extremists with opposing positions can feed off each other, highlighting each other's worst points to justify their own angry rhetoric, which becomes in turn a new example of bad behavior for the other side to highlight.
We would like to avoid these negative dynamics. Accordingly, we ask that you do not use this thread for waging the Culture War. Examples of waging the Culture War:
-
Shaming.
-
Attempting to 'build consensus' or enforce ideological conformity.
-
Making sweeping generalizations to vilify a group you dislike.
-
Recruiting for a cause.
-
Posting links that could be summarized as 'Boo outgroup!' Basically, if your content is 'Can you believe what Those People did this week?' then you should either refrain from posting, or do some very patient work to contextualize and/or steel-man the relevant viewpoint.
In general, you should argue to understand, not to win. This thread is not territory to be claimed by one group or another; indeed, the aim is to have many different viewpoints represented here. Thus, we also ask that you follow some guidelines:
-
Speak plainly. Avoid sarcasm and mockery. When disagreeing with someone, state your objections explicitly.
-
Be as precise and charitable as you can. Don't paraphrase unflatteringly.
-
Don't imply that someone said something they did not say, even if you think it follows from what they said.
-
Write like everyone is reading and you want them to be included in the discussion.
On an ad hoc basis, the mods will try to compile a list of the best posts/comments from the previous week, posted in Quality Contribution threads and archived at /r/TheThread. You may nominate a comment for this list by clicking on 'report' at the bottom of the post and typing 'Actually a quality contribution' as the report reason.
Jump in the discussion.
No email address required.
Notes -
With the increased usage of ChatGPT and other aislop in everyday communication such as casual emails and slack messages, AI apologists have increasingly tried to excuse this usage by non-native English speakers(citation needed, but besides the point). The excuse being that for non-native speakers, AI usage can save time, or even increase the quality of the resulting writing. I want to argue this is actually the opposite, and that using AI output particularly and exceptionally corrosive when used by non-English speakers.
I came across this section(plaintext transcription in below comment) of a YT video, where an intermediate level English learner is trying to use ChatGPT improve a piece of writing, and also learn from it. (source video, not important). Here’s the catch ChatGPT’s output is just plain bad
Overall, my issues with ChatGPT for this use case can be broken down into three main problems:
Let’s go over the main revisions point by point
stunning -> absolutely mind-blowing - Stunning is already quite a strong adjective and ChatGPT is overdoing it. OK edit.
I commented -> I typed in the comments - Absolutely a bad edit. More wordy for no more meaning, and the original English is more true to the original Japanese.
Moreover -> Not only that - Moreover is perfect here. Bad edit.
Em dash - not called for here. AI tell.
reacted really disgusting me -> actually reacted - This seriously changes the meaning, taking away a major element of the storytelling. Bad edit.
I’m in a heaven right now -> I’m in heaven - I’m in heaven right now is emphasis. Bad edit.
It was a peaceful and amazing moment in my life -> That one moment was pure peace and bliss. Probably one of the best highlights of my life. - Deemphasized and wordified into two sentences. A better version would easily be “It was the most peaceful and amazing moment in my life”. Bad edit.
And also, the most excited thing is -> And the most exciting part is still ahead. - AI slop tell. Bad edit.
I could die there -> nothing - ChatGPT just took that out completely!!!! WFT!!!!
I really wanna support her live too. -> I really, truly want to support her with everything I’ve got. - “really, truly” came out of nowhere and the double emphasis with “with everything I’ve got” is odd. Bad edit.
Imagine that live I feel like drinking her bath water. -> Just thinking about that live … feels like I could drink her bathwater. - This one is totally lost. Basic context clues and cultural knowledge make it clear that the narrator already wants to drink gamer girl bathwater irregardless of any live. The correct edit would be “When I imagine that live, I feel like I’m drinking her bathwater” or “Imagining that live feels like drinking her bathwater.” The original English is closer to correct than ChatGPT and the correct meaning can be inferred.
Of course ChatGPT can probably be made to produce better outputs with better prompting, or used differently, but this is just one of many examples where ChatGPT usage by a casual user has actually made things worse.
Now what's the point of this post? First I would like to urge everyone not to use GenAI outputs in the final work, even for edits. Using AI as a judge is probably fine, but the best way to maintain quality is probably write all of the final text in your own words. Even for people without perfect English. Secondly, with all levels of society using or even abusing AI tools, it may increase productivity by some metrics, it will also be like an enshittification of all written communication.
We've seen an increasing number of complaints enter the discourse about foreign immigrants with weak English skills just being annoying to deal with in everyday life. And I've also had similar experiences, where dealing with a fresh off the boat foreigner has been an annoyance when ordering food or asking a simple question - and also where hiring an American would have only costed a tiny bit more. Well now AI slop is going to provide a double whammy - lazy or misguided native speakers are going to enshittify their own communication with slop, and also foreigners will have their English learning impeded, and the English they do write will be worse.
Original English:
Original Japanese:
今日の配信は完璧でした！俺は”踏んでくだステップオンミー！”とコメントすると、推しのはあちゃまが「キモい！」と反応してくれて
ChatGPT output:
Claude knocks it out of the park as far as I'm concerned.
Even 4o:
Yes, surprisingly ChatGPT is better at translating wholesale than trying to revise a work or something. Asking it to translate directly actually gives a quite accurate result.
Unfortunately, as this situation shows, the user asked ChatGPT for revisions on the English work rather than translating the work from native language. I think this is a more typical use case because most people beyond beginners writing in English do not write in native language and then translate to English, but instead write directly in English. We are just fortunate enough to have the Japanese version as well, so we can see clearly where ChatGPT failed to capture the intention.
So we are in a world where "write English -> ask ChatGPT for revisions" is far far inferior to "write in native language (Japanese) -> use AI to translate to English" where translating directly gives a superior result. In this case the workflow that gives the best result involves the absolute least practice of English by the writer.
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link