This is such a cynical take. Contrary to popular belief, the vast majority of moderators do care about their subreddits or else they wouldn't be volunteering their free time. The allure of the power to remove some random person's post on the Internet, or to ban them just so they return with another account, pales in comparison to the thrill of watching your community grow and people having fun because of it. And it's not this weird selfish, hey-look-at-me-I'm-so-successful kind of thrill, it's like you joined this thing because you are interested it and now all these other people who are also interested in it are there talking about it. That's what's cool, you set off to make this place where people can talk about this thing that you think is cool and you get to watch it grow and be successful over time. Some of these communities have been around for over a decade, so, people have invested time and effort into them for over a decade.

Moving to elsewhere isn't really as easy as people make it out to be. At the moment "moving communities" means fracturing your community as there is no unified approach to doing this.

The operative word being "unified" which is next to impossible to achieve. If you get all mods to agree you will have a hard time reaching all your users. This in itself presents the biggest roadblock, ideally you'd close up shop and redirect users to the new platform. Reddit will most certainly not allow this, their approach to protesting subreddits that were not even aiming to migrate made that abundantly clear.

So this means that, at the very least, you are looking at splitting your community over platforms. This is far from a unified approach.

This isn't even touching on the lack of viable long term platforms out there. I'd love for people to move to Lemmy. But realistically speaking Lemmy is very immature, instance owners are confronted with new bugs every day, not to mention the costs of hosting an instance. That also ignores the piss poor state the moderation tooling is in on Lemmy. The same is true for many of the possible other "alternatives".
All the new attention these platforms have gotten also means they are getting much more attention from developers. So things might change in the future for the better, in fact I am counting on it. But that isn't the current state of the fediverse. Currently most of the fediverse, specifically Lemmy is still very much in a late Alpha maybe early Beta state as far as software stability and feature completeness goes.

And, yes, the situation on reddit is degrading and this latest round of things has accelerated something that has been going on for a while. But at the same time Reddit is the platform that has been around for a decade and where the currenty community is. Picking that up and moving elsewhere is difficult and sometimes next to impossible. I mean we haven't even talked about discoverability of communities for regular users.

Lemmy (or any fediverse platform) isn't exactly straightforward to figure out and start participating in. If you can even find the community you are looking for. Reddit also hosts a lot of support communities, who benefit from reddit generally speaking having a low barrier of entry. Many of those wouldn't be able to be as accessible for the groups they are targeting on other platforms.

This is such a cynical take. Contrary to popular belief, the vast majority of moderators do care about their subreddits or else they wouldn't be volunteering their free time. The allure of the power to remove some random person's post on the Internet, or to ban them just so they return with another account, pales in comparison to the thrill of watching your community grow and people having fun because of it. And it's not this weird selfish, hey-look-at-me-I'm-so-successful kind of thrill, it's like you joined this thing because you are interested it and now all these other people who are also interested in it are there talking about it. That's what's cool, you set off to make this place where people can talk about this thing that you think is cool and you get to watch it grow and be successful over time. Some of these communities have been around for over a decade, so, people have invested time and effort into them for over a decade.

Moving to elsewhere isn't really as easy as people make it out to be. At the moment "moving communities" means fracturing your community as there is no unified approach to doing this.

The operative word being "unified" which is next to impossible to achieve. If you get all mods to agree you will have a hard time reaching all your users. This in itself presents the biggest roadblock, ideally you'd close up shop and redirect users to the new platform. Reddit will most certainly not allow this, their approach to protesting subreddits that were not even aiming to migrate made that abundantly clear.

So this means that, at the very least, you are looking at splitting your community over platforms. This is far from a unified approach.

This isn't even touching on the lack of viable long term platforms out there. I'd love for people to move to Lemmy. But realistically speaking Lemmy is very immature, instance owners are confronted with new bugs every day, not to mention the costs of hosting an instance. That also ignores the piss poor state the moderation tooling is in on Lemmy. The same is true for many of the possible other "alternatives".
All the new attention these platforms have gotten also means they are getting much more attention from developers. So things might change in the future for the better, in fact I am counting on it. But that isn't the current state of the fediverse. Currently most of the fediverse, specifically Lemmy is still very much in a late Alpha maybe early Beta state as far as software stability and feature completeness goes.

And, yes, the situation on reddit is degrading and this latest round of things has accelerated something that has been going on for a while. But at the same time Reddit is the platform that has been around for a decade and where the currenty community is. Picking that up and moving elsewhere is difficult and sometimes next to impossible. I mean we haven't even talked about discoverability of communities for regular users.

Lemmy (or any fediverse platform) isn't exactly straightforward to figure out and start participating in. If you can even find the community you are looking for. Reddit also hosts a lot of support communities, who benefit from reddit generally speaking having a low barrier of entry. Many of those wouldn't be able to be as accessible for the groups they are targeting on other platforms.

This feels like clickbait to me, as the fundamental problem clearly isn't AI. At least to me it isn't. The title would have worked as well without AI in the title. The fact that the images are AI generated isn't even that relevant. What is worrying is that the peer review process, at least for this journal clearly is faulty as no actual review of the material took place.

If we do want to talk about AI. I am impressed how well the model managed to actually create text made up of actual letters resembling words. From what I have seen so far that is often just as difficult for these models as hands are.

Long term wearing of vr headsets might indeed be not all that good. Though, the article is light on actual information and is mostly speculation. Which for the Apple Vision Pro can only be the case as it hasn't been out long enough to conduct anything more than a short term experiment. So that leaves very little data in the way of long term data points.

As far as the experiment they did, there was some information provided (although not much). From what was provided this bit did stand out to me.

The team wore Vision Pros and Quests around college campuses for a couple of weeks, trying to do all the things they would have done without them (with a minder nearby in case they tripped or walked into a wall).

I wonder why the Meta Oculus Quests were not included in the title. If it is the meta Quest 3, it is fairly capable as far as pass through goes. But, not nearly as good as I understand the Apple Vision Pro's passthrough is. I am not saying the Apple Vision Pro is perfect, in fact it isn't perfect if the reviews I have seen are any indicator. It is still very good, but there is still distortion around edges of vision, etc.

But given the price difference between the two I am wondering if the majority of the particpants actually used Quests as then I'd say that the next bit is basically a given:

They experienced "simulator sickness" — nausea, headaches, dizziness. That was weird, given how experienced they all were with headsets of all kinds.

VR Nausea is a known thing even experienced people will get. Truly walking around with these devices with the distorted views you get is bound to trigger that. Certainly with the distortion in pass through I have seen of Quests 3 videos. I'd assume there are no Quests 2 in play as the passthrough there is just grainy black and white video. :D

Even Apple with all their fancy promo videos mostly shows people using the Vision pro sitting down or in doors walking short distances.

So yeah, certainly with the current state of technology I am not surprised there are all sorts of weird side effects and distorted views of reality.

What I'd be more interested in, but what is not really possible to test yet, is what the effects will be when these devices become even better. To the point where there is barely a perceivable difference in having them on or off. That would be, I feel, the point where some speculated downsides from the article might actually come into play.

In the article they actually state they believe it is actually better to have the keys included and not rely on some method of inserting them.

After this situation blew up, we received many requests, and even some demands, to remove all Wii keys from our codebase. We're disappointed that so many people on YouTube and social media didn't even consider that maybe the team had done their research and risk analysis before including the keys, and just assumed that now that it was "pointed out to us" we would remove them. However, we do not think that including the Wii Common Key actually matters - the law could easily be interpreted to say that circumventing a Wii disc's encryption by any means is a violation. As such, it is our interpetation that removing the Wii keys would not change whether the exemption in 17 U.S.C. § 1201(f) applies to us or not.

In fact, we think that offloading decryption tasks onto a potential 3rd party application would make the situation worse for everyone. As such, we believe leaving the keys as they are is the best course of action.

At least for the instance this was posted on: the February 2024 Beehaw Financial Update

You are glossing over a lot of infrastructure and development, when boiled down to the basics you are right. So it is basically a question of getting enough users to have that app installed. Which is not impossible given that we do have initiatives like OpenStreetMap.

I am not against emojis overall. But to put it in perspective, the way emojis work they do draw a lot of extra attention to themselves. Specifically because they don't follow text color so are really distinct. So to me, personally, a text with a lot of emojis sprinkled in can come across as busy to the point of distracting to read or a bit shouty.

In my (again personal) view emojis, smilies, etc are most useful when used in moderation on key points in a message. It's also with that reason that on platforms like Lemmy, reddit or basically any old forum I do think they generally don't have a place in titles.

I hope that this makes sense? 🙂

Edit: To maybe clarify it a bit further

Emojis can also basically be a type of "fluff content":

"The Fluff Principle: on a user-voted news site, the links that are easiest to judge will take over unless you take specific measures to prevent it."

Source: Article by Paul Graham

What this means is basically the following, say you have two submissions:

1. An article - takes a few minutes to judge.
2. An image - takes a few seconds to judge.

So in the time that it takes person A to read and judge he article person B, C, D, E and F already saw the image and made their judgement. So basically images will rise to the top not because they are more popular, but simply because it takes less time to vote on them, so they gather votes faster.

To get back to the title thing I mentioned. More often than not I see people use emojis in titles not to strengthen the title, but simply to draw attention to it. And the same thing I have seen in in messages in general. Like I said above, it then starts to approach "shouting" from my perspective. So it isn't emojis themselves I then have an issue with, it is just that they then fall in the same category as ALL CAPS and bolded text that shouldn't be bolded and all that.

The only thing I could ever get anyone to say was that they hated emojis because they made people seem immature.

Depending on context, that can be a legitimate objection against using them. On the other hand, when used sparingly I don't mind them, I even see them being used internally at my work in a corporate environment. I am still not a fan of emojis on platforms like Lemmy depending on how they are used though. I just wrote a different comment about this and then saw yours, in order to not repeat myself: https://beehaw.org/comment/608537

Hopefully this is a bit more of an explanation that does make sense. 😉

If everything you have read is saying that it is fine, then why does it not feel right for you? Looking around I do get the same impression, it is non-combustible so there is not really a concern there. Basically from what I gather as long as you use the proper wire for use in walls/isolation, leave enough space and generally take good practices in account like using conduit where needed you should be good to go.

I am not an electrician though and certainly not aware of your local code and regulations.

Talking about electricians, if you are worried about doing it not right, why not hire one to do it for you?

They’re for different needs.

Yes... but also extremely no. Superficially you are right, but a lot of the arguments of why many new distros are created is just because of human nature. This covers everything from infighting over inane issues to more pragmatic reasons. A lot of them, probably even a majority, don't provide enough actual differentiators to be able to honestly claim that it is because of different needs. In the end it all boils down to the fact that people can just create a new distro when they feel like it.

Which is a strength in one way, but not with regard to fragmentation.

I don't know how to say this in a less direct way. If this is your take then you probably should look to get slightly more informed about what LLMs can do. Specifically, what they can do if you combine them with with some code to fill the gaps.

Things LLMs can do quite well:

• Generate useful search queries.
• Dig through provided text to determine what it contains.
• Summarize text.

These are all the building blocks for searching on the internet. If you are talking about local documents and such retrieval augmented generation (RAG) can be pretty damn useful.

True, though that isn't all that different from people doing knee jerk responses on the internet...

I am not claiming they are perfect, but for the steps I described a human aware of the limitations is perfectly able to validate the outcome. While still having saved a bunch of time and effort on doing an initial search pass.

All I am saying is that it is fine to be critical of LLM and AI claims in general as there is a lot of hype going on. But some people seem to lean towards the "they just suck, period" extreme end of the spectrum. Which is no longer being critical but just being a reverse fanboy/girl/person.

Bing and Google Bard keep disappointing me. Bing for some reason only picks up on half of what I ask. Which is extremely odd as it is supposedly is ChatGPT based and ChatGPT gives pretty good answers on the same queries. The only problem with the latter is that a lot of it is of course outdated.

Bard might just be broken for me. I keep getting I'm a text-based AI, and that is outside of my capabilities. or similar responses.

I totally see why you are worried about all the aspects AI introduces, especially regarding bias and the authenticity of generated content. My main gripe, though, is with the oversight (or lack thereof) in the peer review process. If a journal can't even spot AI-generated images, it raises red flags about the entire paper's credibility, regardless of the content's origin. It's not about AI per se. It is about ensuring the integrity of scholarly work. Because realistically speaking, how much of the paper itself is actually good or valid? Even more interesting, and this would bring AI back in the picture. Is the entire paper even written by a human or is the entire thing fake? Or maybe that is also not interesting at all as there are already tons of papers published with other fake data in it. People that actually don't give a shit about the academic process and just care about their names published somewhere likely already have employed other methods as well. I wouldn't be surprised if there is a paper out there with equally bogus images created by an actual human for pennies on Fiverr.

The crux of the matter is the robustness of the review process, which should safeguard against any form of dubious content, AI-generated or otherwise. Which is what I also said in my initial reply, I am most certainly not waving hands and saying that review is enough. I am saying that it is much more likely the review process has already failed miserably and most likely has been for a while.

Which, again to me, seems like the bigger issue.

I am not quite sure why there are all these bullet points that have very little todo with the actually issue.

Researchers at the University of Wisconsin–Madison found that Chrome browser extensions can still steal passwords, despite compliance with Chrome’s latest security standard, Manifest V3.

I am not sure how Manifest V3 is relevant here? Nothing in Manifest V3 suggests that content_scripts can't access the DOM.

The core issue lies in the extensions’ full access to the Document Object Model (DOM) of web pages, allowing them to interact with text input fields like passwords.

I'd also say this isn't directly the issue. Yes, content_scripts needing an extra permissions to be able to access password input fields would help of course.

Analysis of existing extensions showed that 12.5% had the permissions to exploit this vulnerability, identifying 190 extensions that directly access password fields.

Yes... because accessing the DOM and interacting with it is what browser extensions do. If anything, that 12.5% feels low, so I am going to guess it is the combination of accessing the DOM and being able to phone home with that information.

A proof of concept extension successfully passed the Chrome Web Store review process, demonstrating the vulnerability.

This, to me, feels like the core of the issue right now. The behavior as described always has been part of browser extensions and Manifest V3 didn't change that or made a claim in that direction as far as I know. So that isn't directly relevant right now. I'd also say that firefox is just as much at risk here. Their review process over the years has changed a lot and isn't always as thorough as people tend to think it is.

Researchers propose two fixes: a JavaScript library for websites to block unwanted access to password fields, and a browser-level alert system for password field interactions.

"A javascript library" is not going to do much against content_scripts of extensions accessing the DOM.

The alert system seems better indeed, but that might as well become browser extension permission.

To be clear, I am not saying that all is fine and there are no risks. I just think that the bullet point summary doesn't really focus on the right things.

So yeah... titles are fully parsed as markdown. Which opens up a lot of abuse vectors for spammers/scammers. Not only that, links in markdown are green which opens the door even further for fake admin posts.

Doesn’t matter too much, but if it does not hurt, then I would continue like this. Or does it somehow spam the notification?

In that case, just continue :) I just did happen to notice it but it doesn't lead to extra notifications or annoyances.

For real, it almost felt like an LLM written article the way it basically said nothing. Also, the way it puts everything in bullet points is just jarring to read.

No I am curious what will happen if I try to use a really big image....

Edit: Good, at least Lemmy doesn't allow it to break the page layout :)

Frankly, you are taking a too binary approach to the subject of your rant. There are tons of Lemmy instances, so figuring out the right one isn't as straightforward as stumbling upon a single central platform.

This just feels like a cop out

No, I am just outlining several factors that come into play that do weigh in for people. I am not just saying it is difficult to find Lemmy instances. I am saying it is difficult to move entire communities over. I am also saying several other things than just "moving difficult". To be honest, I highly suggest you go back and ready my comment again with the intent of seeing the nuance.

Oh huh, you are right. I threw that exact prompt in Dall-e and got indeed legible letters.

What do you mean by "it"? The chatGPT interface? Could be, but then you are also missing the point I am making.

After all, chatGPT is just one of the possible implementations of LLMs and indeed not perfect in how they implemented some things like search. In fact, I do think that they shot themselves in the foot by implementing search through bing and implementing it poorly. It basically is nothing more than a proof of concept tech demo.

That doesn't mean that LLM's are useless for tasks like searching, it just means that you need to properly implement the functionality to make it possible. It certainly is possible to implement search functionality around LLMs that is both capable and can be reviewed by a human user to make sure it is not fucking up.

Let me demonstrate. I am doing some steps that you would normally automate with conventional code:

I started about by asking chatGPT a simple question.

*"I want to provide a list of all the children bach had. What would be a suitable google query"

It then responded with.

"To compile a comprehensive list of Johann Sebastian Bach's children, a suitable Google query would be: "List of Johann Sebastian Bach's children names". This query is specific enough to indicate that you're looking for a detailed list, including the names of all the children, which should yield targeted results."

The following step I did manually, but is something you would normally have automated. I put the suggested query in google, I quickly grabbed the first 5 links and then put the following in chatGPT.

The top 5 results in google are the pages I provided below. Browse to each page, and answer the query "List of Johann Sebastian Bach's children names". Just answer the query, but let me know if there is conflicting information on the page.

https://en.wikipedia.org/wiki/Bach_family
https://www.classicfm.com/composers/bach/guides/children/
https://www.bachonbach.com/100-bach-faq-and-soon-there-are-500-bach-faq/faq-26-what-were-the-names-of-all-of-johann-sebastian-bach-s-kids/
https://www.spiritsound.com/music/bachchildren.html
https://www.grahamsmusic.net/post/bach-s-wives-and-children

It then proceeded to give me the following answer

Johann Sebastian Bach had 20 children in total. With his first wife, Maria Barbara Bach, he had seven children, four of whom survived into adulthood: Catharina Dorothea, Wilhelm Friedemann, Carl Philipp Emanuel, and Johann Gottfried Bernhard. With his second wife, Anna Magdalena Wilcke, he had 13 children, of whom six survived into adulthood: Gottfried Heinrich, Elisabeth Juliane Friederica, Johanna Carolina, Regina Susanna, Johann Christoph Friedrich, and Johann Christian

Going over the search results myself seems to confirm this list. Most importantly, except for the initial input, all of this can be automated. And of course, a lot of it can be done better, as I didn't want to spend too much time.

As is often the case there is more nuance to this. As others have pointed out, it is still possible to run your own mailserver if you really want to.

But, there are also other options that aren't google, microsoft or any other service.

I personally have registered my own domain and have my mail hosted by mailbox.org. If I am ever dissatisfied with them I can simply pick a different mail hosting provider and move my domain there. Other privacy minded providers can be found here: https://www.privacytools.io/privacy-email

And there are also more options if you just want reliable mail and care slightly less about overall privacy. Fastmail for example is a popular choice.

Yes, these are not free. But neither is hosting it yourself as that costs you the VPS/container to host it and a bunch more time and effort.

What it does provide you with is the ability to no longer use big tech while allowing you to mail with people still having their mail hosted there.

Github issue made: https://github.com/LemmyNet/lemmy-ui/issues/1976

Fyi, you don't need to ping someone when replying to them ;)

Anyway, yeah I get that it is controversial or already was. But you said it in isolation while the blog post explicitly goes into that choice which I think is important for context.

Isn't that just markdown images?

Looks like it is, also looks like you can basically inline link any image you want. Which.... isn't ideal actually for a variety of reasons.

I feel like two different problems are conflated into one though.

1. The academic review process is broken.
2. AI generated bullshit is going to cause all sorts of issues.

Point two can contribute to point 1 but for that a bunch of stuff needs to happen. Correct my if I am wrong but as far as my understanding of peer-review processes are supposed to go it is something along the lines of:

1. A researcher submits their manuscript to a journal.
2. An editor of that journal validates the paper fits within the scope and aims of the journal. It might get rejected here or it gets send out for review.
3. When it does get send out for review to several experts in the field, the actual peer reviewers. These are supposed to be knowledgeable about the specific topic the paper is about. These then read the paper closely and evaluate things like methodology, results, (lack of) data, and conclusions.
4. Feedback goes to the editor, who then makes a call about the paper. It either gets accepted, revisions are required or it gets rejected.

If at point 3 people don't do the things I highlighted in bold then to me it seems like it is a bit silly to make this about AI. If at point 4 the editor ignores most feedback for the peer reviewers, then it again has very little to do with AI and everything the a base process being broken.

To summarize, yes AI is going to fuck up a lot of information, it already has. But by just shouting, “AI is at it again with its antics!” at every turn instead of looking further and at other core issues we will only make things worse.

Edit:

To be clear, I am not even saying that peer reviewers or editors should "just do their job already". But fake papers have been increasingly an issue for well over a decade as far as I am aware. The way the current peer review process works simply doesn't seem to scale to where we are today. And yes, AI is not going to help with that, but it is still building upon something that already was broken before AI was used to abuse it.

It's markdown inline images so yeah you can do any image.

Today I saw that my countries government has started a mastadon instance, which is pretty neat. Previously they've used twitter for some communication but they got some flack for that recently.

For LLM training I do wonder if they assigned a weight, but I doubt it.

Given my experience with models I think they might actually do assign a weight. Otherwise, I would get a lot more bogus results. It also isn't as if it is that difficult to implement some basic, naive, weighing based on the amount of stars/forks/etc.

Of course it might differ per model and how they are trained.

Having said that, I wouldn't trust the output from an LLM to write secure code either. For me it is a very valuable tool on the end of helping me debug issues on the scale of being a slightly more intelligent rubber ducky. But when you ask most models to create anything more than basic functions/methods you damn well make sure it actually does what it needs it to do.

I suppose there is some role there for seniors to train juniors in how to properly use this new set of tooling. In the end it is very similar to having to deal with people who copy paste answers directly from stack overflow expecting it to magically fix their problem as well.

The fact that you not only need your code/tool to work but also understand why and how it works is also something I am constantly trying to teach to juniors at my place. What I often end up asking them is something along the lines of "Do you want to have learned a trick that might be obsolete in a few years? Or do you want to have mastered a set of skills and understanding which allows you to tackle new challenges when they arrive?".

I realize you asked for other recommendations, but I suspect you don't want to actually maintain your own music library but rather want streaming services recommended?

Of the two alternatives you are currently looking for I do have experience with Deezer, although it has been two years at least. The music library is almost as complete as Spotify in my experience I rarely had issues with songs not being on there. The recommendation algorithm at the time was nice, but would sometimes get stuck in a hyper specific genre that would only reinforce itself.

For HIFI audio you basically do need fairly good audio gear for it (decent wired headphones for example), I'd say that for most people it is not worth paying extra for as it is really difficult to tell the difference.

One other service I have used is Youtube Music as it is included in premium. It does not have an HIFI option but otherwise is fairly okay. Basically worth looking into if you were also considering Youtube premium, but otherwise not really special.

If you're on desktop, I actually made a userstyle that makes use of this font. It also changes a few other things that imho make beehaw a bit more readable. https://userstyles.world/style/10715/beehaw-org-read

You need the stylus extension to install it https://github.com/openstyles/stylus/#readme

Most code on GitHub either is unsecure, or it was written without needing to be secure.

That is a bit of a stretch imho. There are myriads of open source projects hosted on github that do need to be secure in the context where they are used. I am curious how you came to that conclusion.

I’m already getting pull requests from juniors trying to sneak in AI generated code without actually reading it.

That is worrysome though. I assume these people have had some background/education in the field before they were hired?

Nextcloud can do this and replace a bunch of other google services in the process.

Looking at what you said so far though I am not entirely sure if you want to go down the route of self hosting yet. Which is okay, it involves a lot of work and knowledge to do right. Something you might not want to risk your contacts for if you are still learing. There are services that provide nextcloud hosting. Personally I am using Hetzner, a Germany based hosting provider: https://www.hetzner.com/storage/storage-share

Edit:

I forgot to mention, you'll also need to do some fiddling with your phone to sync things: https://docs.nextcloud.com/server/latest/user_manual/en/groupware/sync_android.html

Just to double check, are you trying to login with your beehaw account on the kbin website or trying to find the community through beehaw.org?

The reason I am asking is because accounts aren't transferring to other instances. It works the other way around, through your fediverse instance (in this case beehaw) you can access other federated instances and communities.

Normally, you should be able to go here and find other communities of instances that beehaw has been federated with. Or you can access them directly as well.

Having said that, I couldn't find the specific instance through search and the direct url (https://beehaw.org/c/magicthecirclejerking@kbin.social) also doesn't seem to work. This might have something to do with the character length of the community.

It depends on the platform you are using. But, for platforms like github and gitlab there are extensions for popular IDEs and editors available that allow you to review all changes in the editor itself.

This at the very least allows you to simply do the diffing in your own editor without having to squash or anything like that.

I feel like this is the third time people are selective reading into what I have said.

I specifically acknowledge that AI is already causing all sorts of issues. I am also saying that there is also another issue at play. One that might be exacerbated by the use of AI but at its root isn't caused by AI.

In fact, in this very thread people have pointed out that *in this case" the journal in question is simply the issue. https://beehaw.org/comment/2416937

In fact. The only people likely noticed is, ironically, the fact that AI was being used.

And again I fully agree, AI is causing massive issues already and disturbing a lot of things in destructive ways. But, that doesn't mean all bullshit out there is caused by AI. Even if AI is tangible involved.

If that still, in your view, somehow makes me sound like an defensive AI evangelist then I don't know what to tell you...

Yes, of course :) This is the desktop web front-end, so the "default" .

Oh sorry :( It had been a while since I checked out the page and forgot the poster is part of the entire thing.