Image description
phanisvara (streams)
The vast majority of Mastodon users as well as users of projects that have been based on ActivityPub from the start or for long enough actually think that the Fediverse is only ActivityPub. They don't even know that there's stuff in the Fediverse that has ActivityPub as an optional secondary protocol. Few know that Hubzilla and (streams) exist, even fewer know that neither of these two is based on ActivityPub.
In fact, many Mastodon users, including some who have joined during the second Twitter migration wave in November, 2022, are fully convinced that the Fediverse is only Mastodon, full stop. And that "Fediverse" and "Mastodon" mean the same.
And I think not exactly few want the Fediverse to only be vanilla Mastodon with its hard-coded 500-character limit. They aren't only against federation with Threads and a bridge to Bluesky, but they don't want all that stuff from Pixelfed to Lemmy to Misskey to Friendica to (streams) around either.
Some vulnerable groups have escaped the harassment on Twitter. Of course, they went to Mastodon and only Mastodon because that's all they knew. But now they're stuck on Mastodon. First, they didn't know that better stuff than Mastodon exists in the Fediverse. If they heard about the existence of that stuff, they didn't know and couldn't imagine that it's better or even that anything in the Fediverse could possibly have features that Mastodon doesn't.
But even now they refuse to move again. For one, there's no easy-peasy way to move an entire Mastodon account with all posts, all connections, even all settings to e.g. (streams). But they won't accept anything less. Besides, even if they did try (streams), they'd nope out quickly due to how (streams) doesn't handle anything like Mastodon. They simply don't want to get used to yet another UI/UX, and the step from Mastodon to (streams) is much bigger than from Twitter to Mastodon.
If you really want to introduce (streams)' safety features to them, you must first soft-fork (streams) into something that's indistinguishable from Mastodon on the surface, that is 100% compatible with the Mastodon API, and that Mastodon servers can be seemlessly migrated to. Then you have to migrate all major Mastodon instances, including and especially mastodon.social, to this soft fork. And then you have to adjust everyone's default settings to "perfect harassment protection, but handles exactly the same as Mastodon" because chances are these people won't even touch their settings.
If Mastodon users want perfect privacy and security, they want it on the very Mastodon instance they're on right now. And they want all these perfect privacy and security features to be on by default, but without meddling with their own use of Mastodon.
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta
I guess it's often a case of the creators themselves using these bodies because they prefer them over the super-popular ones for some reason. They basically make clothes for themselves, and while they already have these clothes, they may just as well sell them.
I know at least one such case in OpenSim. She has been making original mesh clothes for Ruth 2.0 for years now. Mind you, in OpenSim, the vast majority of avatars has been wearing stolen Maitreya Laras since 2015. Many users don't even know there's any legal content in OpenSim, much less legal and original mesh bodies. And those who look through the mesh body sections of some freebie stores and find Ruth 2.0 or Ruth2 there can't imagine that anyone actually uses them, what with no big freebie store even offering clothes for these bodies. But she makes them, and she offers them herself.
Why does she do that Out of idealism, so that people have the choice to put on legal mesh clothes made in and for OpenSim Not so much. To support legal mesh bodies by providing clothes for them A bit more, but not so much either. It's mostly because the Maitreya Lara clothes that are being stolen are too sexy/racy/slutty for her. She prefers different styles of clothes, but the content thieves don't cater to her taste and want all female avatars to only ever look as sexy or racy as possible.
#Long #LongPost #CWLong #CWLongPost What about explanations of what's in the image for those who don't know
Is it a universally good advice to assume that everyone who comes across this image knows what a capybara is and what yuzu fruits are or, alternatively, is willing to fire up a Web browser, if necessary, and search the Web for all missing information to understand the image Risk nobody getting the image for brevity's sake
Or would it be better to relocate the image description from the alt-text to the post text, at least if the character limit allows for that, and explain everything that might not be common knowledge but necessary to get the image and/or its description
I'm asking because my own images cover much, much more niche topics.
#Long #LongPost #CWLong #CWLongPost #AltText #ImageDescription #ImageDescriptions #ImageDescriptionMeta #CWImageDescriptionMeta
To be fair, alt-text was invented for static HTML webpages. This means two things in comparison with the Fediverse.
Webpages are usually only visited by people who are specifically interested in them. These people either have some basic knowledge of what the webpage is about, or they're ready, willing and able to browse around to gather the information they need.
Fediverse posts are shoved into the faces of people who'd never look up whatever the post is about. The more niche the topic of a post is, the fewer people know anything about it. Also, especially amongst the mobile users, few want to start a Web browser and start Googling stuff until they understand an image. They want everything described and explained in one place, namely their Fediverse app, especially blind or visually-impaired users.
Also, static HTML webpages don't have a character limit. Most of the Fediverse is limited to 500 characters.
I dare say that what I do on Hubzilla is closer to how things are done on static webpages or in blog posts than what's done on vanilla Mastodon with three times as high a character limit in alt-text as in the post itself.
To sum things up once more, here's how I do single-image posts:
The alt-text for the image:
In alt-text, supposing that I've got enough space, I'd have to give one full, detailed description with all detail descriptions and all explanations for each image. That's also because different Fediverse projects order images differently. Mastodon always reverses the order of my images, so what's the first image for me is the last image for everyone on Mastodon and vice versa.
In 1500 characters, I could only mention. I could only name-drop. But I can neither describe to blind or visually-impaired users what something unfamiliar looks like, nor can I explain to anyone what something unfamiliar is.
I could only say there's an OpenSimWorld beacon standing in a particular spot in the image. But without an explanation what an OpenSimWorld beacon is in the first place, this information is completely and utterly useless, and without a visual description what this particular OpenSimWorld beacon looks like, it's ableist on top of that.
It takes me 1,000 characters to describe the looks of the current standard OpenSimWorld beacon. And it takes me 4,000 characters to explain it, no matter what it looks like.
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #AltText #ImageDescription #ImageDescriptions #ImageDescriptionMeta #CWImageDescriptionMeta
I don't post real-life photos unless they're parts of meme templates.
This is not my one single personal Fediverse account. This channel has virtual worlds, OpenSim specifically, as its primary topic. So I have to see how I can get pictures from virtual worlds to work.
Been there, done that.
My target audience is partly OpenSim users, most of whom are on Mastodon and not necessarily on an instance for that topic, partly other people who might be interested in this stuff.
My actual audience is whoever comes across my posts in whichever timeline, and be it the federated timeline on mastodon.social.
My image descriptions have to be informative enough so that my actual audience gets my images.
Well, apparently, a very very few people did read them.
But if I made my image descriptions shorter, I'd leave blind or visually-impaired people who don't know what virtual worlds and the stuff in virtual worlds look like standing in the rain. And if I shortened them to standard Mastodon alt-text length, nobody would understand my images, and the image descriptions would be useless.
The idea that "alt-text" and "image description" are always mutually synonymous is so Mastodon. I mean, most Mastodon users don't have any space for image descriptions elsewhere than in alt-text.
But I don't put my full, detailed image descriptions into the alt-text.
My alt-texts contain a short, purely visual, not really informative description, and they mention that the actual full image description is in the post itself, either right below or hidden behind the CW above, depending where the reader is. And yes, the full description goes into the post where I've got enough space.
I couldn't put such long image descriptions into alt-text anyway. That is, I could, I don't have any character limits for alt-text either.
But Mastodon, Misskey and their respective forks have hard 1,500-character limits for alt-text, and when a longer alt-text comes in, they chop it off at the 1,500-character mark.
Also, I explain a lot in my image descriptions. That's information that can't be found anywhere else in the post, not in the actual post text, not in the image. Such information must never be exclusively available in the alt-text because there are people who can't access alt-text, e.g. due to a physical disability. Any information only available in alt-text is inaccessible and therefore lost to them.
Lastly, descriptions of images from virtual worlds, obscure virtual worlds even, have to be extremely long. That's because they're so obscure. People don't know anything about them, and so they'll need a lot of information to understand the image.
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #AltText #ImageDescription #ImageDescriptions #ImageDescriptionMeta #CWImageDescriptionMeta(This is actually a comment. Find another post further up in this thread.)
Now let's pry LLaVA's image description apart, shall we
Typical for an AI: It starts vague. That's because it isn't really sure what it's looking at.
This is not a video game. It's a 3-D virtual world.
At least, LLaVA didn't take this for a real-life photograph.
It's an avatar, not a character.
This is the first time that the AI is accurate without being vague. However, there could be more details to this.
And I can and do tell the audience in my own image description why my avatar is facing away from the viewer. Oh, and that it's the avatar of the creator of this picture, namely myself.
Nope. Like the AI could see the eyeballs of my avatar from behind. The avatar is actually looking at the cliff in the background.
Also, it's clearly an advertising board.
If I'm generous, I can let this pass as not exactly wrong. Only that there is no dense canopy, and this is not a park.
Nope again. It's actually late morning. The AI doesn't know because it can't tell that the Sun is in the southeast, and because it has got no idea how tall the trees actually are, what with almost all treetops and half the shadow cast by the avatar being out of frame.
In a setting inspired by thrillers from the 1950s and 1960s. You're adorable, LLaVA. Then again, it was quiet because there was no other avatar present.
There's a whole lot in this image that LLaVA didn't mention at all. First of all, the most blatant shortcomings.
First of all, the colours. Or the lack of them. LLaVA doesn't say with a single world that everything is monochrome. What it's even less aware of is that the motive itself is monochrome, i.e. this whole virtual place is actually monochrome, and the avatar is monochrome, too.
Next, what does my avatar look like Gender Skin Hair Clothes
Then there's that thing on the right. LLaVA doesn't even mention that this thing is there.
It doesn't mention the sign to the left, it doesn't mention the cliff at the end of the path, it doesn't mention the mountains in the background, and it's unaware of both the bit of sky near the top edge and the large building hidden behind the trees.
And it does not transcribe even one single bit of text in this image.
And now for what I think should really be in the description, but what no AI will ever be able to describe from looking at an image like this one.
A good image description should mention where an image was taken. AIs can currently only tell that when they're fed famous landmarks. AI won't be able to tell from looking at this image that it was taken at the central crossroads at Black White Castle, a sim in the OpenSim-based Pangea Grid anytime soon. And I'm not even talking about explaining OpenSim, grids and all that to people who don't know what it is.
Speaking of which, the object to the right. LLaVA completely ignores it. However, it should be able to not only correctly identify it as an OpenSimWorld beacon, but also describe what it looks like and explain to the reader what an OpenSimWorld beacon is, what OpenSimWorld is etc. because it should know that this can not be expected to be common knowledge. My own description does that in round about 5,000 characters.
And LLaVA should transcribe what's written on the touch screen which it should correctly identify as a touch screen. It should also mention the sign on the left and transcribe what's written on it.
In fact, all text anywhere within the borders of the picture should be transcribed 100% verbatim. Since there's no rule against transcribing text that's so small that it's illegible or that's so tiny that it's practically invisible or that's partially obscured or partially out of frame, a good AI should be capable of transcribing such text 100% verbatim in its entirety as well. Unless text is too small for me to read in-world, I can and do that.
And how about not only knowing that the advertising board is an advertising board, but also mentioning and describing what's on it Technically speaking, there's actually a lot of text on that board, and in order to transcribe it, its context needs to be described. That is, I must admit I was sloppy myself and omitted a whole lot of transcriptions in my own description.
Still, AI has a very very long way to go. And it will never fully get there.
#Long #LongPost #CWLong #CWLongPost #AltText #ImageDescription #ImageDescriptions #ImageDescriptionMeta #CWImageDescriptionMeta #AI #LLaVAOkay, I've done it.
I've pitted an image-describing AI against myself and one of my own image descriptions.
As the test object, I've used my latest in-world picture which has first been published , including the exact same full-length image description and explanation from that post. The short description in the alt-text is the same, too, all shortcomings included, but I had to modify the alt-text itself for this specific use-case.
Users of Pleroma and its forks, Friendica, Hubzilla and (streams) can see the image here:
Users of Mastodon, Misskey and their respective forks can see it as a file attachment below this post.
My AI of choice was the . I've fed it the image at the resolution at which I've also posted it, namely at a resolution of 800x533 pixels.
The AI took a few seconds to produce this 558-character image description:
I'll talk about this description in more details in a follow-up.
Now, here comes my description. I didn't write it while looking at the scaled-down image. I didn't write it while looking at the image at its original solution of 2100x1400 pixels either.
I wrote it while I was still in-world. I could walk around and zoom around and see everything from different angles and at much, much higher resolutions. For example, one of the picture on the advertising board to the right shows a building that's nearby but outside the borders of the image. I could describe that picture by walking to that very building.
All in all, I took eight hours to produce this 25,271-character image description:
Now, if you've made it all the way down here, I ask you: Which description is more accurate Which description is more detailed Which description is more informative Which description actually helps you understand the image
#Long #LongPost #CWLong #CWLongPost #BlackAndWhite #Monochrome #OpenSim #OpenSimulator #Metaverse #VirtualWorlds #AltText #ImageDescription #ImageDescriptions #ImageDescriptionMeta #CWImageDescriptionMeta #AI #LLaVA
Since I tend to give both a short description of the visuals of an image in the alt-text and a full, detailed description and explanation in the post itself, I might actually start giving full meme explanations on an even higher level of detail than KnowYourMeme because it's probably good style not to rely on external sources if it can be avoided somehow.
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #AltText #ImageDescription #ImageDescriptions #ImageDescriptionMeta #CWImageDescriptionMeta #Memes Wobei es ja auch da Aufteilungen gibt.
Misskey ist fr Japaner und die, die es gern wren.
Sharkey hat groe Zielgruppenberschneidungen mit Blhaj und Programmiersocken.
Hubzilla ist fr die Schmerzbefreiten, die sonst schon alles gesehen haben, featureschtige bergeeks und die Urgesteine, die schon immer auf Mikes Projekten unterwegs waren.
Und (streams), das eigentlich der ultimative Safe Haven sein knnte, wenn es denn jemand kannte, wird hauptschlich von denjenigen Spielkindern genutzt, denen es nur auf Hubzilla zu langweilig wird. hnlich wie damals die Red Matrix fr ein paar wenige Friendica-Nutzer. Aber solange der Totalumbau unter der Haube noch nicht abgeschlossen ist, ist das auch gut so.
#Long #LongPost #CWLong #CWLongPost #LangerPost #CWLangerPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #Misskey #Sharkey #Hubzilla #Streams #(streams) An sich ginge das theoretisch schon, allerdings mit Einschrnkungen und Besonderheiten.
Zunchst einmal: Die Dokumente, die kollaborativ bearbeitet werden knnten, wren keine Dateien, also nicht z. B. Word- oder ODF-Dokumente. Das wren im Prinzip Blogposts, die auch hnlich wie Blogposts in BBcode formatiert wren, nur da die nicht wie Posts an die eigenen Followers geschickt werden.
Man knnte die auch nicht isoliert ansehen, sondern nur in ihrer angestammten Umgebung mitsamt der ganzen UI drumherum. Als gesonderte Dokumente exportieren, z. B. als PDF, ginge auch nicht.
Dazu kme auch noch, da es so gesehen keinen zentralen Cloud-Speicher fr die Dokumente gbe. Irgendjemand mte so ein Dokument jeweils auf seinem Kanal (hnlich wie ein Mastodon-Konto) parken und dann diejenigen, die dieses Dokument bearbeiten drfen, hndisch freischalten.
Existierende Dokumente (Text, Word, ODF etc. oder auch PDF) knnen zwar in den Cloud-Speicher hochgeladen werden, aber nicht bearbeitet. Eine eingebaute Ansichtsfunktion gibt's meines Wissens auch nicht. Und diesen Cloud-Speicher gibt's eben einmal pro Kanal, aber nicht einmal zentral. Wenn man einen zentralen Speicher fr solche Sachen will, mu das ein eigener Kanal sein.
Alternativ zu einzelnen blogpostartigen Dokumenten knnte man auch Wikis anlegen, die natrlich eigene Vorzge htten, nmlich die Verlinkung von Seiten untereinander, also einfachere Navigation. Die knnen genauso kollaborativ bearbeitet werden, und die untersttzen neben BBcode wahlweise auch Markdown. Man kann sogar pro Kanal, also pro Nase, mehr als ein Wiki haben mit jeweils praktisch beliebig vielen Seiten.
Aber auch da gibt's nichts in der Art einer Druckansicht oder eines Export. Auerdem darf man sich zum einen daran gewhnen, da die Wikis eben nur BBcode und Markdown kennen, aber nicht die MediaWiki-Auszeichnungssprache. Und gerade Wikis sind im Grunde komplett undokumentiert, d. h. man darf sich da selbst reinfuchsen oder Hubzilla-Nutzer zu finden versuchen, die schon mal Wikis gemacht haben.
#Long #LongPost #CWLong #CWLongPost #Hubzilla Der Abschnitt "Update: Friendica posts in Mastodon" ist nicht nur sachlich falsch, sondern auch noch stark unvollstndig.
Ich als langjhriger Hubzilla-Nutzer mit Friendica-Vergangenheit wrde das eher so formulieren:
Posts and comments coming into Mastodon from Friendica, Hubzilla and (streams) are special cases. That's because neither of them have Mastodon's dedicated CW field. Instead, they have reader-side content warnings that can optionally be created automatically. By default, a post is automatically hidden behind a content warning button if it contains "nsfw" and/or "sensitive".
Automatic reader-side content warnings have been part of the culture of both Friendica and Hubzilla since before Mastodon was even made as well as of fairly new (streams). Poster-side content warnings in a dedicated field have never been part of their culture, both because they've got a much better solution for content warnings and because they don't provide dedicated means for poster-side content warnings.
Technically speaking, Hubzilla and (streams) do have Mastodon's CW field. But unlike Mastodon, it isn't labelled "CW". It's labelled "summary". It has been a summary field originally, but since a hard-coded maximum of 500 characters doesn't require summaries, Mastodon repurposed that field for content warnings. Hubzilla and (streams) have no character limits at all, so using that field for summaries is still justified.
Hence, Hubzilla and (streams) users use this field for short summaries for very long posts, if at all, but not for content warnings.
Also, just like Friendica, both Hubzilla and (streams) have a conversation model like Facebook or Tumblr or blogs with only one post and many comments. All replies are comments, and there is a separate, dedicated entry form for comments under each post. This entry form does not, however, have a summary field because what sense does it make to give a summary for a blog comment
Hence, Hubzilla and (streams) users can't put Mastodon-style content warnings on replies at all. Also, neither Hubzilla nor (streams) can re-use content warnings from posts or comments they reply to.
Friendica, the oldest one of the three, doesn't even have a dedicated summary field. The only way to add a summary, i.e. a Mastodon-style CW, is between the Friendica-specific BBcode tag pair
Since Friendica doesn't have a dedicated UI element for Mastodon-style CWs, neither for posts nor for comments, most Friendica users don't give Mastodon-style CWs at all because they simply don't know that this is possible in the first place, much less how.
Also, users of Friendica, Hubzilla and (streams) tend to find the idea of writing a content warning between a pair of obscure BBcode tags (Friendica) or into the summary field (Hubzilla, (streams)) ridiculous. Trying to convince them otherwise would be like trying to convince Mastodon users to double their CWs with keywords or hashtags to trigger the NSFW content-warning generation on non-Mastodon projects.
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #CW #CWs #ContentWarning #ContentWarnings #ContentWarningMeta #Friendica #Hubzilla #Streams #(streams) Add your location to a Google Map It's fair to mention at this point that hashtags aren't only ever used to increase visibility. They're also used to trigger the automated generation of reader-side content warnings.
Yes, they exist. Not only does Mastodon itself have that feature since version 4.0 from last year. But Mistpark had it as early as 2010, almost six years before Mastodon existed. And unlike Mastodon, it did not repurpose the summary field for content warnings.
From Mistpark emerged today's Friendica, Hubzilla and (streams). All three have this feature. All three don't have Mastodon's CW field Hubzilla and (streams) still call it "summary" while Friendica lacks it altogether. At least Hubzilla and (streams) don't provide any means of adding a Mastodon CW to replies at all.
And all three have had it in their cultures since they were launched to have CWs automatically generated individually for each reader by the "NSFW app".
I am on Hubzilla, and I will not adjust my way of using it so that it becomes indistinguishable from posts on vanilla Mastodon by someone who only knows Mastodon.
I will add 12 hashtags to this comment. The first four are to trigger filters that either remove or CW my posts and comments with over 500 characters because long posts disturb many Mastodon users. The next four are to trigger filters that either remove or CW my posts and comments about the Fediverse because many Mastodon users don't want to see that technical mumbo-jumbo.
Yes, four of each. How am I supposed to know who uses which one of these in their filters
The next two are for discoverability purposes. The last two are for triggering filters again.
So that's two discoverability hashtags and ten filter-triggering hashtags.
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #Hashtag #Hashtags #HashtagMeta #CWHashtagMeta
It seems like the loudest voices on Mastodon are amongst those who don't know anything about ActivityPub and the Fediverse even though they think and claim they do.
A lot of what comes from them is based on the assumption that the Fediverse started with Mastodon, Eugen Rochko invented ActivityPub as the base protocol for Mastodon, and therefore, Mastodon is 100% fully ActivityPub-compliant because Mastodon itself is the very definition of ActivityPub and the gold standard of ActivityPub. Some even seem convinced that all this happened in spring of 2022 because they hadn't heard of Mastodon before then.
Well, and everything that doesn't work perfectly with Mastodon and/or doesn't support all features that Mastodon has the Mastodon way, as well as everything that has features that go beyond Mastodon, is not ActivityPub-compliant and therefore broken.
A while ago, someone absolutely unironically and seriously tried to convince me that Mastodon is the only "feature-complete" Fediverse project. I was about to rattle down a list of Hubzilla features and ask him whether Mastodon has them. Unfortunately, I couldn't demonstrate them to him because that was in Mastodon 3 days when Mastodon users couldn't even see text formatting.
It's nigh-impossible to convince the hard fans and purists of the truth.
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #Mastodon #ActivityPub
Threads on these projects are loosely tied together from single posts. Any post, regardless of whether it's a reply or not, only goes out to the followers of the poster plus whomever the post mentions.
If Alice posts something, it's her followers and the users mentioned in the post. who are notified about it.
If Bob replies to Alice's post, it's his followers and the users whom he mentions who are notified about it. Alice's followers are not notified unless Bob mentions them one by one. In fact, not even Alice would be notified if Bob didn't mention her.
As far as I know, before nodeBB appeared, there were only a few Fediverse projects that had a concept of conversations:
What is now Friendica was not designed as an alternative to Twitter. It was designed as an alternative to Facebook. And so it as a thread structure like Facebook or Tumblr or a blog: exactly one post plus many comments.
Again, if Alice posts something, it's her followers and the users mentioned in the post. who are notified about it.
But if Bob replies to Alice's post, it's a comment on Alice's post and not a stand-alone post itself. Next to whomever Bob mentions, it's Alice and Alice's followers who are notified. Bob's followers are not notified unless they're mentioned because it's none of their business what Bob comments on Alice's post. And Alice is notified even without a mention, as are her followers.
If Carol comments on Bob's comment, apart from whomever Carol mentions, it's Alice, Alice's followers and Bob who are notified. Again, Carol does not have to mention Alice or Alice's followers or Bob. And again, Carol's followers are not notified, neither are Bob's followers.
By sending the post, Alice automatically follows the thread which this post starts. Thus, she receives special notifications for each comment. Likewise, by commenting, both Bob and Carol subscribe to the thread, follow it and receive special notifications for each new comment, regardless of what within the thread is commented on.
Also, Alice, Bob and Carol have the thread in their respective streams anyway. So even if they unsubscribe from the thread, they still get the same notifications for comments as they get for comments on posts from whomever they follow.
By the way, it's only what Friendica, Hubzilla and (streams) perceive as posts that is drawn into a stream and listed as unread. So even if you follow Bob or Carol, but not Alice, Bob's and Carol's comments don't show up in your stream.
Lastly, it's Alice who owns the whole thread. Including all comments. At least on Hubzilla and (streams), Alice can moderate her own thread and delete posts from it unfortunately, that deletion is not forwarded to originally ActivityPub-based projects such as Mastodon which don't understand such measures. And self-moderation on (streams) can go even further than on Hubzilla.
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #Friendica #Hubzilla #Streams #(streams)
I usually write something like "digital rendering from within a 3-D virtual world, generated using shaders, but without ray-tracing" in the full description which goes into the post.
, however, I only added the part before the first comma to the alt-text and forgot the details after the first comma. I hope I'll remember to do better next time, especially seeing as I still had lots of room in the alt-text.
Most of the time, I transcribe all text anywhere in the image absolutely verbatim down to every last spelling mistake. ought to be a good example. I even include text that's
listso small that it's illegible in the image itself
so tiny that it's essentially invisible in the image itself (character height of half a pixel or less)
partly or mostly obscured by something
any combination of the above/url In most cases, the only exception is when I can't decipher text because it's too small or too blurry.
But I just remembered that I got sloppy last time (see Type of image for a link). I didn't mention that the room numbers and the "Office" label are written on the doors of the motel on the advertising poster, let alone in which typeface and colour, and I neither described the license plate hanging above the office door, nor did I transcribe anything on it. I guess I wanted to get this over with. For the same reason, I omitted to describe what can be seen through the open blinds inside some of the motel rooms.
Since my pictures always come from places that probably nobody who reads this knows exist, namely very obscure virtual worlds, I have to mention who the avatars in an image are, if any, explain who they are and describe in detail what they look like and what they wear.
Also because of this, it's always only myself and maybe also my in-world sister Juno Rowland who is in the pictures. It'd be too much of an effort to document the identities and looks of two dozen avatars in a party picture and research and explain who they are and what they do. Besides, chances are that some of them teleport out between me taking the main picture and me getting to identify them and take detail pictures for the description.
This really takes up a whole lot of characters when I write an image description. It definitely only ever goes into the detailed description in the post, never into the alt-text, also because there's no room for it in alt-text anymore. The last time (again, see Type of image for a link), it took me almost 2,300 characters to explain where the image was made, 800 characters or over 50% more than what fits into alt-text on Mastodon, Misskey and their mutual forks.
But I have to write that much because, again, nobody knows the place where the image is from. So I have to write at which location the image was taken, on which sim, in which grid, in OpenSim, what OpenSim is, what Second Life is, what a grid is, why it's called a grid, what a region is, what a sim is, what a varsim is if necessary, what this specific grid is, what this specific sim is and maybe even what this specific place is. Last time I stopped just short of explaining who Edgar Wallace was because that would have been important for non-German and/or too young readers to understand the name of the location.
I try to remember to mention the colour of everything I describe, usually down to the hue. Okay, it was easy last time because it was a picture of a monochrome avatar in a fully monochrome location, save for some very slightly blu-ish or teal-ish hues on the OpenSimWorld beacon which are barely visible in the image, if at all.
Pass. That's because I quit showing human or otherwise variable faces in my images. And that, in turn, is because there's absolutely no way to hide them from Mastodon users, and some autistic Mastodon users must have such images concealed from them due to the danger of being triggered by eye contact.
But even if I showed faces: Avatar faces are mostly expressionless because it takes special animations triggered either by hand or by script for them to show an expression for a few seconds. So there wouldn't be anything specific to describe.
I usually go from the foreground to the background, unless the actual background dominates everything (see my second link) in which case I'll start with that. From top to bottom doesn't always make sense the last time, I would have started with mostly feature-less and completely unimportant off-sim mountains and the sky and then continued with the trees from left to right, jumping back and forth between trees farther in the back and trees farther up front.
Otherwise, if at all possible, I describe everything I can that's at least partly in the image and not fully concealed by something in full detail. I mean, my images consist entirely of stuff that next to nobody has ever come across. And people, including blind or visually-impaired people, might be curious. Besides, regardless whether someone is sighted or not, they might still need extensive explanations to understand certain elements in the image.
Still, it often happens to me that I realise after posting a described image that I've skimped on certain details too much. I think the only time I was halfway satisfied was with almost precisely 40,000 characters for one individual image plus over 1,300 characters for the preamble for both images. It would have been much longer, however, if I had transcribed repeating bits of text and described repeating fabric textures whenever they occurred.
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #AltText #ImageDescription #ImageDescriptions #ImageDescriptionMeta #CWImageDescriptionMeta I'd really like to give you a full, step-by-step, walk-through tutorial. Teleport there, pick this up, pick that up, unpack it, put these items on, click there on that HUD etc., and you've got a good-looking avatar with a bunch of clothes to pick from.
But I'd have to be 100% certain that the tutorial will be absolutely guaranteed to work.
I can't guarantee that. I barely have any experience with male mesh bodies from SL, even less with male BoM mesh bodies from SL. I simply don't use them.
The body I use was made in OpenSim for OpenSim. It works a whole lot differently from all the SL bodies in OpenSim. And it's way too difficult for a complete novice to use, also because there's next to no clothing specifically made for that body.
What I can do is tell you where to get what. But I can't teach you how to use it. I can't walk you through setting everything up. Because I don't know any of that stuff.
Teleport to Nutella (hg.osgrid.org:80:Nutella).
Take a landmark.
Go to the Head & Body Shop (ca. 298, 240).
Pick up the following boxes:
Pick up some hair you like.
Next, go to SilverFox Designs Mall (kishaki.de:8002:SilverFox Designs Mall).
Take a landmark.
Enter the mall building through the black door.
Go to the right.
Here you will find clothes stores.
Now you've got a body, a few heads to try out + shapes + eyes + beards, some skins, some hair and some clothes and shoes.
But from then on, you're on your own. I can't tell you how this body and these heads etc. exactly work.
DISCLAIMER: This is untested!
#Long #LongPost #CWLong #CWLongPost
Nope. Everyone's expected to already know everything from SL.
It's here where SL is different from OpenSim.
See, when mesh bodies were first introduced in the 2010s, alpha masks had no effect on them. That was long before BoM. In fact, you needed a whole-avatar alpha mask to hide the system body. In order to still make it possible to hide parts of the body, it was cut up into 200+ little pieces, and it was given a HUD with which you can make each one of these pieces invisible and visible again.
Alpha cuts and the alpha HUD were meant to be a hack, but both SL and OpenSim users saw them as an advancement over alpha masks. Newer and more technologically advanced = better, and everything else = old = obsolete = bad.
When BoM came, it was suddenly possible to hide parts of the mesh body with alpha masks. In theory. In practice, this pretty much only became the case in SL. Body makers sewed their mesh bodies back together, did away with the alpha HUDs and advertised their bodies as more lightweight in mesh (because there no longer were 200+ submeshes) and scripting (because hide/show scripts were only necessary for female feet anymore). And clothesmakers included alpha masks with their clothes if they could be worn with BoM bodies.
This never happened in OpenSim. OpenSim still has that "alpha masks = old obsolete crap" attitude.
That's partly because those who offer mesh bodies can't possibly convince the users that this "old obsolete crap" is the new hot shit again, also because 99% of all OpenSim users think BoM is only a glorified skin and make-up applier.
And it's partly for another reason: From 2020 to 2022, there seemed to be exactly two BoM bodies in OpenSim: Athena 6 (stolen Maitreya Lara with basic BoM support glued on by the importers) and Adonis 4 (Slink Physique Male with basic BoM support glued on by the same importers). Both of them do not (properly) support alpha masks because their alpha modes are botched.
Hardly anyone noticed because both still have their alpha cuts and alpha HUDs, so hardly anyone even tried to put an alpha mask on them. Those who did failed, and the verdict was "BoM doesn't support alpha masks in OpenSim" even though Ruth2 v4 and Roth2 v2 do support and actually rely on alpha masks.
So when more mesh bodies came in more recently without being renamed (eBody Reborn, Legacy, Legacy Perky, a newer version of Signature Gianni etc.), I think it was the variants with alpha cuts and alpha HUDs that were imported. That's what people were used to.
Older mesh clothes from SL usually don't have any alpha masks because a) they were imported in times when there was no BoM, and b) they were imported to be worn with mesh bodies.
The moment that Maitreya Lara was imported and eventually renamed Athena, nobody added alpha masks to female mesh clothing anymore. The moment that Slink Physique Male was imported and renamed Adonis, nobody added alpha masks to male mesh clothing anymore. Also because whoever already wore mesh clothing was expected to switch to one of the stolen mesh bodies anyway.
The association of clothes with bodies is another issue.
Back in the 2010s, Athena was even more of a standard in OpenSim than Maitreya Lara was in Second Life. Athena was the only mesh body that mattered. So it was deemed completely unnecessary to mention that mesh clothes are "rigged for Athena" when they were. After all, nobody imported any clothes for Belleza Freya or Belleza Venus, both of which were imported to OpenSim, too.
Almost the only exception were Decadence clothes (with the black bar on the left of the box) after stolen copies of Slink Physique Hourglass spread (BBHG, Decadence-HG, Je'Thai Hourglass) from then on, at least HG clothes were labelled as such.
So if there was no body compatibility mentioned on female clothing, it felt only natural to do away with it on male clothing as well.
The problem was that there wasn't that one standard male body. Adonis (actually Slink Physique Male) was there first. But not much later came Apollo and Decadence Male (both actually Signature Gianni), and another bit later came Ares (actually Belleza Jake).
Some importers could be bothered to write onto clothes what they were compatible with, but usually only if they offered clothes for multiple bodies. Even that wasn't consistent. Some importers didn't rename what they had imported at all, so you find the SL body names on old clothes rather than the OpenSim body names.
Then there were those who considered Adonis the male standard in OpenSim because it appeared to be the most widespread. I think most of the clothes with the Sacrarium logo on them are imported Slink Physique Male clothes. They usually don't mention what body they're for, also because Adonis was the only body which the "copybotting mafiya" kept maintaining.
Decadence, having its "own" body Decadence Male, probably only supported that body and Apollo along with it by only importing clothes made for Signature Gianni. But supporting only one body also meant that there was "no need" to write body names on the clothes or the boxes.
It's only now that the number of SL bodies available in OpenSim is increasing that the importers start putting body names on their clothes again, both female and male. That is, if something for male avatars has been imported only recently, and there's no body name on it, you can be certain it's for Signature Gianni (= Apollo = Decadence Male).
#Long #LongPost #CWLong #CWLongPost
Not a fork. Second Life is still closed-source server-side.
It was a case of Second Life open-sourcing its official viewer in 2006. Thus, the API lay open. Third-party viewers were developed against that API. And then someone had the idea to develop a Second Life-like server application against the API from the other side.
, by the way.
One quite particular feature of both Second Life and OpenSim is that you can store any and all kinds of in-world content in objects. This can be used for various things, for example, you can put scripts into doors to animate them, or you can build teleporters by putting a teleport script into an object, or you can build sound emitters that way.
But this can also be used to sell content to avatars, be it for money, be it for free. You put that content into a box, decorate the box and set the box up so that clicking it either gives you the box including contents or an inventory folder with the contents inside. Or you configure the box so that avatars can copy the box into their inventories.
This way, avatars can pick up more than one item at once. It's one thing to pick 16 Christmas wreaths from a wall one by one, but it's another to get a box with all 16 inside it.
Selea Core made a whole lot of sim decoration boxes many years ago. Coincidentally, most of them are actually cubes.
#Long #LongPost #CWLong #CWLongPost #OpenSim #OpenSimulator #Metaverse #VirtualWorldsphanisvara (streams)
Zumal Content Warnings hier ganz anders funktionieren. Und zwar werden sie a) optional und b) auf der Seite des Lesers generiert und nicht auf der Seite des Posters geschrieben und allen aufgedrckt.
Ein Feature, das (streams) auf Umwegen von Hubzilla geerbt hat und Hubzilla auf etwas krzeren Umwegen von Mistpark. Das ist also wahrscheinlich schon von 2010.
Mastodon hat das jetzt auch, aber erst seit 2023. Auerdem drften die allermeisten Mastodon-Nutzer gar nicht wissen, da es das kann, und den meisten derer, die es wissen, ist es zu kompliziert.
Ich bin auch wieder knapp vor der 500-Connections-Marke. Aber ich bin auf ActivityPub und Mastodon angewiesen, weil die Zielgruppen sowohl des Primrthemas als auch des Sekundrthemas dieses Kanals fast ausschlielich auf Mastodon sind.
Blderweise breiten sich meine Posts und Kommentare dadurch auch auf den fderierten Timelines vieler Mastodon-Instanzen aus. Und da sitzen dann die Empfindlichen, die nichts sehen wollen, was sie strt. Dazu zhlt auch alles, was Vanilla-Mastodon 3.x nicht auch konnte. Praktisch keiner von denen kann Filter bedienen.
Da habe ich dann meine liebe Not damit, von jedem meiner Posts die Vorschau in einen Texteditor zu copypasten, um die Zeichen zu zhlen, und wenn's ber 500 Zeichen geht, eine Content Warning fr einen langen Post dranzubauen inklusive Anzahl der Zeichen. Plus alle mglichen anderen Content Warnings. Inklusive Fediverse-Meta, wenn ich irgendwas irgendwie bers Fediverse schreibe, weil es Leute gibt. Ich habe inzwischen eine Liste mit ca. 90 Dingen, die Leute geCWt sehen wollen, und da ist Aufdrselung in landesspezifische Politik noch gar nicht eingerechnet.
Und wenn ich wie jetzt einen Kommentar schreibe (Nutzer von Mastodon, Pleroma nebst Forks, Misskey nebst Forks etc., die das lesen: Hier auf Hubzilla ist eine Antwort kein Post, sondern ein Kommentar mit eigenem Eingabefeld und etwas vllig anderes als ein Post), rechne ich auch immer mit Rffeln oder gar Sperren, weil ich keine CW angebe. Weil ich das gar nicht kann. Und Mastodon-Nutzern in einem einzigen Kommentar mit maximal 500 Zeichen beizupulen, warum das so ist, ist aussichtslos. Geschweige denn, ihnen zu erklren, warum ich dann auch noch ein Dutzend Hashtags unter den "Post" hnge.
Bilder mit Augenkontakt versuche ich gar komplett zu vermeiden. Wenn das nicht geht und der Augenkontakt zu offensichtlich ist, also die Augen nicht jeweils nur einen winzigen Bruchteil eines Pixel klein, dann packe ich das Bild detaillierter Bildbeschreibung in einen Artikel, und zwar inklusive kurzer Bildbeschreibung im Alt-Text und detaillierter Bildbeschreibung im Artikel, und verlinke den Artikel im Post.
Von Hubzilla aus habe ich im Gegensatz zu (streams) absolut keine Chance, Bilder in Posts auf Mastodon ausblenden zu lassen. Gar keine. Auf Friendica, Hubzilla oder (streams) kann ich die Leute bis zu viermal klicken lassen, bevor sie das Bild sehen. Erst auf die Content Warning, wenn sie NSFW an haben. Dann auf das Summary. Dann auf den Spoiler-Tag. Dann auf das verschwommene Bild selbst. Aber exakt dasselbe Bild in exakt demselben Post wird auf Mastodon jedem sofort ohne Warnung ins Gesicht geschmissen. Nur weil Mastodon keinen Bock hat, sich an irgendwelche Standards zu halten oder auch nur das Einbetten von Bildern in Posts zu untersttzen, weil Twitter das ja auch nicht kann.
CC:
#Long #LongPost #CWLong #CWLongPost #LangerPost #CWLangerPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #Mastodon #Friendica #Hubzilla #Streams #(streams) #CW #CWs #ContentWarning #ContentWarnings #CWMeta #ContentWarningMetaSo I've been collecting Selea Core boxes for a few years now. I've got the same goal as a number of people before me, namely for someone to have all Selea Core boxes in one store one day.
I thought my collection was extensive already. But then I found out that Star Ravenhurst has a collection she built from at least one source that I hadn't visited yet. She has fixed and reworked what needed to be fixed and reworked, and now she offers these boxes at in the Genesis Roleplay Grid.
Finding this out was what finally drove me to create a spreadsheet with the boxes I have, including additions, plus the boxes she and Lavia Lavine have.
Turned out she has 63 boxes that I don't have. But I have ca. 57 boxes from various sources that I can send her because she either hasn't got them yet, or they may contain stuff that she hasn't got yet.
All in all, I've catalogued 284 boxes currently, but some of those in my possession seem like they were recompiled or renamed. And I know there have to be even more boxes somewhere out there.
#Long #LongPost #CWLong #CWLongPost #OpenSim #OpenSimulator #Metaverse #VirtualWorlds #SeleaCore #GenesisRoleplayGrid Essentially, Mike Macgirvin (creator of the now-defunct DFRN protocol, , the Zot protocol and , inventor of and creator and maintainer of both the Nomad protocol and ) is redesigning (streams)' conversation model into something that's more compatible with ActivityPub and easier to understand for projects built against the ActivityPub protocol.
It's called Conversation Containers.
If you can take a lot of technobabble: .
It's worth mentioning at this point that (streams) is not based on ActivityPub itself. It's based on an advanced version of the Zot protocol named Nomad, and it only supports ActivityPub as an optional secondary protocol.
CC:
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #ActivityPub #Streams #(streams)On the one hand, FediGroups is kind of lacking from a Hubzilla/(streams) POV. Forums on Hubzilla and (streams) can be made fully private, i.e. nobody from outside the forum can even read them. Not possible on FediGroups because not possible on Mastodon, not to mention that it'd be somewhat inconvenient without server-side OpenWebAuth support.
Also, it's not only possible for Hubzilla and (streams) users to post to Hubzilla and (streams) forums without also posting to their own connections, it's standard. Hubzilla and (streams) forums only forward posts to their connections that come in as direct messages. This does not apply to comments, only to posts.
The same thing is impossible with FediGroups because it rejects direct messages outright.
On the other hand, both features make Hubzilla and (streams) forums harder to use for Mastodon users as they want to use everything in the Fediverse as if it's all Mastodon. Even if a forum is configured to be read by any logged-in user, Hubzilla and (streams) don't recognise logged-in Mastodon users because Mastodon still doesn't have client-side OpenWebAuth support either.
And the very reason why Hubzilla and (streams) forums are being perceived as incompatible with Mastodon is because it's too inconvenient for Mastodon users to start threads on them. I'm not even sure if this has been tested because there's no documentation on this.
Either Mastodon users have to send a DM to the forum which is completely unnatural to Mastodon users who are used to
That said, there are even more shortcomings from a Hubzilla/(streams) POV.
It's impossible to make threads with titles because Mastodon doesn't support titles on Note objects. By the way, this might hit the Friendica crowd hard: FediGroups won't work with posts from Friendica with titles because these go out as Article objects (like blog posts) instead of Note objects (like Mastodon toots), and I'm not sure how FediGroups will handle Article objects.
Generally, it seems a crazy idea to build groups on top of something that not only doesn't have a concept of groups, but that doesn't have a concept of conversations either. But then again, at least two thirds of the Fediverse don't have a concept of conversations. Users of these two thirds can only follow threads if everyone in that thread keeps mentioning them in every last post. At least on Hubzilla and (streams), this is completely unnecessary.
Moderation will be unnecessarily difficult because Mastodon also doesn't have a concept of permissions beyond Mute and Block, and because all replies to posts are posts themselves and exclusively owned by whoever posts them and thus can't be moderated by the thread starter.
Also, FediGroups are so far the only "groups" in the Fediverse that don't present themselves as Group actors. Thus, they're the only ones which Hubzilla and (streams) don't list as forums. Even Guppe groups are listed as forums on Hubzilla and probably also on (streams). This can only change if FediGroups actually soft-forks Mastodon and at least adds Group actor identification, no matter how much of Mastodon's code will have to be changed for that.
I'll be honest: I hope that when the redesign of conversations on (streams) goes stable, it'll become a good base for Fediverse-wide forums, even for Mastodon users who think the Fediverse is only Mastodon and for notoriously stubborn Misskey plus Forkeys.
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #Mastodon #Hubzilla #Streams #(streams) #Groups #Forums #FediGroups
The irony is that it's the worlds without these three that actually work, even decidedly non-commercial Overte. The cryptobros' get-rich-quick schemes ended up underdeveloped (NeosVR) at best, likely even buggy (Decentraland), and I guess not exactly few sold expensive NFTs as tokens to virtual land which never came to exist because they've never launched their world in the first place.
It's hard to tell whether they were cases of intentional fraud, and the owners never intended to develop and launch a virtual world in the first place, or whether they did want to launch a virtual world, but their cryptocurrency crashed before they could fund the development.
I mean, I find it increasingly hard to believe that the makers of Decentraland really knew nothing about virtual worlds first. I find it more likely meanwhile that they intentionally lied to their customers about having created the world's first decentralised metaverse than that they simply didn't know that this title belongs to something that's eleven years older and actually decentralised.
By the way, there have even been cryptobros who obviously could be bothered to spend a bit more time on Google, and who discovered OpenSim. Free and open-source. Most importantly, free-of-charge. And readily available, they wouldn't have to pay for the development of a virtual world platform first. So they decided to glue a blockchain and a cryptocurrency onto OpenSim and either sell land for crypto or offer crypto gambling or both.
None of this came to fruition. Regardless of whether they were dumb enough to open their grid to the Hypergrid, they had to compete with grids that offer standard Second Life regions for $10/month and varsims for not much more. On top of that, closed grids had to compete with the Hypergrid which had a lot more and better content, not to mention more users.
Oh, and OpenSim doesn't really work with VR headsets for a whole bunch of reasons, so they couldn't market it to the VR crowd either.
#Long #LongPost #CWLong #CWLongPost #Metaverse #Blockchain #Blockchains #Crypto #Cryptocurrency #Cryptocurrencies #NFT #NFTs #Cryptobros #Decentraland #NeosVR #OpenSim #OpenSimulator #VirtualWorlds I'm on Hubzilla which works vastly different from Mastodon. Also, I don't automatically accept new contacts. But here on Hubzilla, when I allow someone to follow me, I automatically "follow them back" (only that I usually don't actually let their posts in). Followers and followed aren't separate here they're all contacts or connections.
So if I unfollow someone, I also stop sending them my own posts, thus disallowing them to follow me.
I only go through my contacts list every few months to try and check who actually still follows me, usually by going through their own follower lists, and to remove dead contacts which I can identify through delivery reports.
I myself very rarely follow someone because I already follow just about everyone everywhere in the Fediverse who is into the primary topic of my channel. And I never start following users who don't write about this primary topic. I don't want masses of Twitter-like noise on my stream.
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #Hubzilla #Followers #Followed #Contacts #Connections
Direktnachrichten sind Nachrichten, die an eine oder mehrere Einzelverbindungen adressiert sind. Sie sind ber den Netzwerkstream zugnglich. Ein Filter fr Direktnachrichten wurde dem Stream-Filter-Widget fr den schnellen Zugriff hinzugefgt.
Mchte man eine Direktnachricht an einen (oder mehrere) andere Nutzer versenden (Direktnachrichten knnen nur von den Adressaten und vom Versender gelesen werden), so verfasst man einen normalen Beitrag und adressiert diesen per spezieller Erwhnung ausschlielich an den / die Empfnger. Dies geschieht mit der privaten Erwhnung (Privacy-Tag). Ein Privacy-Tag ist ein Name, dem die beiden Zeichen ! vorangestellt sind und der zustzlich zur Markierung dieser Kanle auch die Datenschutzberechtigungen des Beitrags so ndert, dass nur diese bercksichtigt werden.
Zum Anzeigen kann man die DN im Stream filtern.
Um auf eine DN auch wieder "privat", also als DN zu antworten, muss man kein Privacy-Tag nutzen. Man antwortet einfach direkt auf die eingegangene DN.
Alternativ zum Privacy-Tag kann man auch Kanle oder Privacygruppen aus dem Privacy-Tool auswhlen. Dies ist der umstndlichere Weg, der aber auch funktioniert. Die Nutzung eines Privacy-Tags berschreibt allerdings eine ggf. getroffene Auswahl im Privacy-Tool. Schreibt man also einen Beitrag, der als Direktnachricht verschickt werden soll, kann man den Privacy-Tag weglassen und stattdessen auf das Vorhangschloss-Symbol neben dem Button "Teilen" klicken, so dass man in die Berechtigungs-Einstellungen gelangt.
Dort whlt man dann den Punkt "Benutzerdefiniert" und kann anschlieend dem gewnschten Adressaten die notzwendige Berechtigung einrumen.
Die so abgeschickte DN erscheint dann beim Adressaten, ist fr andere aber nicht sichtbar.
Mit dem Versionssprung von 4.6 auf 5.x wurde die ursprngliche Mail-Funktionalitt deaktiviert, weil es im neuen zot6-Protokoll kein Konzept fr private Mails mehr gibt. Die alte Mail-Funktionalitt konnte, sofern sie noch bentigt wurde, mit der Mail-App, die als Addon angeboten wurde, aktiviert werden. Die App ist inzwischen auch eingestellt worden.
Das Konzept des Mail-Versands wurde durch Direktnachrichten (DN) ersetzt. #FediTips #FediverseTips #hubzilla #hubzillahppchen
#Long #LongPost #CWLong #CWLongPost
Direktnachrichten sind Nachrichten, die an eine oder mehrere Einzelverbindungen adressiert sind. Sie sind ber den Netzwerkstream zugnglich. Ein Filter fr Direktnachrichten wurde dem Stream-Filter-Widget fr den schnellen Zugriff hinzugefgt.
Mchte man eine Direktnachricht an einen (oder mehrere) andere Nutzer versenden (Direktnachrichten knnen nur von den Adressaten und vom Versender gelesen werden), so verfasst man einen normalen Beitrag und adressiert diesen per spezieller Erwhnung ausschlielich an den / die Empfnger. Dies geschieht mit der privaten Erwhnung (Privacy-Tag). Ein Privacy-Tag ist ein Name, dem die beiden Zeichen ! vorangestellt sind und der zustzlich zur Markierung dieser Kanle auch die Datenschutzberechtigungen des Beitrags so ndert, dass nur diese bercksichtigt werden.
Zum Anzeigen kann man die DN im Stream filtern.
Um auf eine DN auch wieder "privat", also als DN zu antworten, muss man kein Privacy-Tag nutzen. Man antwortet einfach direkt auf die eingegangene DN.
Alternativ zum Privacy-Tag kann man auch Kanle oder Privacygruppen aus dem Privacy-Tool auswhlen. Dies ist der umstndlichere Weg, der aber auch funktioniert. Die Nutzung eines Privacy-Tags berschreibt allerdings eine ggf. getroffene Auswahl im Privacy-Tool. Schreibt man also einen Beitrag, der als Direktnachricht verschickt werden soll, kann man den Privacy-Tag weglassen und stattdessen auf das Vorhangschloss-Symbol neben dem Button "Teilen" klicken, so dass man in die Berechtigungs-Einstellungen gelangt.
Dort whlt man dann den Punkt "Benutzerdefiniert" und kann anschlieend dem gewnschten Adressaten die notzwendige Berechtigung einrumen.
Die so abgeschickte DN erscheint dann beim Adressaten, ist fr andere aber nicht sichtbar.
Mit dem Versionssprung von 4.6 auf 5.x wurde die ursprngliche Mail-Funktionalitt deaktiviert, weil es im neuen zot6-Protokoll kein Konzept fr private Mails mehr gibt. Die alte Mail-Funktionalitt konnte, sofern sie noch bentigt wurde, mit der Mail-App, die als Addon angeboten wurde, aktiviert werden. Die App ist inzwischen auch eingestellt worden.
Das Konzept des Mail-Versands wurde durch Direktnachrichten (DN) ersetzt. #FediTips #FediverseTips #hubzilla #hubzillahppchen
#Long #LongPost #CWLong #CWLongPostMchte man Inhalte (z.B. Dateien aus der Cloud) fr bestimmte Personen zugreifbar machen, obwohl diese ber keinen Hubzilla-Account verfgen, aber ansonsten nicht fr die ffentlichkeit, so arbeitet man mit Gastzugngen.
Wer mit einem solchen Gastzugang eingeloggt ist, kann alles sehen, was ffentlich zugnglich ist und zustzlich alles, was der Zuteiler des Gastzugangs fr diesen speziellen Gastzugang freigegeben hat.
Angenommen wir htten eine "geheime" Grafik mit dem Dateinamen "geheimesgeheimnis.jpg" in unsere Cloud hochgeladen und wrden diese Datei einem Nutzer, der keinen Hubzilla-Account hat, zugnglich machen wollen.
Zu diesem Zweck legen wir dafr einen Gastzugang an. Das geschieht mit der App (Hamburger-Men ) "Gastzugang".
Es wird ein Eingabeformular fr die Gastzugangsdaten angezeigt. Hier denkt man sich einen temporren Benutzernamen aus. Ein Passwort wird vom System automatisch erstellt. Diese Daten (Name / Passwort) muss man demjenigen, dem man Zugang gewhren mchte mitteilen.
Auerdem gibt man hier ein "Verfallsdatum" fr den Gastzugang ein (oder lsst das Feld leer, fr zeitlich unbegrenzten Zugang). Nach Ablauf der Frist wird der Gastzugang automatisch gelscht.
Solange man noch keine eigenen Rollen definiert hat, ist fr die Rolle "Standard" voreingestellt. Das kann man so auch belassen, sofern man nichts besonderes vorhat.
Nun klickt man auf "Absenden" und der Gastzugang ist erstellt.
Jetzt ffnet man im Hamburger-Men die App "Dateien" und ldt dort die Datei hoch.
Anschlieend ffnet man das Kontextmen () der Datei und whlt dort "Berechtigungen anpassen). Unter der Dateiliste erscheint nun ein kleines Vorhangschloss-Symbol, auf welches man klickt. Es ist jetzt mglich, die Zugangsberechtigungen aus einer Reihe von Standard-Berechtigungen auszuwhlen. Fr unsere Zwecke whlen wir "Benutzerdefinierte Auswahl".
In der erscheinenden Gruppen- und Kontaktliste erscheint unser gerade angelegter Gastzugang. Diesem rumt man die Zugriffsberechtigung ein "Klick auf "Erlauben") und man schliet anschlieend die Liste.
Ist das erledigt, klickt man auf den Button "Absenden" neben dem Vorhangschloss-Symbol (das jetzt einen geschlossenen Bgel zeigt) und ist fertig.
Die URL fr die Datei wird angezeigt, wenn man mit dem Mauszeiger ber den Dateinamen fhrt.
Bei den jetzt gewhlten Einstellungen knnen nur wir selbst und der Gastzugang auf die Datei zugreifen. Nicht bei Hubzilla angemeldete Nutzer und sogar Nutzer mit einem eigenen Account bei Hubzilla knnen die Datei nicht sehen.
Wenn sich nun der Nutzer, der ber die Zugangsdaten fr den Gastzugang verfgt, mit diesen einloggt, dann wird ihm die Datei zugnglich gemacht.
Falls man den Gastzugang irgendwann auch schon vor dem Ablaufdatum lschen mchte, klickt man im Hamburger-Men auf "Gastzugang". In der linken Seitenleiste werden die Gastzugnge aufgelistet. Hier whlt man dann den zu lschenden Gastzugang aus und klickt in der erscheinenden Maske auf "Lschen".
#FediTips #FediverseTips #hubzilla #hubzillahppchen
#Long #LongPost #CWLong #CWLongPost Hubzilla-Hppchen: Gastzugang
Mchte man Inhalte (z.B. Dateien aus der Cloud) fr bestimmte Personen zugreifbar machen, obwohl diese ber keinen Hubzilla-Account verfgen, aber ansonsten nicht fr die ffentlichkeit, so arbeitet man mit Gastzugngen.
Wer mit einem solchen Gastzugang eingeloggt ist, kann alles sehen, was ffentlich zugnglich ist und zustzlich alles, was der Zuteiler des Gastzugangs fr diesen speziellen Gastzugang freigegeben hat.
Angenommen wir htten eine "geheime" Grafik mit dem Dateinamen "geheimesgeheimnis.jpg" in unsere Cloud hochgeladen und wrden diese Datei einem Nutzer, der keinen Hubzilla-Account hat, zugnglich machen wollen.
Zu diesem Zweck legen wir dafr einen Gastzugang an. Das geschieht mit der App (Hamburger-Men ) "Gastzugang".
Es wird ein Eingabeformular fr die Gastzugangsdaten angezeigt. Hier denkt man sich einen temporren Benutzernamen aus. Ein Passwort wird vom System automatisch erstellt. Diese Daten (Name / Passwort) muss man demjenigen, dem man Zugang gewhren mchte mitteilen.
Auerdem gibt man hier ein "Verfallsdatum" fr den Gastzugang ein (oder lsst das Feld leer, fr zeitlich unbegrenzten Zugang). Nach Ablauf der Frist wird der Gastzugang automatisch gelscht.
Solange man noch keine eigenen Rollen definiert hat, ist fr die Rolle "Standard" voreingestellt. Das kann man so auch belassen, sofern man nichts besonderes vorhat.
Nun klickt man auf "Absenden" und der Gastzugang ist erstellt.
Jetzt ffnet man im Hamburger-Men die App "Dateien" und ldt dort die Datei hoch.
Anschlieend ffnet man das Kontextmen () der Datei und whlt dort "Berechtigungen anpassen). Unter der Dateiliste erscheint nun ein kleines Vorhangschloss-Symbol, auf welches man klickt. Es ist jetzt mglich, die Zugangsberechtigungen aus einer Reihe von Standard-Berechtigungen auszuwhlen. Fr unsere Zwecke whlen wir "Benutzerdefinierte Auswahl".
In der erscheinenden Gruppen- und Kontaktliste erscheint unser gerade angelegter Gastzugang. Diesem rumt man die Zugriffsberechtigung ein "Klick auf "Erlauben") und man schliet anschlieend die Liste.
Ist das erledigt, klickt man auf den Button "Absenden" neben dem Vorhangschloss-Symbol (das jetzt einen geschlossenen Bgel zeigt) und ist fertig.
Die URL fr die Datei wird angezeigt, wenn man mit dem Mauszeiger ber den Dateinamen fhrt.
Bei den jetzt gewhlten Einstellungen knnen nur wir selbst und der Gastzugang auf die Datei zugreifen. Nicht bei Hubzilla angemeldete Nutzer und sogar Nutzer mit einem eigenen Account bei Hubzilla knnen die Datei nicht sehen.
Wenn sich nun der Nutzer, der ber die Zugangsdaten fr den Gastzugang verfgt, mit diesen einloggt, dann wird ihm die Datei zugnglich gemacht.
Falls man den Gastzugang irgendwann auch schon vor dem Ablaufdatum lschen mchte, klickt man im Hamburger-Men auf "Gastzugang". In der linken Seitenleiste werden die Gastzugnge aufgelistet. Hier whlt man dann den zu lschenden Gastzugang aus und klickt in der erscheinenden Maske auf "Lschen".
#FediTips #FediverseTips #hubzilla #hubzillahppchen
#Long #LongPost #CWLong #CWLongPost
Hubzilla-Hppchen: HQ
HQ ist die Standard-Startseite nach der Anmeldung. Sie bietet einen schnellen berblick ber die letzten Beitrge und Direktnachrichten.
Ruft man den Hubzilla-Server (Hub) auf, bei welchem man registriert ist (und loggt sich, sofern das noch nicht geschehen ist, ein), dann landet man inzwischen nicht in der normalen Grid-/, sondern auf der Seite "HQ". Der erste sprbare Vorteil ist, dass die Seite wesentlich schneller rendert.
Man erreicht das HQ aber auch aus dem Hamburger-Men oben rechts () oder, wenn die HQ-App angepinnt ist, aus der Header-Leiste.
In der linken Seitenleiste ist zunchst ein Teil des mit ffentlichen und beschrnkten Beitrgen zu sehen, bei welchen jedoch nur ein Excerpt angezeigt wird. Ein Klick auf einen dieser Eintrge bringt den Beitrag in der Hauptansicht (mitte) zur Ansicht.
Nach dem Aufrufen des HQ sind in der Hauptansicht zunchst aber die letzten nderungen in verschiedenen Berichte, wie Wiki, Webseiten, Fotos, Dateien etc. zu sehen.
Die linke Seitenleiste weist verschiedene Reiter auf, mit denen weitere Listen angezeigt werden knnen.
Der zweite Reiter dient der Listenasicht ausschlielich von (DN).
Der dritte Reiter zeigt "markierte" Beitrge, also Beitrge, die man mit einem "Sternchen" Markiert hat (das geschieht im Kontextmen des jeweiligen Beitrags).
Der vierte Reiter zeigt die Mitteilungs-Liste.
Unter dieser Listenansicht sind noch zwei Icons vorhanden, ein "Bleistift", der bei einem Klick den Beitrags-Editor ffnet um schnell einen neuen Beitrag zu erstellen, und einen "Notiz-Zettel", welcher den Editor fr Notiz-Eingaben ffnet.
#FediTips #FediverseTips #hubzilla #hubzillahppchen
#Long #LongPost #CWLong #CWLongPost
HQ ist die Standard-Startseite nach der Anmeldung. Sie bietet einen schnellen berblick ber die letzten Beitrge und Direktnachrichten.
Ruft man den Hubzilla-Server (Hub) auf, bei welchem man registriert ist (und loggt sich, sofern das noch nicht geschehen ist, ein), dann landet man inzwischen nicht in der normalen Grid-/, sondern auf der Seite "HQ". Der erste sprbare Vorteil ist, dass die Seite wesentlich schneller rendert.
Man erreicht das HQ aber auch aus dem Hamburger-Men oben rechts () oder, wenn die HQ-App angepinnt ist, aus der Header-Leiste.
In der linken Seitenleiste ist zunchst ein Teil des mit ffentlichen und beschrnkten Beitrgen zu sehen, bei welchen jedoch nur ein Excerpt angezeigt wird. Ein Klick auf einen dieser Eintrge bringt den Beitrag in der Hauptansicht (mitte) zur Ansicht.
Nach dem Aufrufen des HQ sind in der Hauptansicht zunchst aber die letzten nderungen in verschiedenen Berichte, wie Wiki, Webseiten, Fotos, Dateien etc. zu sehen.
Die linke Seitenleiste weist verschiedene Reiter auf, mit denen weitere Listen angezeigt werden knnen.
Der zweite Reiter dient der Listenasicht ausschlielich von (DN).
Der dritte Reiter zeigt "markierte" Beitrge, also Beitrge, die man mit einem "Sternchen" Markiert hat (das geschieht im Kontextmen des jeweiligen Beitrags).
Der vierte Reiter zeigt die Mitteilungs-Liste.
Unter dieser Listenansicht sind noch zwei Icons vorhanden, ein "Bleistift", der bei einem Klick den Beitrags-Editor ffnet um schnell einen neuen Beitrag zu erstellen, und einen "Notiz-Zettel", welcher den Editor fr Notiz-Eingaben ffnet.
#FediTips #FediverseTips #hubzilla #hubzillahppchen
#Long #LongPost #CWLong #CWLongPost Hubzilla-Hppchen: Zot
Zot ist das Protokoll, mit dem Hubzilla betrieben wird. Es ermglicht die Kommunikation, das Identittsmanagement und die Zugangskontrolle.
Die Kommunikation mittels Zot kann ffentlich oder privat sein, wobei die private Kommunikation nicht nur einen vollstndig verschlsselten Transport, sondern auch eine verschlsselte Speicherung zum Schutz vorsieht.
Zot untersttzt eine breite Palette von Hintergrunddiensten im Grid, von Freundschaftsvorschlgen bis hin zu Verzeichnisdiensten. Neue Inhalte und Datenaktualisierungen werden im Hintergrund zwischen den Hubs im gesamten Grid gem den Zugriffskontrolllisten und den von den Sender- und Empfngerkanlen festgelegten Berechtigungen weitergegeben. Die Daten werden auch zwischen einer beliebigen Anzahl von Kanalklonen synchronisiert, so dass Hub-Mitglieder auch dann auf Daten zugreifen und nahtlos weiter zusammenarbeiten knnen, wenn ihr primrer Hub nicht erreichbar oder offline ist.
Zot bietet auch eine nomadische Identitt, so dass Ihre Kommunikation mit Freunden, Familie oder anderen Personen, mit denen Sie kommunizieren, nicht durch den Verlust Ihres primren Kommunikationsknotens beeintrchtigt wird - entweder vorbergehend oder dauerhaft.
Die wichtigen Teile Ihrer Identitt und Ihrer Beziehungen knnen auf einem USB-Stick, dem Laptop oder PC gesichert werden und jederzeit an einem beliebigen Knoten im Netz erscheinen - mit all Ihren Freunden und Vorlieben.
Entscheidend ist, dass diese nomadischen Instanzen synchron gehalten werden, so dass jede Instanz bernehmen kann, wenn eine andere gefhrdet oder beschdigt ist. Dies schtzt Sie nicht nur vor greren Systemausfllen, sondern auch vor vorbergehender berlastung der Website und staatlicher Manipulation oder Zensur.
Die nomadische Identitt, die einmalige Anmeldung und die Dezentralisierung von Hubzilla gewhrleisten ein hohes Ma an Widerstandsfhigkeit und Bestndigkeit in der Internetkommunikation. Mittels magic-auth meldet man nur einmal an Ihrem Heimat-Hub (oder einem nomadischen Backup-Hub) an. Dadurch kann man auf alle authentifizierten Dienste zugreifen, die berall im Netz angeboten werden - wie Einkaufen, Blogs, Foren und Zugang zu privaten Informationen. Das Passwort wird nicht auf tausend verschiedenen Websites gespeichert, sondern auf Servern, man selbst kontrolliert oder denen man vertraut.
Zugriffskontrolle: Die Identittsschicht von Zot ermglicht es, fein abgestufte Berechtigungen fr jeden Inhalt zu vergeben, den man verffentlichen mchte. Diese Berechtigungen erstrecken sich ber das gesamte Grid. Das ist so, als htte man eine riesige Website, die aus einer Grozahl von kleinen, individuellen Websites besteht und bei der jeder Kanal im Grid seine Datenschutz- und Freigabeprferenzen fr alle von ihm erstellten Webressourcen vollstndig kontrollieren kann.
Derzeit untersttzt Hubzilla die Zugriffskontrolle fr viele Datentypen, darunter Diskussionsbeitrge und -kommentare, Fotoalben, Veranstaltungen, Cloud-Dateien, Webseiten, Wikis und mehr. Jedes Objekt und die Art und Weise, wie und mit wem es geteilt wird, unterliegt vollstndig Ihrer Kontrolle.
Im Grid braucht man keine riesige Benutzerdatenbank auf dem Rechner, denn das Grid ist die Benutzerdatenbank. Sie verfgt ber eine im Grunde unendliche Kapazitt (begrenzt durch die Gesamtzahl der Hubs, die im Internet online sind) und ist auf unzhlige Computer verteilt.
Der Zugang kann, berall im Grid, fr jede Ressource, jeden Kanal oder jede Gruppe von Kanlen gewhrt oder verweigert werden. Andere knnen auf die eigenen Inhalte zugreifen, wenn es ihnen erlaubt wird, und sie mssen nicht einmal ein Konto auf dem selben Hub haben.
Aktuell verwendet Hubzilla das Zot-Protokoll in der Version 6 (Zot6).
#FediTips #FediverseTips #hubzilla #hubzillahppchen
#Long #LongPost #CWLong #CWLongPost
many on the AP side of things seem to feel they are the real or only fediverse and don't spend much thought on compatibility with us, leaving our developers alone with that pressure.
The vast majority of Mastodon users as well as users of projects that have been based on ActivityPub from the start or for long enough actually think that the Fediverse is only ActivityPub. They don't even know that there's stuff in the Fediverse that has ActivityPub as an optional secondary protocol. Few know that Hubzilla and (streams) exist, even fewer know that neither of these two is based on ActivityPub.
In fact, many Mastodon users, including some who have joined during the second Twitter migration wave in November, 2022, are fully convinced that the Fediverse is only Mastodon, full stop. And that "Fediverse" and "Mastodon" mean the same.
And I think not exactly few want the Fediverse to only be vanilla Mastodon with its hard-coded 500-character limit. They aren't only against federation with Threads and a bridge to Bluesky, but they don't want all that stuff from Pixelfed to Lemmy to Misskey to Friendica to (streams) around either.
Some vulnerable groups have escaped the harassment on Twitter. Of course, they went to Mastodon and only Mastodon because that's all they knew. But now they're stuck on Mastodon. First, they didn't know that better stuff than Mastodon exists in the Fediverse. If they heard about the existence of that stuff, they didn't know and couldn't imagine that it's better or even that anything in the Fediverse could possibly have features that Mastodon doesn't.
But even now they refuse to move again. For one, there's no easy-peasy way to move an entire Mastodon account with all posts, all connections, even all settings to e.g. (streams). But they won't accept anything less. Besides, even if they did try (streams), they'd nope out quickly due to how (streams) doesn't handle anything like Mastodon. They simply don't want to get used to yet another UI/UX, and the step from Mastodon to (streams) is much bigger than from Twitter to Mastodon.
If you really want to introduce (streams)' safety features to them, you must first soft-fork (streams) into something that's indistinguishable from Mastodon on the surface, that is 100% compatible with the Mastodon API, and that Mastodon servers can be seemlessly migrated to. Then you have to migrate all major Mastodon instances, including and especially mastodon.social, to this soft fork. And then you have to adjust everyone's default settings to "perfect harassment protection, but handles exactly the same as Mastodon" because chances are these people won't even touch their settings.
If Mastodon users want perfect privacy and security, they want it on the very Mastodon instance they're on right now. And they want all these perfect privacy and security features to be on by default, but without meddling with their own use of Mastodon.
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta
I wonder sometimes at creators making clothes for bodies no one uses, while not supporting very popular ones.
I guess it's often a case of the creators themselves using these bodies because they prefer them over the super-popular ones for some reason. They basically make clothes for themselves, and while they already have these clothes, they may just as well sell them.
I know at least one such case in OpenSim. She has been making original mesh clothes for Ruth 2.0 for years now. Mind you, in OpenSim, the vast majority of avatars has been wearing stolen Maitreya Laras since 2015. Many users don't even know there's any legal content in OpenSim, much less legal and original mesh bodies. And those who look through the mesh body sections of some freebie stores and find Ruth 2.0 or Ruth2 there can't imagine that anyone actually uses them, what with no big freebie store even offering clothes for these bodies. But she makes them, and she offers them herself.
Why does she do that Out of idealism, so that people have the choice to put on legal mesh clothes made in and for OpenSim Not so much. To support legal mesh bodies by providing clothes for them A bit more, but not so much either. It's mostly because the Maitreya Lara clothes that are being stolen are too sexy/racy/slutty for her. She prefers different styles of clothes, but the content thieves don't cater to her taste and want all female avatars to only ever look as sexy or racy as possible.
#Long #LongPost #CWLong #CWLongPost What about explanations of what's in the image for those who don't know
Is it a universally good advice to assume that everyone who comes across this image knows what a capybara is and what yuzu fruits are or, alternatively, is willing to fire up a Web browser, if necessary, and search the Web for all missing information to understand the image Risk nobody getting the image for brevity's sake
Or would it be better to relocate the image description from the alt-text to the post text, at least if the character limit allows for that, and explain everything that might not be common knowledge but necessary to get the image and/or its description
I'm asking because my own images cover much, much more niche topics.
#Long #LongPost #CWLong #CWLongPost #AltText #ImageDescription #ImageDescriptions #ImageDescriptionMeta #CWImageDescriptionMeta
However, I believe that your interpretation of the term image description or alt tag is not what the inventors had in mind when they introduced this HTML tag.
To be fair, alt-text was invented for static HTML webpages. This means two things in comparison with the Fediverse.
Webpages are usually only visited by people who are specifically interested in them. These people either have some basic knowledge of what the webpage is about, or they're ready, willing and able to browse around to gather the information they need.
Fediverse posts are shoved into the faces of people who'd never look up whatever the post is about. The more niche the topic of a post is, the fewer people know anything about it. Also, especially amongst the mobile users, few want to start a Web browser and start Googling stuff until they understand an image. They want everything described and explained in one place, namely their Fediverse app, especially blind or visually-impaired users.
Also, static HTML webpages don't have a character limit. Most of the Fediverse is limited to 500 characters.
I dare say that what I do on Hubzilla is closer to how things are done on static webpages or in blog posts than what's done on vanilla Mastodon with three times as high a character limit in alt-text as in the post itself.
To sum things up once more, here's how I do single-image posts:
- The post itself from top to bottom:
list - Actual post text
- Embedded image (ripped out of context and converted to a file attachment by Mastodon, Misskey and their forks)
- Full, detailed image description
- Hashtags
- Short description of visuals that deliberately doesn't try to fully describe the image, much less explain anything
- Something like this: "A full, detailed image description including explanations can be found in the actual post. If you're on Mastodon, Glitch, Hometown, Misskey, Firefish, Iceshrimp, Sharkey, Catodon or the like, it is right above, hidden behind the long post content warning. If you're on Pleroma, Akkoma, Friendica, Hubzilla, (streams) or the like, it will follow here in the post, right below this image."
In alt-text, supposing that I've got enough space, I'd have to give one full, detailed description with all detail descriptions and all explanations for each image. That's also because different Fediverse projects order images differently. Mastodon always reverses the order of my images, so what's the first image for me is the last image for everyone on Mastodon and vice versa.
In my opinion, 1500 characters should be sufficient to list the most important elements required to understand the image.
In 1500 characters, I could only mention. I could only name-drop. But I can neither describe to blind or visually-impaired users what something unfamiliar looks like, nor can I explain to anyone what something unfamiliar is.
I could only say there's an OpenSimWorld beacon standing in a particular spot in the image. But without an explanation what an OpenSimWorld beacon is in the first place, this information is completely and utterly useless, and without a visual description what this particular OpenSimWorld beacon looks like, it's ableist on top of that.
It takes me 1,000 characters to describe the looks of the current standard OpenSimWorld beacon. And it takes me 4,000 characters to explain it, no matter what it looks like.
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #AltText #ImageDescription #ImageDescriptions #ImageDescriptionMeta #CWImageDescriptionMeta
You've done a hell of a lot of work, but perhaps you would have been better off using a real photo.
I don't post real-life photos unless they're parts of meme templates.
This is not my one single personal Fediverse account. This channel has virtual worlds, OpenSim specifically, as its primary topic. So I have to see how I can get pictures from virtual worlds to work.
And then you should also question who the alt texts are intended for.
Been there, done that.
My target audience is partly OpenSim users, most of whom are on Mastodon and not necessarily on an instance for that topic, partly other people who might be interested in this stuff.
My actual audience is whoever comes across my posts in whichever timeline, and be it the federated timeline on mastodon.social.
My image descriptions have to be informative enough so that my actual audience gets my images.
Nobody would even attempt to read a picture description like yours because it's far too long.
Well, apparently, a very very few people did read them.
But if I made my image descriptions shorter, I'd leave blind or visually-impaired people who don't know what virtual worlds and the stuff in virtual worlds look like standing in the rain. And if I shortened them to standard Mastodon alt-text length, nobody would understand my images, and the image descriptions would be useless.
I was told that texts of this length and possibly this level of detail are not useful as ALTTEXT and should be limited to the bare essentials.
The idea that "alt-text" and "image description" are always mutually synonymous is so Mastodon. I mean, most Mastodon users don't have any space for image descriptions elsewhere than in alt-text.
But I don't put my full, detailed image descriptions into the alt-text.
My alt-texts contain a short, purely visual, not really informative description, and they mention that the actual full image description is in the post itself, either right below or hidden behind the CW above, depending where the reader is. And yes, the full description goes into the post where I've got enough space.
I couldn't put such long image descriptions into alt-text anyway. That is, I could, I don't have any character limits for alt-text either.
But Mastodon, Misskey and their respective forks have hard 1,500-character limits for alt-text, and when a longer alt-text comes in, they chop it off at the 1,500-character mark.
Also, I explain a lot in my image descriptions. That's information that can't be found anywhere else in the post, not in the actual post text, not in the image. Such information must never be exclusively available in the alt-text because there are people who can't access alt-text, e.g. due to a physical disability. Any information only available in alt-text is inaccessible and therefore lost to them.
Lastly, descriptions of images from virtual worlds, obscure virtual worlds even, have to be extremely long. That's because they're so obscure. People don't know anything about them, and so they'll need a lot of information to understand the image.
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #AltText #ImageDescription #ImageDescriptions #ImageDescriptionMeta #CWImageDescriptionMeta(This is actually a comment. Find another post further up in this thread.)
Now let's pry LLaVA's image description apart, shall we
The image appears to be a 3D rendering or a screenshot from a video game or a virtual environment.
Typical for an AI: It starts vague. That's because it isn't really sure what it's looking at.
This is not a video game. It's a 3-D virtual world.
At least, LLaVA didn't take this for a real-life photograph.
It shows a character
It's an avatar, not a character.
standing on a paved path with a brick-like texture.
This is the first time that the AI is accurate without being vague. However, there could be more details to this.
The character is facing away from the viewer,
And I can and do tell the audience in my own image description why my avatar is facing away from the viewer. Oh, and that it's the avatar of the creator of this picture, namely myself.
looking towards a sign or information board on the right side of the image.
Nope. Like the AI could see the eyeballs of my avatar from behind. The avatar is actually looking at the cliff in the background.
Also, it's clearly an advertising board.
The environment is forested with tall trees and a dense canopy, suggesting a natural, possibly park-like setting.
If I'm generous, I can let this pass as not exactly wrong. Only that there is no dense canopy, and this is not a park.
The lighting is subdued, with shadows cast by the trees, indicating either early morning or late afternoon.
Nope again. It's actually late morning. The AI doesn't know because it can't tell that the Sun is in the southeast, and because it has got no idea how tall the trees actually are, what with almost all treetops and half the shadow cast by the avatar being out of frame.
The overall atmosphere is calm and serene.
In a setting inspired by thrillers from the 1950s and 1960s. You're adorable, LLaVA. Then again, it was quiet because there was no other avatar present.
There's a whole lot in this image that LLaVA didn't mention at all. First of all, the most blatant shortcomings.
First of all, the colours. Or the lack of them. LLaVA doesn't say with a single world that everything is monochrome. What it's even less aware of is that the motive itself is monochrome, i.e. this whole virtual place is actually monochrome, and the avatar is monochrome, too.
Next, what does my avatar look like Gender Skin Hair Clothes
Then there's that thing on the right. LLaVA doesn't even mention that this thing is there.
It doesn't mention the sign to the left, it doesn't mention the cliff at the end of the path, it doesn't mention the mountains in the background, and it's unaware of both the bit of sky near the top edge and the large building hidden behind the trees.
And it does not transcribe even one single bit of text in this image.
And now for what I think should really be in the description, but what no AI will ever be able to describe from looking at an image like this one.
A good image description should mention where an image was taken. AIs can currently only tell that when they're fed famous landmarks. AI won't be able to tell from looking at this image that it was taken at the central crossroads at Black White Castle, a sim in the OpenSim-based Pangea Grid anytime soon. And I'm not even talking about explaining OpenSim, grids and all that to people who don't know what it is.
Speaking of which, the object to the right. LLaVA completely ignores it. However, it should be able to not only correctly identify it as an OpenSimWorld beacon, but also describe what it looks like and explain to the reader what an OpenSimWorld beacon is, what OpenSimWorld is etc. because it should know that this can not be expected to be common knowledge. My own description does that in round about 5,000 characters.
And LLaVA should transcribe what's written on the touch screen which it should correctly identify as a touch screen. It should also mention the sign on the left and transcribe what's written on it.
In fact, all text anywhere within the borders of the picture should be transcribed 100% verbatim. Since there's no rule against transcribing text that's so small that it's illegible or that's so tiny that it's practically invisible or that's partially obscured or partially out of frame, a good AI should be capable of transcribing such text 100% verbatim in its entirety as well. Unless text is too small for me to read in-world, I can and do that.
And how about not only knowing that the advertising board is an advertising board, but also mentioning and describing what's on it Technically speaking, there's actually a lot of text on that board, and in order to transcribe it, its context needs to be described. That is, I must admit I was sloppy myself and omitted a whole lot of transcriptions in my own description.
Still, AI has a very very long way to go. And it will never fully get there.
#Long #LongPost #CWLong #CWLongPost #AltText #ImageDescription #ImageDescriptions #ImageDescriptionMeta #CWImageDescriptionMeta #AI #LLaVAOkay, I've done it.
I've pitted an image-describing AI against myself and one of my own image descriptions.
As the test object, I've used my latest in-world picture which has first been published , including the exact same full-length image description and explanation from that post. The short description in the alt-text is the same, too, all shortcomings included, but I had to modify the alt-text itself for this specific use-case.
Users of Pleroma and its forks, Friendica, Hubzilla and (streams) can see the image here:
Users of Mastodon, Misskey and their respective forks can see it as a file attachment below this post.
My AI of choice was the . I've fed it the image at the resolution at which I've also posted it, namely at a resolution of 800x533 pixels.
The AI took a few seconds to produce this 558-character image description:
The image appears to be a 3D rendering or a screenshot from a video game or a virtual environment. It shows a character standing on a paved path with a brick-like texture. The character is facing away from the viewer, looking towards a sign or information board on the right side of the image. The environment is forested with tall trees and a dense canopy, suggesting a natural, possibly park-like setting. The lighting is subdued, with shadows cast by the trees, indicating either early morning or late afternoon. The overall atmosphere is calm and serene.
I'll talk about this description in more details in a follow-up.
Now, here comes my description. I didn't write it while looking at the scaled-down image. I didn't write it while looking at the image at its original solution of 2100x1400 pixels either.
I wrote it while I was still in-world. I could walk around and zoom around and see everything from different angles and at much, much higher resolutions. For example, one of the picture on the advertising board to the right shows a building that's nearby but outside the borders of the image. I could describe that picture by walking to that very building.
All in all, I took eight hours to produce this 25,271-character image description:
Image description
The picture in this post is a digital rendering from inside a 3-D virtual world based on OpenSimulator, generated in a regular client for this kind of virtual worlds, also known as a viewer, using shaders and generated shadows, but without ray-tracing. It shows my avatar on a paved path surrounded by conifer trees and with cliffs in the background. Everything in the picture is in monochrome like an old black-and-white film. However, the image is unaltered and shows both my avatar and the scene as they are in-world.What OpenSimulator is
OpenSimulator is a free, open-source, cross-platform server-side re-implementation of the technology of . The latter is a commercial 3-D virtual world created by Philip Rosedale, also known as Philip Linden, of Linden Labs and launched in 2003. It is a so-called "pancake" virtual world which is accessed through desktop or laptop computers using standard 2-D screens rather than virtual reality headsets. Second Life had its heyday in 2007 and 2008. It is often believed to have shut down in late 2008 or early 2009 when the constant stream of news about it broke away, but in fact, it celebrated its 20th birthday in 2023, and it is still evolving.
, OpenSim in short, was first published in January, 2007. Unlike Second Life, it is not one monolithic, centralised world. It is rather a server application for worlds or "grids" like Second Life which anyone could run on either rented Web space or at home, given a sufficiently powerful computer and a sufficiently fast and reliable land-line Internet connection. This makes OpenSim as decentralised as the Fediverse. The introduction of the Hypergrid in 2008 made it possible for avatars registered on one OpenSim grid to travel to most other OpenSim grids.
Second Life and the OpenSim-based worlds are called "grids" because they are flat worlds divided into square areas of 256 by 256 metres each which is roughly 280 by 280 yards. These areas are called "regions".Where the picture was made
The picture displays a part of Black White Castle, a fairly recent sim in Pangea Grid. "Sim" is short for "simulator" which refers to what is running in a region so that something can be built in it, and avatars can enter it. In Second Life, a sim is always one region. In OpenSim, so-called varsims can span multiple regions, always in a square arrangement with the same number of regions in both directions. Up to 32x32 regions in one sim are possible. Black White Castle only covers one region.
is a German OpenSim grid with a special focus on arts, architecture and landscaping.
The name "Black White Castle" is most likely borrowed from a section of the innuendo-saturated German comedy film Neues vom Wixxer from 2007, the sequel to Der Wixxer from 2004. Both films are parodies on the German black-and-white mystery thrillers Der Hexer from 1964 and its sequel Neues vom Hexer from 1965. These films, in turn, are part of a series commonly referred to as "Edgar Wallace films" as they're based on crime novels written by the British author Richard Horatio Edgar Wallace. These two films are based on the novel The Ringer from 1926, a revised version of a 1925 novel known by the titles The Gaunt Stranger and Police Work.
Neues vom Wixxer, while generally in colour, picks up black and white as what has grown into a style element in the classic Edgar Wallace films in a place named "Black-White Castle". As the name indicates, it is entirely black and white for reasons of tradition, everyone and everything inside it included.
The eponymous sim was built in small parts by making entirely new assets with monochrome textures, but mostly by taking existing objects, extracting their textures, exporting them from OpenSim, using an external image editor to reduce their saturation to zero, re-uploading them to OpenSim and replacing the original textures on the objects with their new monochrome versions. The basic ground texture was altered in the same way, and even the sky and the sunlight are devoid of colour. Likewise, it's common for visitors like me to try and make their own avatars entirely black and white.
The sim was built by Bink Draconia who had previously built a sim with the TV series The Good Place, started in 2016, as its theme.My avatar
My avatar is standing in the middle of the image, the head right of centre by about two or three percent of the image's width due to most of the weight resting on the right foot, the feet a few percent above the bottom edge of the image, roughly centred on average and slightly apart. His back is turned towards the camera, and he is facing away from the camera, so his face is entirely invisible.
He is a male human with fair skin that was altered to light grey and short black hair. He is wearing a dark grey tweed suit with a very large herringbone pattern on the jacket and an even larger herringbone pattern on the trousers. Underneath the jacket, he is wearing a white button-down shirt, of which only a part of the collar above the collar of the jacket and the cuffs below the sleeves of the jacket are visible. In addition, he is wearing a black bowler hat and a pair of dark grey, slightly shiny formal dress shoes.The ground
Beneath the avatar, there is a straight path with irregular edges that is about five metres or 17 feet wide and leads about 40 metres or 140 feet forward, ahead of and away from the avatar. Its texture shows pavement made of medium grey, rectangular concrete pavers, placed in alternating orientations in a 90-degree herringbone pattern, but rotated against the region's coordinate axes by 45 degrees and against the rough direction of the path by about 20 degrees to the right. The pavers are about twice as large as they would be in real life.
On both sides of the avatar, the pathway widens into a crossing, but the other three paths are beyond the edges of the image.
The ground on the sides of the paved path has a blurry light grey texture with a coarse resolution that is either a desaturated, very light grass texture or thin, dirty snow.The scenery to the left
To the very left, there is a wooden arrow sign that is approximately rectangular except for the rough shape of the wood, including four notches on the left-hand side, and the extra corner protruding from the right-hand edge that points into the distance along the path. The bottom edge of the sign is at roughly the same height as the middle of my avatar's thighs, and the top edge is a little bit more than twice as high.
The sign has has "BlackWhite Castle" written on it in a Fraktur blackletter typeface, reminiscent of bright, shiny embossed metal with some dark shading surrounding it, but with a hard-to-identify texture on it. "BlackWhite" is written as one word, but in Pascal Case with the first letters of both "Black" and "White" as capitals. The writing is a bit less than a third of the height of the sign and about as long as its top and bottom edges. The medium-grey paint has partly come off again, especially near the top, but the writing is still intact. The sign shows the way to the building after which the whole sim is named. The sign is placed on top a lighter piece of wood with a rectangular cross-section that is a bit thinner than the sign itself and serves as its sign pole.
The sign is surrounded by three identical groups of eight bushels of high grass each, one to its left, one behind it, one to its right and partly in front of it. Most of the grass is less tall than the sign, but some of it, especially in the bushels behind the sign which have been enlarged, is taller. Also, in front of the sign, there is a group of six stone mushrooms at six different sizes which, given the colour-less setting, appear like actual rock. The two biggest ones have a diameter larger than that of my avatar's bowler hat.
There are three mountain pines to the left of the path which are identical, save for their size. The one the farthest away is about 12 metres or 40 feet tall. It is mostly obscured by another pine which is standing a little further to the left in the image and closer to the on-looker, and which is roughly 14 metres or 47 feet tall. Just right of the arrow sign and behind the right-hand grass bushel, there is a pine of about 20 metres or 70 feet, tall enough for its treetop to be beyond the borders of the image. All three cast a shadow on the ground around them and the pathway, as does a fourth 12-metre pine way to the left whose trunk is entirely outside the borders of the image, but whose shadow ends at my avatar's feet.
Between the second and the third pine, closer to the edge of the pathway than any of the pines, there are two rocks lying on the ground. Both take up the same ground area, but the one to the right is about knee-high, and the one to the left is roughly 60 percent higher. There is another group of eight grass bushels, four of which are in front of these two rocks while the other four seem to have fused with the rocks. More grass bushels surround the first pine.The scenery to the right
To the right of the end of the path, there is another set of six stone mushrooms.
Another mountain pine, just a little shorter than the second one, is standing opposite the second one. Further to the right and further up-front, there are several more conifers of various heights, some only nine metres or 30 feet, others twice as high. The closest of these conifers, also one of the smallest, is at about a quarter of the width of the image away from the right-hand border, and it is the closest to the edge of the pathway.
All trees are made the tradition Second Life and OpenSim way: The trunk is a textured 3-D model. Everything else consists of the same partly transparent texture with branches, twigs and and needles on flat surfaces that pass through the trunk and have the texture on both sides. The mountain pines have three such surfaces at angles of 60 degrees from another, the other conifers have four which are 45 degrees apart. Within the context of the scenery, however, this is hardly noticeable, and it puts less strain on the graphics hardware.
To the right of the path, the ground is covered by a lot more grass, only that most of it more simple, using one partly transparent 2-D surface for each bushel, and only a bit higher than knee-high at its maximum.
A mostly wooden outdoor info board is protruding to the left from behind the closest of the conifers. Two vertical wooden teams have between them, from top to bottom, a longer but smaller horizontal beam, six rows of two slightly darker horizontal planks and another two horizontal beams, nine much smaller vertical bars standing between these two and connecting them. On top of each of the big vertical beams, two short beams mounted in a 90-degree arrangement carry a roof with a texture that seems to suggest slate shingles. The rooftop is a bit more than 3.60 metres or 12 feet above the ground. On the second row of planks, "Info Board" is written in a lighter tone of grey than the planks themselves. The last two letters are behind the trunk of the conifer in front of the sign.
Below the writing, at eye height, there are three square info panels on the board, each with a wooden frame around it. Only the ones on the left and in the middle are visible the one to the right is fully obscured by the conifer again.
The panel on the left carries a worn-out advertising poster for BlackWhite Motel which is on the sim as well, in the opposite direction of where my avatar is looking. It is a two-storey building which is shaped like the letter L laid on the ground. On the short side in the left of the picture, it has room 101 and the office on the ground floor and rooms 201 and 202 upstairs. On the long side, it has eight more rooms, numbers 103 through 106 and 203 through 206, only six of which are in the picture if you visit the motel itself, it becomes clearer why.
There is a parking-lot in front of the building with spaces for eleven cars, separated by white lines. One of the spaces in front of room 104, in the middle of the poster, is occupied by a two-tone white-and-white 1957 Chevrolet Impala four-door sedan which not only lacks hubcaps on its steel wheels, but also has opaque windows in a tone of grey just slightly lighter than the asphalt. Three spaces further to the right, at the right-hand edge of the poster, there is an almost identical car which is only darker all over from the carbody to the chrome trim to even the white walls on the tyres.
The ground floor of the building has a concrete walkway in front of itself which is a bit higher than the parking-lot. The upper floor can be accessed via 180-degree angled stairs in the corner of the building and an open gallery on the parking-lot side. Both the gallery and the actual front of the building are supported by vertical columns made of dark grey concrete with a square cross-section, save for one square cut-out in each corner.
All rooms, the office included, have dark grey doors which face the parking-lot, as do their windows which have very dark grey wooden frames and always come in pairs. Rooms 101 and 201 have two pairs of windows, one on each side of the door. The office and room 202 are window-less. The other rooms have one pair of windows to the right of the door. The doors are framed by two columns with a dark grey concrete panel above them. The wall sections with windows are otherwise filled with very light grey brick walls with unusually long bricks. The same bricks are used for the wall sections to the left of rooms 103 through 106 and 203 through 206 which also feature shiny black wall lamps with energy-saving bulbs.
The low walls that surround the gallery between the columns are made of eight long, very bright grey horizontal panels of probably some kind of metal each, topped with dark grey wooden handrails. The one in front of room 201 carries a flashing neon sign which reads "Vacancy" in all-caps with a brighter rectangular frame around it. Also, on top of the roof, near its front edge, in front of rooms 204 and 205, there's a "motel" sign with no caps and a rather unreliable illumination. Both signs are glowing on the poster.
All windows have blinds on the inside which are mostly closed. Only the right-hand blinds of rooms 101 and 201 and the blinds of rooms 103 and 204 are open. For those who want to know, even though it's outside the advertising poster: The blinds of room 106 are pulled up.
On the gallery-supporting column in front of the door to room 104, a medium-grey surveillance camera facing the parking-lot is moving into various positions. Next to the door of room 105, there is a refrigerated container for packaged ice with two side-hinged but actually unmoving bulb plate hatches on it.
On the ground in front of rooms 101 and 104, there are arrows consisting of seven chevrons each which point towards the office door. In order to enhance their effect, a gradient texture scrolls along them on each of them.
In the background behind the motel, a mountain pine rises above the roof in the middle to the left of the "motel" sign. Behind the sign and all the way to the left, there are three more conifers. These trees are basically identical to the ones in this image. Also, left of centre, a snow-covered mountain top rises further in the background.
The left half of the poster is covered by a dark overlay. Near its top, there is a very light grey rectangle aligned with the right-hand edge of the overlay. It has "Best Price" written on it in dark grey letters. Below that, there are five slightly ligher grey dingbats, either teardrop-spoked asterisks (Unicode U+273B) or sparkles (Unicode U+2747), which imply a five-star rating. An almost identical rectangle is just as close to the bottom and aligned with the left-hand edge of the poster, only that it has "Book Now" written on it. Between them, in the middle of the darkened half, "The BlackWhite Motel" is written in three lines with "BlackWhite" joined to one word again. All writing is done in the same narrow slab-serif typeface, and all characters including the dingbats have lighter lines around them that make them appear embossed.
Back to the panels on the info board: The one in the middle is mounted a bit lower than one on the left. It shows what appears to be a late medieval sea map of a place which I couldn't identify. Due to the limitation of in-world texture sizes to a maximum of 1024x1024 pixels, the rather small writing on the map is indecipherable. Most of it is ocean with some land in the upper half. On the land and in the bottom right corner, there are typical illustrations for maps from those days. The map shows its age with its darker tint and its jagged edges, and its shading makes it appear like it had been folded to a sixteenth of its original size before.
In front of the info board from the on-looker's point of view and actually between it and the conifer nearby, there is another group of eight grass bushels.
In front and partly to the right of the conifer, there is an object which doesn't exist in real life, but which is typical for OpenSimulator: an official OpenSimWorld beacon of the latest generation, but modified to fit the style of the sim.
This particular device has a shiny black foot with a long rectangular footprint which is about 80 percent as high as it is deep and tapered upward, and which has rounded edges. It carries the less shiny main body of the device. It starts narrower than the top surface of the foot in all directions. From bottom to top, it first protrudes forward and immediately increases in depth and slightly and curves backward and continues in a straight slope which still goes more upward than backward. Eventually, it curves upward and ends in a slim, rounded top. Transversally, it keeps the same width all the way. Both sides are carved out and illuminated, normally in cyan, here in almost white. Otherwise, it comes in its standard dark grey. However, it's actually a brownish anthracite grey, and the very top shows some light blue, so while it clearly hasn't received the monochrome treatment all over, a closer look also reveals that it should have. The same goes for the foot which is slightly bluish.
The straight section of the main body carries a shiny black frame with the central element of each OpenSimWorld beacon: the touch display with a ratio of 4:3. When not in use, this specimen shows the standard idle screen, only that it was modified to monochrome. Slightly above the middle, there is the official OpenSimWorld logo, namely the word "OpenSimWorld" itself with no actual caps. However, the "O" at the beginning is replaced with a circle matching the rounded sans-serif typeface which contains a stylised globe tilted to the left by an angle similar to Earth's inclination and showing three parallels and two meridians, but no land underneath. The last five letters, "world", are darker than the rest. Below it, in the same typeface, but in an even lighter grey, and without caps again, but a bit smaller, "teleporter" is written. Both lines also have shaded outlines that make them appear imprinted.
Further below, "Click for destinations" is written, still in the same type face and in about the same shade of grey as "OpenSim" above, but small enough to appear shorter than "teleporter" above. The background of the screen is a very light grey on the top 35 percent, medium grey on the bottom 35 percent and a gradient between the two. Clicking the screen breaks the monochrome theme, though, because the user interface which then appears has not been modified.
Lastly, there's a light grey panel on the front side of the foot which is scripted, too. It has "Like or comment this region" written on it in two lines in the same typeface as the writing on the touch screen, but with medium grey outlines. On the left, there is a medium grey thumb-up symbol, and on the right, there is a speech bubble with three dots in it in two shades of medium grey.
An OpenSimWorld beacon serves several purposes. For one, it transmits information about the sim to . This information includes not only the name of the sim and whether it's currently online, but also how many avatars are currently on the sim. The identities of these avatars are not transmitted, only how many they are. This makes finding sims with activity on them easier for users who want to go to parties or otherwise get into contacts with others, for OpenSim's general population density is much, much lower than Second Life's. This feature also helps generate rather controversial statistics about how popular any given sim is.
OpenSimWorld itself can be seen as the third-party centre of the decentralised Hypergrid. It started out about a decade ago as a sim catalogue, making navigating the Hypergrid and finding places much easier and more convenient than previous solutions like teleport stations or simply exchanging landmarks. Sims must be listed manually by registered users, and they need one OpenSimWorld beacon in-world. For example, is the entry for Black White Castle.
In addition, OpenSimWorld offers discussion forums, user-created information and discussion groups for various topics, announcements of in-world events, information about free or paid land rentals other than whole sim rentals by grids, a catalogue for in-world scripts etc.
The other purpose of an OpenSimWorld beacon is as a teleporter which gives you access to currently about 1,700 sims all over the Hypergrid by means of a crowd-sourced sim list, namely that on OpenSimWorld itself. If you click the touch screen, it shows a list with the ten sims known to OpenSimWorld with the most avatars on them. Each sim is listed with its activity ranking, its name, the letter "A" in square brackets if it is Adult-rated and the number of avatars on it. The list can be navigated page by page with always ten sims on them. However, while it gets the information it shows directly from OpenSimWorld, it doesn't show any further information, not about the sim and not about whatever event may be on-going on any given sim. Clicking on a listed sim will immediately teleport you there, but it won't tell you what the place is where the beacon is taking you.
After a while of inactivity, the touch screen switches back into its idle mode.
Clicking the panel on the foot leaves a like on the entry of the sim.
The shadow of the tallest mountain pine on the left-hand side of the pathway is cast on the OpenSimWorld beacon.
All the way to the right, two leaves of an otherwise out-of-frame fern reach into the picture. Further above and in the background, the lower one of another pair of rocks appears with the higher one being to the right of it and hidden behind the trunk of a conifer.The background
Just right of the avatar's head in the picture, the paved path ends at the foot of a rock cliff which spans the whole width of the image. The cliff is about nine metres or thirty feet high. A narrower, rocky path leads to the right and upward from just right of the middle of the paved path to about 40 percent of the height of the cliff. Then, hidden behind the mountain pine tree to the right of the end of the paved path, it takes a sharp turn of roughly 180 degrees to the left and ascends to about 80 percent of the height of the cliff. Right above where the paved path ends, almost right above my avatar's head, the cliff path takes another sharp U-turn to the right and ascends in a fairly gentle slope until it reaches the top of the cliff about as far right as the first turn.
The cliff extends to both sides at a constant height, save for its jagged upper edge. On the left and within the borders of the image, it does so roughly parallel to the paved path. It surrounds a largely snow-covered plateau with more mountain pines and other conifers on it and Black White Castle itself.
To the left of the top of the second mountain pine from the centre, upward from the pair of rocks left of the paved path, the top right corner of Black White Castle's dark grey roof of unidentified material peeks through a gap between the trees. The whole rest of the building is either hidden behind the forest, outside the image borders or both.
Further in the background, snow-covered mountains rise high above the treetops. These are actually already outside the sim, reaching into regions with no sim running on them. A little bit of sky appears to the right of the mountains. It is clear, but true to the visual theme of the whole sim, it is deep grey.The final details
The camera is roughly at realistic eye height and oriented south-by-southwest-ward. The position of the Sun as the only directed light source in the picture is unusual for OpenSim, namely in the southeast. It is permanently fixed in this place because making one single setting for the sky is great deal easier than making settings for a whole day. But if it was moving, it would not do what it almost always does in OpenSim and pass through the zenith. Still, judging by the length of the tree shadows since the Sun is absent as an actual celestial body in the sky, it is too high up for winter.
Now, if you've made it all the way down here, I ask you: Which description is more accurate Which description is more detailed Which description is more informative Which description actually helps you understand the image
#Long #LongPost #CWLong #CWLongPost #BlackAndWhite #Monochrome #OpenSim #OpenSimulator #Metaverse #VirtualWorlds #AltText #ImageDescription #ImageDescriptions #ImageDescriptionMeta #CWImageDescriptionMeta #AI #LLaVA
und ein zum sind eingerichtet. und sind jetzt auch im verfgbar.
---
/ and a to the have been set up. and are now also available in -term monitoring.
Still as relevant as in 2021...
-still-here -lasting -changing
PRETTYGARDEN Women's Loose Solid Off Shoulder Elastic Waist Stretchy Long Romper Jumpsuit
Check Now Amazon=
Size Guide: S=US 4-6, M=US 8-10L=US 12-14XL=US 16-18 High Quality Stretchy And Soft Fabric Made The Dressy Jumpsuit Works With Most Body Types, And Provides You The Ultimate Comfy Wearing Experience.
Since I tend to give both a short description of the visuals of an image in the alt-text and a full, detailed description and explanation in the post itself, I might actually start giving full meme explanations on an even higher level of detail than KnowYourMeme because it's probably good style not to rely on external sources if it can be avoided somehow.
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #AltText #ImageDescription #ImageDescriptions #ImageDescriptionMeta #CWImageDescriptionMeta #Memes Wobei es ja auch da Aufteilungen gibt.
Misskey ist fr Japaner und die, die es gern wren.
Sharkey hat groe Zielgruppenberschneidungen mit Blhaj und Programmiersocken.
Hubzilla ist fr die Schmerzbefreiten, die sonst schon alles gesehen haben, featureschtige bergeeks und die Urgesteine, die schon immer auf Mikes Projekten unterwegs waren.
Und (streams), das eigentlich der ultimative Safe Haven sein knnte, wenn es denn jemand kannte, wird hauptschlich von denjenigen Spielkindern genutzt, denen es nur auf Hubzilla zu langweilig wird. hnlich wie damals die Red Matrix fr ein paar wenige Friendica-Nutzer. Aber solange der Totalumbau unter der Haube noch nicht abgeschlossen ist, ist das auch gut so.
#Long #LongPost #CWLong #CWLongPost #LangerPost #CWLangerPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #Misskey #Sharkey #Hubzilla #Streams #(streams) An sich ginge das theoretisch schon, allerdings mit Einschrnkungen und Besonderheiten.
Zunchst einmal: Die Dokumente, die kollaborativ bearbeitet werden knnten, wren keine Dateien, also nicht z. B. Word- oder ODF-Dokumente. Das wren im Prinzip Blogposts, die auch hnlich wie Blogposts in BBcode formatiert wren, nur da die nicht wie Posts an die eigenen Followers geschickt werden.
Man knnte die auch nicht isoliert ansehen, sondern nur in ihrer angestammten Umgebung mitsamt der ganzen UI drumherum. Als gesonderte Dokumente exportieren, z. B. als PDF, ginge auch nicht.
Dazu kme auch noch, da es so gesehen keinen zentralen Cloud-Speicher fr die Dokumente gbe. Irgendjemand mte so ein Dokument jeweils auf seinem Kanal (hnlich wie ein Mastodon-Konto) parken und dann diejenigen, die dieses Dokument bearbeiten drfen, hndisch freischalten.
Existierende Dokumente (Text, Word, ODF etc. oder auch PDF) knnen zwar in den Cloud-Speicher hochgeladen werden, aber nicht bearbeitet. Eine eingebaute Ansichtsfunktion gibt's meines Wissens auch nicht. Und diesen Cloud-Speicher gibt's eben einmal pro Kanal, aber nicht einmal zentral. Wenn man einen zentralen Speicher fr solche Sachen will, mu das ein eigener Kanal sein.
Alternativ zu einzelnen blogpostartigen Dokumenten knnte man auch Wikis anlegen, die natrlich eigene Vorzge htten, nmlich die Verlinkung von Seiten untereinander, also einfachere Navigation. Die knnen genauso kollaborativ bearbeitet werden, und die untersttzen neben BBcode wahlweise auch Markdown. Man kann sogar pro Kanal, also pro Nase, mehr als ein Wiki haben mit jeweils praktisch beliebig vielen Seiten.
Aber auch da gibt's nichts in der Art einer Druckansicht oder eines Export. Auerdem darf man sich zum einen daran gewhnen, da die Wikis eben nur BBcode und Markdown kennen, aber nicht die MediaWiki-Auszeichnungssprache. Und gerade Wikis sind im Grunde komplett undokumentiert, d. h. man darf sich da selbst reinfuchsen oder Hubzilla-Nutzer zu finden versuchen, die schon mal Wikis gemacht haben.
#Long #LongPost #CWLong #CWLongPost #Hubzilla Der Abschnitt "Update: Friendica posts in Mastodon" ist nicht nur sachlich falsch, sondern auch noch stark unvollstndig.
Ich als langjhriger Hubzilla-Nutzer mit Friendica-Vergangenheit wrde das eher so formulieren:
Update: Posts and comments from Friendica, Hubzilla and (streams) in Mastodon
Posts and comments coming into Mastodon from Friendica, Hubzilla and (streams) are special cases. That's because neither of them have Mastodon's dedicated CW field. Instead, they have reader-side content warnings that can optionally be created automatically. By default, a post is automatically hidden behind a content warning button if it contains "nsfw" and/or "sensitive".
Automatic reader-side content warnings have been part of the culture of both Friendica and Hubzilla since before Mastodon was even made as well as of fairly new (streams). Poster-side content warnings in a dedicated field have never been part of their culture, both because they've got a much better solution for content warnings and because they don't provide dedicated means for poster-side content warnings.
Technically speaking, Hubzilla and (streams) do have Mastodon's CW field. But unlike Mastodon, it isn't labelled "CW". It's labelled "summary". It has been a summary field originally, but since a hard-coded maximum of 500 characters doesn't require summaries, Mastodon repurposed that field for content warnings. Hubzilla and (streams) have no character limits at all, so using that field for summaries is still justified.
Hence, Hubzilla and (streams) users use this field for short summaries for very long posts, if at all, but not for content warnings.
Also, just like Friendica, both Hubzilla and (streams) have a conversation model like Facebook or Tumblr or blogs with only one post and many comments. All replies are comments, and there is a separate, dedicated entry form for comments under each post. This entry form does not, however, have a summary field because what sense does it make to give a summary for a blog comment
Hence, Hubzilla and (streams) users can't put Mastodon-style content warnings on replies at all. Also, neither Hubzilla nor (streams) can re-use content warnings from posts or comments they reply to.
Friendica, the oldest one of the three, doesn't even have a dedicated summary field. The only way to add a summary, i.e. a Mastodon-style CW, is between the Friendica-specific BBcode tag pair
abstract/abstract. This works in both posts and comments, but the availability of this tag pair is neither advertised in the post editor nor in the comment editor.Since Friendica doesn't have a dedicated UI element for Mastodon-style CWs, neither for posts nor for comments, most Friendica users don't give Mastodon-style CWs at all because they simply don't know that this is possible in the first place, much less how.
Also, users of Friendica, Hubzilla and (streams) tend to find the idea of writing a content warning between a pair of obscure BBcode tags (Friendica) or into the summary field (Hubzilla, (streams)) ridiculous. Trying to convince them otherwise would be like trying to convince Mastodon users to double their CWs with keywords or hashtags to trigger the NSFW content-warning generation on non-Mastodon projects.
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #CW #CWs #ContentWarning #ContentWarnings #ContentWarningMeta #Friendica #Hubzilla #Streams #(streams) Add your location to a Google Map It's fair to mention at this point that hashtags aren't only ever used to increase visibility. They're also used to trigger the automated generation of reader-side content warnings.
Yes, they exist. Not only does Mastodon itself have that feature since version 4.0 from last year. But Mistpark had it as early as 2010, almost six years before Mastodon existed. And unlike Mastodon, it did not repurpose the summary field for content warnings.
From Mistpark emerged today's Friendica, Hubzilla and (streams). All three have this feature. All three don't have Mastodon's CW field Hubzilla and (streams) still call it "summary" while Friendica lacks it altogether. At least Hubzilla and (streams) don't provide any means of adding a Mastodon CW to replies at all.
And all three have had it in their cultures since they were launched to have CWs automatically generated individually for each reader by the "NSFW app".
I am on Hubzilla, and I will not adjust my way of using it so that it becomes indistinguishable from posts on vanilla Mastodon by someone who only knows Mastodon.
I will add 12 hashtags to this comment. The first four are to trigger filters that either remove or CW my posts and comments with over 500 characters because long posts disturb many Mastodon users. The next four are to trigger filters that either remove or CW my posts and comments about the Fediverse because many Mastodon users don't want to see that technical mumbo-jumbo.
Yes, four of each. How am I supposed to know who uses which one of these in their filters
The next two are for discoverability purposes. The last two are for triggering filters again.
So that's two discoverability hashtags and ten filter-triggering hashtags.
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #Hashtag #Hashtags #HashtagMeta #CWHashtagMeta
Also, the reasoning "not in ActivityPub" is well, Mastodon is as guilty of that since the discussions of AP started. Since Mastodon was successful in positioning itself at the proper place, everyone ended up / was forced to implement Mastodon-only stuff just so their software will be interoperable with it, even though it isn't part of ActivityPub.
It seems like the loudest voices on Mastodon are amongst those who don't know anything about ActivityPub and the Fediverse even though they think and claim they do.
A lot of what comes from them is based on the assumption that the Fediverse started with Mastodon, Eugen Rochko invented ActivityPub as the base protocol for Mastodon, and therefore, Mastodon is 100% fully ActivityPub-compliant because Mastodon itself is the very definition of ActivityPub and the gold standard of ActivityPub. Some even seem convinced that all this happened in spring of 2022 because they hadn't heard of Mastodon before then.
Well, and everything that doesn't work perfectly with Mastodon and/or doesn't support all features that Mastodon has the Mastodon way, as well as everything that has features that go beyond Mastodon, is not ActivityPub-compliant and therefore broken.
A while ago, someone absolutely unironically and seriously tried to convince me that Mastodon is the only "feature-complete" Fediverse project. I was about to rattle down a list of Hubzilla features and ask him whether Mastodon has them. Unfortunately, I couldn't demonstrate them to him because that was in Mastodon 3 days when Mastodon users couldn't even see text formatting.
It's nigh-impossible to convince the hard fans and purists of the truth.
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #Mastodon #ActivityPub
L'Htel de Ville, Long, Environs d'Abbeville, c.1910 - Edition Cally CPA
Mastodon doesn't really have a conversation model at all. It doesn't know what a conversation is because such a thing doesn't exist on Twitter either. The same goes for Pleroma, Misskey and all their forks.Threads on these projects are loosely tied together from single posts. Any post, regardless of whether it's a reply or not, only goes out to the followers of the poster plus whomever the post mentions.
If Alice posts something, it's her followers and the users mentioned in the post. who are notified about it.
If Bob replies to Alice's post, it's his followers and the users whom he mentions who are notified about it. Alice's followers are not notified unless Bob mentions them one by one. In fact, not even Alice would be notified if Bob didn't mention her.
As far as I know, before nodeBB appeared, there were only a few Fediverse projects that had a concept of conversations:
- Mistpark/Friendika/Friendica
- Free Friendika (fork of Friendika defunct)
- Friendica Red/Red/the Red Matrix/Hubzilla
- Osada (first a fork of Hubzilla, then a fork of Zap, then probably a fork of Zap again all discontinued)
- Zap (fork of the first Osada discontinued)
- Mistpark 2020 (probably fork of Zap or the third Osada discontinued)
- Redmatrix 2020 (probably fork of Zap, the third Osada or Mistpark 2020 discontinued)
- Roadhouse (fork of the third Osada/Mistpark 2020/Redmatrix 2020 discontinued)
- the Streams repository (fork of Roadhouse)
What is now Friendica was not designed as an alternative to Twitter. It was designed as an alternative to Facebook. And so it as a thread structure like Facebook or Tumblr or a blog: exactly one post plus many comments.
Again, if Alice posts something, it's her followers and the users mentioned in the post. who are notified about it.
But if Bob replies to Alice's post, it's a comment on Alice's post and not a stand-alone post itself. Next to whomever Bob mentions, it's Alice and Alice's followers who are notified. Bob's followers are not notified unless they're mentioned because it's none of their business what Bob comments on Alice's post. And Alice is notified even without a mention, as are her followers.
If Carol comments on Bob's comment, apart from whomever Carol mentions, it's Alice, Alice's followers and Bob who are notified. Again, Carol does not have to mention Alice or Alice's followers or Bob. And again, Carol's followers are not notified, neither are Bob's followers.
By sending the post, Alice automatically follows the thread which this post starts. Thus, she receives special notifications for each comment. Likewise, by commenting, both Bob and Carol subscribe to the thread, follow it and receive special notifications for each new comment, regardless of what within the thread is commented on.
Also, Alice, Bob and Carol have the thread in their respective streams anyway. So even if they unsubscribe from the thread, they still get the same notifications for comments as they get for comments on posts from whomever they follow.
By the way, it's only what Friendica, Hubzilla and (streams) perceive as posts that is drawn into a stream and listed as unread. So even if you follow Bob or Carol, but not Alice, Bob's and Carol's comments don't show up in your stream.
Lastly, it's Alice who owns the whole thread. Including all comments. At least on Hubzilla and (streams), Alice can moderate her own thread and delete posts from it unfortunately, that deletion is not forwarded to originally ActivityPub-based projects such as Mastodon which don't understand such measures. And self-moderation on (streams) can go even further than on Hubzilla.
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #Friendica #Hubzilla #Streams #(streams)
Hello !
This will be my . I look forward to posting my and other related things. I also look forward to new . I am mainly into and but I also listen to . I started music roughly about 2010 but took a from everything. I like to in my downtime or surf the Internet. I studied and . I have a background in and .
on
Theres no question that we have tried to put together a group far away from the day to day political debates, of people who may have constituencies but no longer have to get elected.
They are able to discuss things privately and come up with solutions.
It is very undemocratic in a classic sense in that it is elitist.
But its not like our group suddenly has superpowers and we can do whatever we want.
All we can do is have the power to suggest.
Thats all we have.
Type of image
I usually write something like "digital rendering from within a 3-D virtual world, generated using shaders, but without ray-tracing" in the full description which goes into the post.
, however, I only added the part before the first comma to the alt-text and forgot the details after the first comma. I hope I'll remember to do better next time, especially seeing as I still had lots of room in the alt-text.
Text
Most of the time, I transcribe all text anywhere in the image absolutely verbatim down to every last spelling mistake. ought to be a good example. I even include text that's
list
But I just remembered that I got sloppy last time (see Type of image for a link). I didn't mention that the room numbers and the "Office" label are written on the doors of the motel on the advertising poster, let alone in which typeface and colour, and I neither described the license plate hanging above the office door, nor did I transcribe anything on it. I guess I wanted to get this over with. For the same reason, I omitted to describe what can be seen through the open blinds inside some of the motel rooms.
Who is in the image
Since my pictures always come from places that probably nobody who reads this knows exist, namely very obscure virtual worlds, I have to mention who the avatars in an image are, if any, explain who they are and describe in detail what they look like and what they wear.
Also because of this, it's always only myself and maybe also my in-world sister Juno Rowland who is in the pictures. It'd be too much of an effort to document the identities and looks of two dozen avatars in a party picture and research and explain who they are and what they do. Besides, chances are that some of them teleport out between me taking the main picture and me getting to identify them and take detail pictures for the description.
Setting of the image
This really takes up a whole lot of characters when I write an image description. It definitely only ever goes into the detailed description in the post, never into the alt-text, also because there's no room for it in alt-text anymore. The last time (again, see Type of image for a link), it took me almost 2,300 characters to explain where the image was made, 800 characters or over 50% more than what fits into alt-text on Mastodon, Misskey and their mutual forks.
But I have to write that much because, again, nobody knows the place where the image is from. So I have to write at which location the image was taken, on which sim, in which grid, in OpenSim, what OpenSim is, what Second Life is, what a grid is, why it's called a grid, what a region is, what a sim is, what a varsim is if necessary, what this specific grid is, what this specific sim is and maybe even what this specific place is. Last time I stopped just short of explaining who Edgar Wallace was because that would have been important for non-German and/or too young readers to understand the name of the location.
Color(s)
I try to remember to mention the colour of everything I describe, usually down to the hue. Okay, it was easy last time because it was a picture of a monochrome avatar in a fully monochrome location, save for some very slightly blu-ish or teal-ish hues on the OpenSimWorld beacon which are barely visible in the image, if at all.
Expression and emotions
Pass. That's because I quit showing human or otherwise variable faces in my images. And that, in turn, is because there's absolutely no way to hide them from Mastodon users, and some autistic Mastodon users must have such images concealed from them due to the danger of being triggered by eye contact.
But even if I showed faces: Avatar faces are mostly expressionless because it takes special animations triggered either by hand or by script for them to show an expression for a few seconds. So there wouldn't be anything specific to describe.
Item locations and descriptions
I usually go from the foreground to the background, unless the actual background dominates everything (see my second link) in which case I'll start with that. From top to bottom doesn't always make sense the last time, I would have started with mostly feature-less and completely unimportant off-sim mountains and the sky and then continued with the trees from left to right, jumping back and forth between trees farther in the back and trees farther up front.
Otherwise, if at all possible, I describe everything I can that's at least partly in the image and not fully concealed by something in full detail. I mean, my images consist entirely of stuff that next to nobody has ever come across. And people, including blind or visually-impaired people, might be curious. Besides, regardless whether someone is sighted or not, they might still need extensive explanations to understand certain elements in the image.
Still, it often happens to me that I realise after posting a described image that I've skimped on certain details too much. I think the only time I was halfway satisfied was with almost precisely 40,000 characters for one individual image plus over 1,300 characters for the preamble for both images. It would have been much longer, however, if I had transcribed repeating bits of text and described repeating fabric textures whenever they occurred.
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #AltText #ImageDescription #ImageDescriptions #ImageDescriptionMeta #CWImageDescriptionMeta
But I'd have to be 100% certain that the tutorial will be absolutely guaranteed to work.
I can't guarantee that. I barely have any experience with male mesh bodies from SL, even less with male BoM mesh bodies from SL. I simply don't use them.
The body I use was made in OpenSim for OpenSim. It works a whole lot differently from all the SL bodies in OpenSim. And it's way too difficult for a complete novice to use, also because there's next to no clothing specifically made for that body.
What I can do is tell you where to get what. But I can't teach you how to use it. I can't walk you through setting everything up. Because I don't know any of that stuff.
Teleport to Nutella (hg.osgrid.org:80:Nutella).
Take a landmark.
Go to the Head & Body Shop (ca. 298, 240).
Pick up the following boxes:
- SIGNATURE Gianni Bento Mesh Body BOM
(body) - Lelutka Bento BoM Mesh Head Kane 2.0 Boxed
(head) - Bento BoM Mesh Head Thor 2.0 Boxed
(another head) - Lelutka Bento BoM Mesh Head Skyler 2.0 Boxed
(another head) - Lelutka Bento BoM Mesh Head Luka 2.0 Boxed
(another head) - BoM Stuff Skin Man
(skins to get you started) - BoM Male Hairbase 52 Starter Pack Boxed
(hairbase tattoos you might need them)
Pick up some hair you like.
Next, go to SilverFox Designs Mall (kishaki.de:8002:SilverFox Designs Mall).
Take a landmark.
Enter the mall building through the black door.
Go to the right.
Here you will find clothes stores.
Now you've got a body, a few heads to try out + shapes + eyes + beards, some skins, some hair and some clothes and shoes.
But from then on, you're on your own. I can't tell you how this body and these heads etc. exactly work.
DISCLAIMER: This is untested!
#Long #LongPost #CWLong #CWLongPost
is there tutorial somewhere.
Nope. Everyone's expected to already know everything from SL.
No it is harder than SL because in SL for cloth that need alpha they include alpha in the pack or you have cloth per type of body but here I try a shop and my wonderfull works is a disaster
It's here where SL is different from OpenSim.
See, when mesh bodies were first introduced in the 2010s, alpha masks had no effect on them. That was long before BoM. In fact, you needed a whole-avatar alpha mask to hide the system body. In order to still make it possible to hide parts of the body, it was cut up into 200+ little pieces, and it was given a HUD with which you can make each one of these pieces invisible and visible again.
Alpha cuts and the alpha HUD were meant to be a hack, but both SL and OpenSim users saw them as an advancement over alpha masks. Newer and more technologically advanced = better, and everything else = old = obsolete = bad.
When BoM came, it was suddenly possible to hide parts of the mesh body with alpha masks. In theory. In practice, this pretty much only became the case in SL. Body makers sewed their mesh bodies back together, did away with the alpha HUDs and advertised their bodies as more lightweight in mesh (because there no longer were 200+ submeshes) and scripting (because hide/show scripts were only necessary for female feet anymore). And clothesmakers included alpha masks with their clothes if they could be worn with BoM bodies.
This never happened in OpenSim. OpenSim still has that "alpha masks = old obsolete crap" attitude.
That's partly because those who offer mesh bodies can't possibly convince the users that this "old obsolete crap" is the new hot shit again, also because 99% of all OpenSim users think BoM is only a glorified skin and make-up applier.
And it's partly for another reason: From 2020 to 2022, there seemed to be exactly two BoM bodies in OpenSim: Athena 6 (stolen Maitreya Lara with basic BoM support glued on by the importers) and Adonis 4 (Slink Physique Male with basic BoM support glued on by the same importers). Both of them do not (properly) support alpha masks because their alpha modes are botched.
Hardly anyone noticed because both still have their alpha cuts and alpha HUDs, so hardly anyone even tried to put an alpha mask on them. Those who did failed, and the verdict was "BoM doesn't support alpha masks in OpenSim" even though Ruth2 v4 and Roth2 v2 do support and actually rely on alpha masks.
So when more mesh bodies came in more recently without being renamed (eBody Reborn, Legacy, Legacy Perky, a newer version of Signature Gianni etc.), I think it was the variants with alpha cuts and alpha HUDs that were imported. That's what people were used to.
Older mesh clothes from SL usually don't have any alpha masks because a) they were imported in times when there was no BoM, and b) they were imported to be worn with mesh bodies.
The moment that Maitreya Lara was imported and eventually renamed Athena, nobody added alpha masks to female mesh clothing anymore. The moment that Slink Physique Male was imported and renamed Adonis, nobody added alpha masks to male mesh clothing anymore. Also because whoever already wore mesh clothing was expected to switch to one of the stolen mesh bodies anyway.
The association of clothes with bodies is another issue.
Back in the 2010s, Athena was even more of a standard in OpenSim than Maitreya Lara was in Second Life. Athena was the only mesh body that mattered. So it was deemed completely unnecessary to mention that mesh clothes are "rigged for Athena" when they were. After all, nobody imported any clothes for Belleza Freya or Belleza Venus, both of which were imported to OpenSim, too.
Almost the only exception were Decadence clothes (with the black bar on the left of the box) after stolen copies of Slink Physique Hourglass spread (BBHG, Decadence-HG, Je'Thai Hourglass) from then on, at least HG clothes were labelled as such.
So if there was no body compatibility mentioned on female clothing, it felt only natural to do away with it on male clothing as well.
The problem was that there wasn't that one standard male body. Adonis (actually Slink Physique Male) was there first. But not much later came Apollo and Decadence Male (both actually Signature Gianni), and another bit later came Ares (actually Belleza Jake).
Some importers could be bothered to write onto clothes what they were compatible with, but usually only if they offered clothes for multiple bodies. Even that wasn't consistent. Some importers didn't rename what they had imported at all, so you find the SL body names on old clothes rather than the OpenSim body names.
Then there were those who considered Adonis the male standard in OpenSim because it appeared to be the most widespread. I think most of the clothes with the Sacrarium logo on them are imported Slink Physique Male clothes. They usually don't mention what body they're for, also because Adonis was the only body which the "copybotting mafiya" kept maintaining.
Decadence, having its "own" body Decadence Male, probably only supported that body and Apollo along with it by only importing clothes made for Signature Gianni. But supporting only one body also meant that there was "no need" to write body names on the clothes or the boxes.
It's only now that the number of SL bodies available in OpenSim is increasing that the importers start putting body names on their clothes again, both female and male. That is, if something for male avatars has been imported only recently, and there's no body name on it, you can be certain it's for Signature Gianni (= Apollo = Decadence Male).
#Long #LongPost #CWLong #CWLongPost
I did a little bit of searching and I discovered the sim youre in is a open source (fork) of Second Life which is really coolIm definitely checking it out.
Not a fork. Second Life is still closed-source server-side.
It was a case of Second Life open-sourcing its official viewer in 2006. Thus, the API lay open. Third-party viewers were developed against that API. And then someone had the idea to develop a Second Life-like server application against the API from the other side.
, by the way.
But what are the cubes
One quite particular feature of both Second Life and OpenSim is that you can store any and all kinds of in-world content in objects. This can be used for various things, for example, you can put scripts into doors to animate them, or you can build teleporters by putting a teleport script into an object, or you can build sound emitters that way.
But this can also be used to sell content to avatars, be it for money, be it for free. You put that content into a box, decorate the box and set the box up so that clicking it either gives you the box including contents or an inventory folder with the contents inside. Or you configure the box so that avatars can copy the box into their inventories.
This way, avatars can pick up more than one item at once. It's one thing to pick 16 Christmas wreaths from a wall one by one, but it's another to get a box with all 16 inside it.
Selea Core made a whole lot of sim decoration boxes many years ago. Coincidentally, most of them are actually cubes.
#Long #LongPost #CWLong #CWLongPost #OpenSim #OpenSimulator #Metaverse #VirtualWorldsphanisvara (streams)
ich bin mittlerweile wieder bei hubzilla / streams angekommen und fhle mich hier wesentlich wohler.
Zumal Content Warnings hier ganz anders funktionieren. Und zwar werden sie a) optional und b) auf der Seite des Lesers generiert und nicht auf der Seite des Posters geschrieben und allen aufgedrckt.
Ein Feature, das (streams) auf Umwegen von Hubzilla geerbt hat und Hubzilla auf etwas krzeren Umwegen von Mistpark. Das ist also wahrscheinlich schon von 2010.
Mastodon hat das jetzt auch, aber erst seit 2023. Auerdem drften die allermeisten Mastodon-Nutzer gar nicht wissen, da es das kann, und den meisten derer, die es wissen, ist es zu kompliziert.
da nicht alles berall hin ausposaunt wird, bekommst du auch nicht so leicht tausende followers, doch das war noch nie mein bestreben.
Ich bin auch wieder knapp vor der 500-Connections-Marke. Aber ich bin auf ActivityPub und Mastodon angewiesen, weil die Zielgruppen sowohl des Primrthemas als auch des Sekundrthemas dieses Kanals fast ausschlielich auf Mastodon sind.
Blderweise breiten sich meine Posts und Kommentare dadurch auch auf den fderierten Timelines vieler Mastodon-Instanzen aus. Und da sitzen dann die Empfindlichen, die nichts sehen wollen, was sie strt. Dazu zhlt auch alles, was Vanilla-Mastodon 3.x nicht auch konnte. Praktisch keiner von denen kann Filter bedienen.
Da habe ich dann meine liebe Not damit, von jedem meiner Posts die Vorschau in einen Texteditor zu copypasten, um die Zeichen zu zhlen, und wenn's ber 500 Zeichen geht, eine Content Warning fr einen langen Post dranzubauen inklusive Anzahl der Zeichen. Plus alle mglichen anderen Content Warnings. Inklusive Fediverse-Meta, wenn ich irgendwas irgendwie bers Fediverse schreibe, weil es Leute gibt. Ich habe inzwischen eine Liste mit ca. 90 Dingen, die Leute geCWt sehen wollen, und da ist Aufdrselung in landesspezifische Politik noch gar nicht eingerechnet.
Und wenn ich wie jetzt einen Kommentar schreibe (Nutzer von Mastodon, Pleroma nebst Forks, Misskey nebst Forks etc., die das lesen: Hier auf Hubzilla ist eine Antwort kein Post, sondern ein Kommentar mit eigenem Eingabefeld und etwas vllig anderes als ein Post), rechne ich auch immer mit Rffeln oder gar Sperren, weil ich keine CW angebe. Weil ich das gar nicht kann. Und Mastodon-Nutzern in einem einzigen Kommentar mit maximal 500 Zeichen beizupulen, warum das so ist, ist aussichtslos. Geschweige denn, ihnen zu erklren, warum ich dann auch noch ein Dutzend Hashtags unter den "Post" hnge.
Bilder mit Augenkontakt versuche ich gar komplett zu vermeiden. Wenn das nicht geht und der Augenkontakt zu offensichtlich ist, also die Augen nicht jeweils nur einen winzigen Bruchteil eines Pixel klein, dann packe ich das Bild detaillierter Bildbeschreibung in einen Artikel, und zwar inklusive kurzer Bildbeschreibung im Alt-Text und detaillierter Bildbeschreibung im Artikel, und verlinke den Artikel im Post.
Von Hubzilla aus habe ich im Gegensatz zu (streams) absolut keine Chance, Bilder in Posts auf Mastodon ausblenden zu lassen. Gar keine. Auf Friendica, Hubzilla oder (streams) kann ich die Leute bis zu viermal klicken lassen, bevor sie das Bild sehen. Erst auf die Content Warning, wenn sie NSFW an haben. Dann auf das Summary. Dann auf den Spoiler-Tag. Dann auf das verschwommene Bild selbst. Aber exakt dasselbe Bild in exakt demselben Post wird auf Mastodon jedem sofort ohne Warnung ins Gesicht geschmissen. Nur weil Mastodon keinen Bock hat, sich an irgendwelche Standards zu halten oder auch nur das Einbetten von Bildern in Posts zu untersttzen, weil Twitter das ja auch nicht kann.
CC:
#Long #LongPost #CWLong #CWLongPost #LangerPost #CWLangerPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #Mastodon #Friendica #Hubzilla #Streams #(streams) #CW #CWs #ContentWarning #ContentWarnings #CWMeta #ContentWarningMetaSo I've been collecting Selea Core boxes for a few years now. I've got the same goal as a number of people before me, namely for someone to have all Selea Core boxes in one store one day.
I thought my collection was extensive already. But then I found out that Star Ravenhurst has a collection she built from at least one source that I hadn't visited yet. She has fixed and reworked what needed to be fixed and reworked, and now she offers these boxes at in the Genesis Roleplay Grid.
Finding this out was what finally drove me to create a spreadsheet with the boxes I have, including additions, plus the boxes she and Lavia Lavine have.
Turned out she has 63 boxes that I don't have. But I have ca. 57 boxes from various sources that I can send her because she either hasn't got them yet, or they may contain stuff that she hasn't got yet.
All in all, I've catalogued 284 boxes currently, but some of those in my possession seem like they were recompiled or renamed. And I know there have to be even more boxes somewhere out there.
#Long #LongPost #CWLong #CWLongPost #OpenSim #OpenSimulator #Metaverse #VirtualWorlds #SeleaCore #GenesisRoleplayGrid Essentially, Mike Macgirvin (creator of the now-defunct DFRN protocol, , the Zot protocol and , inventor of and creator and maintainer of both the Nomad protocol and ) is redesigning (streams)' conversation model into something that's more compatible with ActivityPub and easier to understand for projects built against the ActivityPub protocol.
It's called Conversation Containers.
If you can take a lot of technobabble: .
It's worth mentioning at this point that (streams) is not based on ActivityPub itself. It's based on an advanced version of the Zot protocol named Nomad, and it only supports ActivityPub as an optional secondary protocol.
CC:
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #ActivityPub #Streams #(streams)On the one hand, FediGroups is kind of lacking from a Hubzilla/(streams) POV. Forums on Hubzilla and (streams) can be made fully private, i.e. nobody from outside the forum can even read them. Not possible on FediGroups because not possible on Mastodon, not to mention that it'd be somewhat inconvenient without server-side OpenWebAuth support.
Also, it's not only possible for Hubzilla and (streams) users to post to Hubzilla and (streams) forums without also posting to their own connections, it's standard. Hubzilla and (streams) forums only forward posts to their connections that come in as direct messages. This does not apply to comments, only to posts.
The same thing is impossible with FediGroups because it rejects direct messages outright.
On the other hand, both features make Hubzilla and (streams) forums harder to use for Mastodon users as they want to use everything in the Fediverse as if it's all Mastodon. Even if a forum is configured to be read by any logged-in user, Hubzilla and (streams) don't recognise logged-in Mastodon users because Mastodon still doesn't have client-side OpenWebAuth support either.
And the very reason why Hubzilla and (streams) forums are being perceived as incompatible with Mastodon is because it's too inconvenient for Mastodon users to start threads on them. I'm not even sure if this has been tested because there's no documentation on this.
Either Mastodon users have to send a DM to the forum which is completely unnatural to Mastodon users who are used to
!, the Hubzilla/(streams) prefix for DMs, which is completely unknown and completely alien to Mastodon, not to mention completely unsupported.That said, there are even more shortcomings from a Hubzilla/(streams) POV.
It's impossible to make threads with titles because Mastodon doesn't support titles on Note objects. By the way, this might hit the Friendica crowd hard: FediGroups won't work with posts from Friendica with titles because these go out as Article objects (like blog posts) instead of Note objects (like Mastodon toots), and I'm not sure how FediGroups will handle Article objects.
Generally, it seems a crazy idea to build groups on top of something that not only doesn't have a concept of groups, but that doesn't have a concept of conversations either. But then again, at least two thirds of the Fediverse don't have a concept of conversations. Users of these two thirds can only follow threads if everyone in that thread keeps mentioning them in every last post. At least on Hubzilla and (streams), this is completely unnecessary.
Moderation will be unnecessarily difficult because Mastodon also doesn't have a concept of permissions beyond Mute and Block, and because all replies to posts are posts themselves and exclusively owned by whoever posts them and thus can't be moderated by the thread starter.
Also, FediGroups are so far the only "groups" in the Fediverse that don't present themselves as Group actors. Thus, they're the only ones which Hubzilla and (streams) don't list as forums. Even Guppe groups are listed as forums on Hubzilla and probably also on (streams). This can only change if FediGroups actually soft-forks Mastodon and at least adds Group actor identification, no matter how much of Mastodon's code will have to be changed for that.
I'll be honest: I hope that when the redesign of conversations on (streams) goes stable, it'll become a good base for Fediverse-wide forums, even for Mastodon users who think the Fediverse is only Mastodon and for notoriously stubborn Misskey plus Forkeys.
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #Mastodon #Hubzilla #Streams #(streams) #Groups #Forums #FediGroups
'I own this branch'
-tailed
I still remember when cryptobros tried to make everyone believe that The Metaverse (or metaverses in general) absolutely require a blockchain, a cryptocurrency and NFTs, and that 3-D virtual worlds are technologically impossible without any of these three.The irony is that it's the worlds without these three that actually work, even decidedly non-commercial Overte. The cryptobros' get-rich-quick schemes ended up underdeveloped (NeosVR) at best, likely even buggy (Decentraland), and I guess not exactly few sold expensive NFTs as tokens to virtual land which never came to exist because they've never launched their world in the first place.
It's hard to tell whether they were cases of intentional fraud, and the owners never intended to develop and launch a virtual world in the first place, or whether they did want to launch a virtual world, but their cryptocurrency crashed before they could fund the development.
I mean, I find it increasingly hard to believe that the makers of Decentraland really knew nothing about virtual worlds first. I find it more likely meanwhile that they intentionally lied to their customers about having created the world's first decentralised metaverse than that they simply didn't know that this title belongs to something that's eleven years older and actually decentralised.
By the way, there have even been cryptobros who obviously could be bothered to spend a bit more time on Google, and who discovered OpenSim. Free and open-source. Most importantly, free-of-charge. And readily available, they wouldn't have to pay for the development of a virtual world platform first. So they decided to glue a blockchain and a cryptocurrency onto OpenSim and either sell land for crypto or offer crypto gambling or both.
None of this came to fruition. Regardless of whether they were dumb enough to open their grid to the Hypergrid, they had to compete with grids that offer standard Second Life regions for $10/month and varsims for not much more. On top of that, closed grids had to compete with the Hypergrid which had a lot more and better content, not to mention more users.
Oh, and OpenSim doesn't really work with VR headsets for a whole bunch of reasons, so they couldn't market it to the VR crowd either.
#Long #LongPost #CWLong #CWLongPost #Metaverse #Blockchain #Blockchains #Crypto #Cryptocurrency #Cryptocurrencies #NFT #NFTs #Cryptobros #Decentraland #NeosVR #OpenSim #OpenSimulator #VirtualWorlds I'm on Hubzilla which works vastly different from Mastodon. Also, I don't automatically accept new contacts. But here on Hubzilla, when I allow someone to follow me, I automatically "follow them back" (only that I usually don't actually let their posts in). Followers and followed aren't separate here they're all contacts or connections.
So if I unfollow someone, I also stop sending them my own posts, thus disallowing them to follow me.
I only go through my contacts list every few months to try and check who actually still follows me, usually by going through their own follower lists, and to remove dead contacts which I can identify through delivery reports.
I myself very rarely follow someone because I already follow just about everyone everywhere in the Fediverse who is into the primary topic of my channel. And I never start following users who don't write about this primary topic. I don't want masses of Twitter-like noise on my stream.
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #Hubzilla #Followers #Followed #Contacts #Connections
Northern lights over Lake Inari Lappland Finnland by Matthias Dengler www.matthiasdengler.com
Hubzilla-Hppchen: DirektnachrichtenDirektnachrichten sind Nachrichten, die an eine oder mehrere Einzelverbindungen adressiert sind. Sie sind ber den Netzwerkstream zugnglich. Ein Filter fr Direktnachrichten wurde dem Stream-Filter-Widget fr den schnellen Zugriff hinzugefgt.
Mchte man eine Direktnachricht an einen (oder mehrere) andere Nutzer versenden (Direktnachrichten knnen nur von den Adressaten und vom Versender gelesen werden), so verfasst man einen normalen Beitrag und adressiert diesen per spezieller Erwhnung ausschlielich an den / die Empfnger. Dies geschieht mit der privaten Erwhnung (Privacy-Tag). Ein Privacy-Tag ist ein Name, dem die beiden Zeichen ! vorangestellt sind und der zustzlich zur Markierung dieser Kanle auch die Datenschutzberechtigungen des Beitrags so ndert, dass nur diese bercksichtigt werden.
Zum Anzeigen kann man die DN im Stream filtern.
Um auf eine DN auch wieder "privat", also als DN zu antworten, muss man kein Privacy-Tag nutzen. Man antwortet einfach direkt auf die eingegangene DN.
Alternativ zum Privacy-Tag kann man auch Kanle oder Privacygruppen aus dem Privacy-Tool auswhlen. Dies ist der umstndlichere Weg, der aber auch funktioniert. Die Nutzung eines Privacy-Tags berschreibt allerdings eine ggf. getroffene Auswahl im Privacy-Tool. Schreibt man also einen Beitrag, der als Direktnachricht verschickt werden soll, kann man den Privacy-Tag weglassen und stattdessen auf das Vorhangschloss-Symbol neben dem Button "Teilen" klicken, so dass man in die Berechtigungs-Einstellungen gelangt.
Dort whlt man dann den Punkt "Benutzerdefiniert" und kann anschlieend dem gewnschten Adressaten die notzwendige Berechtigung einrumen.
Die so abgeschickte DN erscheint dann beim Adressaten, ist fr andere aber nicht sichtbar.
Mit dem Versionssprung von 4.6 auf 5.x wurde die ursprngliche Mail-Funktionalitt deaktiviert, weil es im neuen zot6-Protokoll kein Konzept fr private Mails mehr gibt. Die alte Mail-Funktionalitt konnte, sofern sie noch bentigt wurde, mit der Mail-App, die als Addon angeboten wurde, aktiviert werden. Die App ist inzwischen auch eingestellt worden.
Das Konzept des Mail-Versands wurde durch Direktnachrichten (DN) ersetzt. #FediTips #FediverseTips #hubzilla #hubzillahppchen
#Long #LongPost #CWLong #CWLongPost
Direktnachrichten sind Nachrichten, die an eine oder mehrere Einzelverbindungen adressiert sind. Sie sind ber den Netzwerkstream zugnglich. Ein Filter fr Direktnachrichten wurde dem Stream-Filter-Widget fr den schnellen Zugriff hinzugefgt.
Mchte man eine Direktnachricht an einen (oder mehrere) andere Nutzer versenden (Direktnachrichten knnen nur von den Adressaten und vom Versender gelesen werden), so verfasst man einen normalen Beitrag und adressiert diesen per spezieller Erwhnung ausschlielich an den / die Empfnger. Dies geschieht mit der privaten Erwhnung (Privacy-Tag). Ein Privacy-Tag ist ein Name, dem die beiden Zeichen ! vorangestellt sind und der zustzlich zur Markierung dieser Kanle auch die Datenschutzberechtigungen des Beitrags so ndert, dass nur diese bercksichtigt werden.
Zum Anzeigen kann man die DN im Stream filtern.
Um auf eine DN auch wieder "privat", also als DN zu antworten, muss man kein Privacy-Tag nutzen. Man antwortet einfach direkt auf die eingegangene DN.
Alternativ zum Privacy-Tag kann man auch Kanle oder Privacygruppen aus dem Privacy-Tool auswhlen. Dies ist der umstndlichere Weg, der aber auch funktioniert. Die Nutzung eines Privacy-Tags berschreibt allerdings eine ggf. getroffene Auswahl im Privacy-Tool. Schreibt man also einen Beitrag, der als Direktnachricht verschickt werden soll, kann man den Privacy-Tag weglassen und stattdessen auf das Vorhangschloss-Symbol neben dem Button "Teilen" klicken, so dass man in die Berechtigungs-Einstellungen gelangt.
Dort whlt man dann den Punkt "Benutzerdefiniert" und kann anschlieend dem gewnschten Adressaten die notzwendige Berechtigung einrumen.
Die so abgeschickte DN erscheint dann beim Adressaten, ist fr andere aber nicht sichtbar.
Mit dem Versionssprung von 4.6 auf 5.x wurde die ursprngliche Mail-Funktionalitt deaktiviert, weil es im neuen zot6-Protokoll kein Konzept fr private Mails mehr gibt. Die alte Mail-Funktionalitt konnte, sofern sie noch bentigt wurde, mit der Mail-App, die als Addon angeboten wurde, aktiviert werden. Die App ist inzwischen auch eingestellt worden.
Das Konzept des Mail-Versands wurde durch Direktnachrichten (DN) ersetzt. #FediTips #FediverseTips #hubzilla #hubzillahppchen
#Long #LongPost #CWLong #CWLongPostMchte man Inhalte (z.B. Dateien aus der Cloud) fr bestimmte Personen zugreifbar machen, obwohl diese ber keinen Hubzilla-Account verfgen, aber ansonsten nicht fr die ffentlichkeit, so arbeitet man mit Gastzugngen.
Wer mit einem solchen Gastzugang eingeloggt ist, kann alles sehen, was ffentlich zugnglich ist und zustzlich alles, was der Zuteiler des Gastzugangs fr diesen speziellen Gastzugang freigegeben hat.
Angenommen wir htten eine "geheime" Grafik mit dem Dateinamen "geheimesgeheimnis.jpg" in unsere Cloud hochgeladen und wrden diese Datei einem Nutzer, der keinen Hubzilla-Account hat, zugnglich machen wollen.
Zu diesem Zweck legen wir dafr einen Gastzugang an. Das geschieht mit der App (Hamburger-Men ) "Gastzugang".
Es wird ein Eingabeformular fr die Gastzugangsdaten angezeigt. Hier denkt man sich einen temporren Benutzernamen aus. Ein Passwort wird vom System automatisch erstellt. Diese Daten (Name / Passwort) muss man demjenigen, dem man Zugang gewhren mchte mitteilen.
Auerdem gibt man hier ein "Verfallsdatum" fr den Gastzugang ein (oder lsst das Feld leer, fr zeitlich unbegrenzten Zugang). Nach Ablauf der Frist wird der Gastzugang automatisch gelscht.
Solange man noch keine eigenen Rollen definiert hat, ist fr die Rolle "Standard" voreingestellt. Das kann man so auch belassen, sofern man nichts besonderes vorhat.
Nun klickt man auf "Absenden" und der Gastzugang ist erstellt.
Jetzt ffnet man im Hamburger-Men die App "Dateien" und ldt dort die Datei hoch.
Anschlieend ffnet man das Kontextmen () der Datei und whlt dort "Berechtigungen anpassen). Unter der Dateiliste erscheint nun ein kleines Vorhangschloss-Symbol, auf welches man klickt. Es ist jetzt mglich, die Zugangsberechtigungen aus einer Reihe von Standard-Berechtigungen auszuwhlen. Fr unsere Zwecke whlen wir "Benutzerdefinierte Auswahl".
In der erscheinenden Gruppen- und Kontaktliste erscheint unser gerade angelegter Gastzugang. Diesem rumt man die Zugriffsberechtigung ein "Klick auf "Erlauben") und man schliet anschlieend die Liste.
Ist das erledigt, klickt man auf den Button "Absenden" neben dem Vorhangschloss-Symbol (das jetzt einen geschlossenen Bgel zeigt) und ist fertig.
Die URL fr die Datei wird angezeigt, wenn man mit dem Mauszeiger ber den Dateinamen fhrt.
Bei den jetzt gewhlten Einstellungen knnen nur wir selbst und der Gastzugang auf die Datei zugreifen. Nicht bei Hubzilla angemeldete Nutzer und sogar Nutzer mit einem eigenen Account bei Hubzilla knnen die Datei nicht sehen.
Wenn sich nun der Nutzer, der ber die Zugangsdaten fr den Gastzugang verfgt, mit diesen einloggt, dann wird ihm die Datei zugnglich gemacht.
Falls man den Gastzugang irgendwann auch schon vor dem Ablaufdatum lschen mchte, klickt man im Hamburger-Men auf "Gastzugang". In der linken Seitenleiste werden die Gastzugnge aufgelistet. Hier whlt man dann den zu lschenden Gastzugang aus und klickt in der erscheinenden Maske auf "Lschen".
#FediTips #FediverseTips #hubzilla #hubzillahppchen
#Long #LongPost #CWLong #CWLongPost Hubzilla-Hppchen: Gastzugang
Mchte man Inhalte (z.B. Dateien aus der Cloud) fr bestimmte Personen zugreifbar machen, obwohl diese ber keinen Hubzilla-Account verfgen, aber ansonsten nicht fr die ffentlichkeit, so arbeitet man mit Gastzugngen.
Wer mit einem solchen Gastzugang eingeloggt ist, kann alles sehen, was ffentlich zugnglich ist und zustzlich alles, was der Zuteiler des Gastzugangs fr diesen speziellen Gastzugang freigegeben hat.
Angenommen wir htten eine "geheime" Grafik mit dem Dateinamen "geheimesgeheimnis.jpg" in unsere Cloud hochgeladen und wrden diese Datei einem Nutzer, der keinen Hubzilla-Account hat, zugnglich machen wollen.
Zu diesem Zweck legen wir dafr einen Gastzugang an. Das geschieht mit der App (Hamburger-Men ) "Gastzugang".
Es wird ein Eingabeformular fr die Gastzugangsdaten angezeigt. Hier denkt man sich einen temporren Benutzernamen aus. Ein Passwort wird vom System automatisch erstellt. Diese Daten (Name / Passwort) muss man demjenigen, dem man Zugang gewhren mchte mitteilen.
Auerdem gibt man hier ein "Verfallsdatum" fr den Gastzugang ein (oder lsst das Feld leer, fr zeitlich unbegrenzten Zugang). Nach Ablauf der Frist wird der Gastzugang automatisch gelscht.
Solange man noch keine eigenen Rollen definiert hat, ist fr die Rolle "Standard" voreingestellt. Das kann man so auch belassen, sofern man nichts besonderes vorhat.
Nun klickt man auf "Absenden" und der Gastzugang ist erstellt.
Jetzt ffnet man im Hamburger-Men die App "Dateien" und ldt dort die Datei hoch.
Anschlieend ffnet man das Kontextmen () der Datei und whlt dort "Berechtigungen anpassen). Unter der Dateiliste erscheint nun ein kleines Vorhangschloss-Symbol, auf welches man klickt. Es ist jetzt mglich, die Zugangsberechtigungen aus einer Reihe von Standard-Berechtigungen auszuwhlen. Fr unsere Zwecke whlen wir "Benutzerdefinierte Auswahl".
In der erscheinenden Gruppen- und Kontaktliste erscheint unser gerade angelegter Gastzugang. Diesem rumt man die Zugriffsberechtigung ein "Klick auf "Erlauben") und man schliet anschlieend die Liste.
Ist das erledigt, klickt man auf den Button "Absenden" neben dem Vorhangschloss-Symbol (das jetzt einen geschlossenen Bgel zeigt) und ist fertig.
Die URL fr die Datei wird angezeigt, wenn man mit dem Mauszeiger ber den Dateinamen fhrt.
Bei den jetzt gewhlten Einstellungen knnen nur wir selbst und der Gastzugang auf die Datei zugreifen. Nicht bei Hubzilla angemeldete Nutzer und sogar Nutzer mit einem eigenen Account bei Hubzilla knnen die Datei nicht sehen.
Wenn sich nun der Nutzer, der ber die Zugangsdaten fr den Gastzugang verfgt, mit diesen einloggt, dann wird ihm die Datei zugnglich gemacht.
Falls man den Gastzugang irgendwann auch schon vor dem Ablaufdatum lschen mchte, klickt man im Hamburger-Men auf "Gastzugang". In der linken Seitenleiste werden die Gastzugnge aufgelistet. Hier whlt man dann den zu lschenden Gastzugang aus und klickt in der erscheinenden Maske auf "Lschen".
#FediTips #FediverseTips #hubzilla #hubzillahppchen
#Long #LongPost #CWLong #CWLongPost
Hubzilla-Hppchen: HQ
HQ ist die Standard-Startseite nach der Anmeldung. Sie bietet einen schnellen berblick ber die letzten Beitrge und Direktnachrichten.
Ruft man den Hubzilla-Server (Hub) auf, bei welchem man registriert ist (und loggt sich, sofern das noch nicht geschehen ist, ein), dann landet man inzwischen nicht in der normalen Grid-/, sondern auf der Seite "HQ". Der erste sprbare Vorteil ist, dass die Seite wesentlich schneller rendert.
Man erreicht das HQ aber auch aus dem Hamburger-Men oben rechts () oder, wenn die HQ-App angepinnt ist, aus der Header-Leiste.
In der linken Seitenleiste ist zunchst ein Teil des mit ffentlichen und beschrnkten Beitrgen zu sehen, bei welchen jedoch nur ein Excerpt angezeigt wird. Ein Klick auf einen dieser Eintrge bringt den Beitrag in der Hauptansicht (mitte) zur Ansicht.
Nach dem Aufrufen des HQ sind in der Hauptansicht zunchst aber die letzten nderungen in verschiedenen Berichte, wie Wiki, Webseiten, Fotos, Dateien etc. zu sehen.
Die linke Seitenleiste weist verschiedene Reiter auf, mit denen weitere Listen angezeigt werden knnen.
Der zweite Reiter dient der Listenasicht ausschlielich von (DN).
Der dritte Reiter zeigt "markierte" Beitrge, also Beitrge, die man mit einem "Sternchen" Markiert hat (das geschieht im Kontextmen des jeweiligen Beitrags).
Der vierte Reiter zeigt die Mitteilungs-Liste.
Unter dieser Listenansicht sind noch zwei Icons vorhanden, ein "Bleistift", der bei einem Klick den Beitrags-Editor ffnet um schnell einen neuen Beitrag zu erstellen, und einen "Notiz-Zettel", welcher den Editor fr Notiz-Eingaben ffnet.
#FediTips #FediverseTips #hubzilla #hubzillahppchen
#Long #LongPost #CWLong #CWLongPost
HQ ist die Standard-Startseite nach der Anmeldung. Sie bietet einen schnellen berblick ber die letzten Beitrge und Direktnachrichten.
Ruft man den Hubzilla-Server (Hub) auf, bei welchem man registriert ist (und loggt sich, sofern das noch nicht geschehen ist, ein), dann landet man inzwischen nicht in der normalen Grid-/, sondern auf der Seite "HQ". Der erste sprbare Vorteil ist, dass die Seite wesentlich schneller rendert.
Man erreicht das HQ aber auch aus dem Hamburger-Men oben rechts () oder, wenn die HQ-App angepinnt ist, aus der Header-Leiste.
In der linken Seitenleiste ist zunchst ein Teil des mit ffentlichen und beschrnkten Beitrgen zu sehen, bei welchen jedoch nur ein Excerpt angezeigt wird. Ein Klick auf einen dieser Eintrge bringt den Beitrag in der Hauptansicht (mitte) zur Ansicht.
Nach dem Aufrufen des HQ sind in der Hauptansicht zunchst aber die letzten nderungen in verschiedenen Berichte, wie Wiki, Webseiten, Fotos, Dateien etc. zu sehen.
Die linke Seitenleiste weist verschiedene Reiter auf, mit denen weitere Listen angezeigt werden knnen.
Der zweite Reiter dient der Listenasicht ausschlielich von (DN).
Der dritte Reiter zeigt "markierte" Beitrge, also Beitrge, die man mit einem "Sternchen" Markiert hat (das geschieht im Kontextmen des jeweiligen Beitrags).
Der vierte Reiter zeigt die Mitteilungs-Liste.
Unter dieser Listenansicht sind noch zwei Icons vorhanden, ein "Bleistift", der bei einem Klick den Beitrags-Editor ffnet um schnell einen neuen Beitrag zu erstellen, und einen "Notiz-Zettel", welcher den Editor fr Notiz-Eingaben ffnet.
#FediTips #FediverseTips #hubzilla #hubzillahppchen
#Long #LongPost #CWLong #CWLongPost Hubzilla-Hppchen: Zot
Zot ist das Protokoll, mit dem Hubzilla betrieben wird. Es ermglicht die Kommunikation, das Identittsmanagement und die Zugangskontrolle.
Die Kommunikation mittels Zot kann ffentlich oder privat sein, wobei die private Kommunikation nicht nur einen vollstndig verschlsselten Transport, sondern auch eine verschlsselte Speicherung zum Schutz vorsieht.
Zot untersttzt eine breite Palette von Hintergrunddiensten im Grid, von Freundschaftsvorschlgen bis hin zu Verzeichnisdiensten. Neue Inhalte und Datenaktualisierungen werden im Hintergrund zwischen den Hubs im gesamten Grid gem den Zugriffskontrolllisten und den von den Sender- und Empfngerkanlen festgelegten Berechtigungen weitergegeben. Die Daten werden auch zwischen einer beliebigen Anzahl von Kanalklonen synchronisiert, so dass Hub-Mitglieder auch dann auf Daten zugreifen und nahtlos weiter zusammenarbeiten knnen, wenn ihr primrer Hub nicht erreichbar oder offline ist.
Zot bietet auch eine nomadische Identitt, so dass Ihre Kommunikation mit Freunden, Familie oder anderen Personen, mit denen Sie kommunizieren, nicht durch den Verlust Ihres primren Kommunikationsknotens beeintrchtigt wird - entweder vorbergehend oder dauerhaft.
Die wichtigen Teile Ihrer Identitt und Ihrer Beziehungen knnen auf einem USB-Stick, dem Laptop oder PC gesichert werden und jederzeit an einem beliebigen Knoten im Netz erscheinen - mit all Ihren Freunden und Vorlieben.
Entscheidend ist, dass diese nomadischen Instanzen synchron gehalten werden, so dass jede Instanz bernehmen kann, wenn eine andere gefhrdet oder beschdigt ist. Dies schtzt Sie nicht nur vor greren Systemausfllen, sondern auch vor vorbergehender berlastung der Website und staatlicher Manipulation oder Zensur.
Die nomadische Identitt, die einmalige Anmeldung und die Dezentralisierung von Hubzilla gewhrleisten ein hohes Ma an Widerstandsfhigkeit und Bestndigkeit in der Internetkommunikation. Mittels magic-auth meldet man nur einmal an Ihrem Heimat-Hub (oder einem nomadischen Backup-Hub) an. Dadurch kann man auf alle authentifizierten Dienste zugreifen, die berall im Netz angeboten werden - wie Einkaufen, Blogs, Foren und Zugang zu privaten Informationen. Das Passwort wird nicht auf tausend verschiedenen Websites gespeichert, sondern auf Servern, man selbst kontrolliert oder denen man vertraut.
Zugriffskontrolle: Die Identittsschicht von Zot ermglicht es, fein abgestufte Berechtigungen fr jeden Inhalt zu vergeben, den man verffentlichen mchte. Diese Berechtigungen erstrecken sich ber das gesamte Grid. Das ist so, als htte man eine riesige Website, die aus einer Grozahl von kleinen, individuellen Websites besteht und bei der jeder Kanal im Grid seine Datenschutz- und Freigabeprferenzen fr alle von ihm erstellten Webressourcen vollstndig kontrollieren kann.
Derzeit untersttzt Hubzilla die Zugriffskontrolle fr viele Datentypen, darunter Diskussionsbeitrge und -kommentare, Fotoalben, Veranstaltungen, Cloud-Dateien, Webseiten, Wikis und mehr. Jedes Objekt und die Art und Weise, wie und mit wem es geteilt wird, unterliegt vollstndig Ihrer Kontrolle.
Im Grid braucht man keine riesige Benutzerdatenbank auf dem Rechner, denn das Grid ist die Benutzerdatenbank. Sie verfgt ber eine im Grunde unendliche Kapazitt (begrenzt durch die Gesamtzahl der Hubs, die im Internet online sind) und ist auf unzhlige Computer verteilt.
Der Zugang kann, berall im Grid, fr jede Ressource, jeden Kanal oder jede Gruppe von Kanlen gewhrt oder verweigert werden. Andere knnen auf die eigenen Inhalte zugreifen, wenn es ihnen erlaubt wird, und sie mssen nicht einmal ein Konto auf dem selben Hub haben.
Aktuell verwendet Hubzilla das Zot-Protokoll in der Version 6 (Zot6).
#FediTips #FediverseTips #hubzilla #hubzillahppchen
#Long #LongPost #CWLong #CWLongPost
Last updated: 2024-03-07
All text and images © eLoc8.is-fabulous.com