Cox and Box

Als Handle oder Nutzerprofil bezeichnet man den Nutzernamen, der in Beitrgen angezeigt wird. Es handelt sich quasi um die "Identitt" eines Nutzers.
Bei sehr vielen Fediverse-Diensten (#mastodon, #misskey und Misskey-Forks = #forkey , #pleroma ,...) hat das Handle folgende Form: <BENUTZERNAME><INSTANZ-URL>.
Mein Handle z.B. fr meinen Mastodon-Account lautet: hvetinariburningboard.net
Bei vielen anderen Fediversediensten, wie z.B. #hubzilla , #streams , #friendica etc. unterscheidet sich das Handle (und die Bezeichnung... hier meistens als "Kanal" bezeichnet) ein wenig. Es hat die Form: <BENUTZERNAME><INSTANZ-URL>.
Das ""am Anfang wird weggelassen.
Diese Tatsache ist wichtig und kann bei Nichtbeachtung zu Problemen fhren.
Mchte man bei Hubzilla (und Verwandten) nach einem Handle suchen oder einen Kontakt hinzufgen, der von anderen Diensten stammt, dann muss man das fhrende "" weglassen!
Mchte man bei einem anderen Fediverse-Dienst (z.B. Mastodon) nach einem Hubzilla-Nutzer (Hubzilla-Kanal) suchen oder diesem folgen, muss man das "" am Anfang ergnzen!
#FediTips #FediverseTips #hubzilla #hubzillahppchen
#Long #LongPost #CWLong #CWLongPost Der Pepe (Hubzilla) That, and the typical Fediverse experience nowadays is a) Mastodon while barely or not at all knowing anything else exists and b) on a phone through a dedicated app.
The average Fediverse user doesn't start by joining Hubzilla on a desktop or laptop computer. They're fed up with Twitter and what became of it. They're told about Mastodon and the Fediverse which is implied to them to be one and the same thing.
So they grab their phones, they "install Mastodon" (the official app they've never in their lives used any online platform through an app that doesn't have the same name as the platform), and they register an account. On mastodon.social.
For at least the first three months, the Fediverse to them is Mastodon. Vanilla Mastodon with no more features than what Mastodon 3.x had. They actually think 500 characters are a lot, and they cannot imagine for the lives of them that it's possible for posts with more posts to exist in the Fediverse. How could they possibly The Fediverse is only Mastodon, after all.
Needless to say that they're deeply shocked and disturbed once they come across a post that does anything they took for absolutely impossible in the Fediverse. It's usually 500 characters, regardless of whether they come from Glitch or Misskey or Hubzilla.
At this point, they've gotten used to the Fediverse not allowing for more than 500 characters, not having text formatting, not having quotes, not having quote-tweets etc. etc. and of course being Mastodon and only Mastodon. And then this happens.
Those who are still on the official app are the poorest saps. The official Mastodon app is mercilessly hard-coded against vanilla Mastodon only with absolute and staunch disregard of the existence of anything else in the Fediverse. It totally refuses to take the existence of both Mastodon forks and non-Mastodon projects into account because that'd mean that Mastodon acknowledges the existence of Fediverse projects that have features that Mastodon a) lacks and b) flat-out refuses to introduce. So those on the official app get all long posts slammed right into their faces in the shape of unshortened walls of text.
Granted, the official Web front-end isn't that much better. It does fold long posts in. But it only folds posts in if they're ca. 2,000 characters or longer, and then it folds them in to ca. 1,500 characters.
Still, long posts can upset Mastodon users regardless of front-end. They're something that these users didn't expect. Something they don't want. Something they say doesn't belong into Mastodon and therefore into the Fediverse. Something that must be abolished.
For some even something they're willing to fight against until it's gone from the Fediverse, until the Fediverse is again what they thought it was when they were new: only vanilla Mastodon with only vanilla Mastodon's capabilities.
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #Mastodon #500Characters Because 2010/2011 was when this federation was established. And not 2012 or 2016 or 2024.
It doesn't matter if Diaspora* has introduced an official API years later. There was no API in 2010/2011. There was no technical documentation in 2010/2011. There was no interest in connecting to anything else in 2010/2011.
But there was Mistpark/Friendika, then still developed by Mike, that had federating with everything that could possibly be federated with as one of its primary goals. No matter the odds. Even including Twitter and Facebook.
In autumn 2010, shortly after the very first public alpha of Diaspora* had come out, there were no signs of things improving, no signs of there being a stable API anytime soon, if ever. Diaspora* gave the impression of only wanting to federate with itself. So trying to wait for an appropriate server-to-server API appeared to be futile, and Mike had to start working on that federation without an API.
And besides, while Diaspora* did evolve to a certain degree, Mistpark evolved more from March, 2010 to July, 2010 than Diaspora* did from May, 2010 to now. And I'm not even talking about what came after Mistpark/Friendika/Friendica, namely the Red Matrix, Hubzilla, Osada, Zap etc. and eventually (streams).
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #Diaspora #Diaspora* #Friendica Find the latitdue and longitude of any place I'm not talking about 2016.
Friendica, then named Friendika, introduced its federation with Diaspora* on March 19th, 2011 (see also ). This means that work on federating Friendika with Diaspora* had started as early as 2010 when the original four devs were still in charge.
If simply asking them had worked, all that hassle with reverse-engineering from source code and cracking encryption would have been unnecessary, and Friendika would have federated with Diaspora* in 2010 already.
And don't tell me that Mike Macgirvin didn't want to get into contact with the Diaspora* devs and intentionally do all the federation behind their backs. Mike has actually contributed to Diaspora*'s protocol, and unlike his attempted contributions to ActivityPub, they were even accepted AFAIK.
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #Diaspora #Diaspora* #Friendica

Where did you read that diaspora* never cared about federation outside of diaspora*

Did Diaspora* ever do anything to facilitate federation for Friendica or Hubzilla or (streams)
Did it ever actively try to stop them
Did it at least officially acknowledge that these three are federated with it

Where did you read that connecting to diaspora* is like to drill in a computer!

It's my description of how difficult it was to federate Friendica with Diaspora*.
Back in the day, Diaspora* had no API and no documentation on its protocol. Diaspora* was all about only federating with itself. Still, Friendica wanted to federate with it because Friendica federated with everything, full stop.
The "drilling into a computer case with a diamond drill" represents the several months it took the Friendica devs to crack Diaspora*'s undocumented encryption.
The "soldering wires onto circuit boards" represents how the Friendica devs had to reverse-engineer Diaspora* by studying its source code because there was no technical documentation whatsoever, and how Friendica could only federate with Diaspora* by latching directly onto Diaspora*'s inner workings instead of making use of any interface because there was no interface to use whatsoever.
Ask Mike Macgirvin .
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #Diaspora #Diaspora* #Friendica In the long run, however, it's bad.
It'll lead to wide-spread segregation of not only single Mastodon users, but entire instances from users that regularly post over 500 characters and instances with such users.
To say that's inconvenient puts it mildly, seeing as the secondary topic of my Hubzilla channel is the Fediverse in general and educating Mastodon users about the Fediverse outside of Mastodon in particular. If these very same Mastodon users can't read my posts anymore because someone else on their instance has talked their instance admin into blocking either my channel or the entirety of hub.netzgemeinde.eu, calling it inconvenient is an understatement.
It also makes explaining that "the Metaverse" is neither Zuckerberg's invention nor dependent on blockchains, cryptocurrencies and NFTs, and that decentralised 3-D virtual worlds have been around for over a decade and a half, much more difficult. And that's the primary topic of this channel.
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta phanisvara (streams) Yes, but many Mastodon users can't stand to see posts with over 500 characters. Not only do they refuse to read "long" posts, but some actually block anyone who exceeds 500 characters in a post even only once.
I'm pretty sure some ask their Mastodon instance admins to deal with such people. Have them blocked instance-wide. Have their whole Hubzilla hub blocked on that Mastodon instance.
Or they try to use Mastodon's report feature to report that Hubzilla user to the admin of that Hubzilla hub, or they have their admin try and get into contact with the admin of that Hubzilla hub, just to have that Hubzilla user sanctioned for breaking some unwritten Mastodon etiquette by posting over 500 characters in one chunk.
Of course, they fail in both cases. Hubzilla doesn't support Mastodon's report feature, and mentioning Hubzilla users, in this case the admin, in a public post won't work either. Verdict: That Hubzilla hub is unmoderated and therefore has to be blocked or even out-right Fediblocked.
On the grounds of the assumption that Hubzilla works exactly like Mastodon. Which I'm trying to debunk with this series of posts.
As at least one of my polls has revealed, there seems to be a not insignificant number of Mastodon users who demand posts with over 500 characters be banned absolutely everywhere in the Fediverse. Including in conversation between users on other projects, regardless of whether overly long posts from that conversation might leak into Mastodon or not.
And, of course, there's the Mastodon police that try to urge non-Mastodon users to limit their posts to a maximum of 500 characters, regardless of whether they're aware that the user in question is on something else than Mastodon or not. They're fully convinced that Mastodon was here first, and all the other projects are intruders in Mastodon's Fediverse and have to follow Mastodon's rules.
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #CharacterCount #CharacterLimit #CharacterLimits #500Characters #Mastodon

It would be best for such a thing to exist within ActivityPub itself, yes.

It would have to exist within ActivityPub. The only alternative would be the whole Fediverse having to adopt yet another non-standard Mastodon hack that isn't documented anywhere because Mastodon didn't intend it to be adopted by other projects.
But if you don't want stuff to leak out through Hubzilla, it would also have to be included into the Zot6 protocol. And if you don't want stuff to leak out through (streams), it would have to be included into the Nomad protocol.
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta

Essentially you'll need a server that hosts a virtual world, a client to consume it, and a way to transfer seamlessly between servers. The underlying protocol should be open, so other implementations can reuse that.
You go from online game to metaverse the moment anyone can author & host their own server, determine what the client experience is like, and connect it to the existing pool of servers in a decentralized way.

You've basically described . Established, free, open-source and decentralised since 2007, interconnected since 2008, today with thousands of individual worlds ("grids"), most of which are connected to the Hypergrid, and over four times the land area of Second Life.
Oh, and the OpenSim community has had "metaverse" as a regular part of their vocabulary since 2007 as well.
#Long #LongPost #CWLong #CWLongPost #OpenSim #OpenSimulator #Metaverse #VirtualWorldsAn alle meine Kontakte hier auf meinem Kanal "pepecyb8806hub.pericles.hu":
Ich habe - aus Grnden (zu lange Update-Intervalle der YunoHost App "Hubzilla") - einen weiteren Hub installiert. Der luft zwar auch auf dem YonuHost-System, aber nicht als YH-App, sondern wurde "zu Fu" aufgesetzt. Nachdem ich einige "Untiefen" umschifft habe, luft er jetzt stabil und das Log ist frei von Fehlern.
Nun ist mir meine Kanaladresse (die "8806" hinter dem pepecyb) schon geraume Zeit auf die Nerven gegangen. Die resultierte noch aus meinen Anfangszeiten mit Hubzilla. Damals hatte ich auf einem Hub den Kanal "pepecyb" (ohne 8806). Der Hub hatte so einige Probleme, so dass ich einen Klon bei einem anderen Hub anlegte. Irgendwann habe ich dann Account und Kanal auf dem ersten Hub gelscht. Nach einiger Zeit gab es dann beim zweiten Hub auch Probleme (zu Zeiten von Hubzilla 3 kam das immer mal vor). Dafr war aber der erste Hub inzwischen stabilisiert und auch schon auf einer aktuellen Version. Also legte ich einen neuen Account auf dem ersten Hub an und wollte den Kanal dorthin klonen. Nur der wollte den Kananamen nicht nehmen (weil es den ja dort schon einmal gab... und der deswegen irgendwie "gesperrt" war, obwohl gelscht) und hngte dem "pepecyb" nun das nervige "8806" an. Dieser Hub wurde aber meine Hauptinstanz fr lngere Zeit... und ich hatte mich mit dem "8806" abgefunden. Und dieses Kanalhandle schleppe ich seit dem mit mir rum. Jetzt wollte ich den Kanal natrlich auf meinen neuen Hub klonen, aber mit alternativem Kanal-Handle ("pepecyb" ohne Nummer). Das ging leider schief. Keine Ahnung weshalb. Ein Import unter dem "Nummern-Handle" funktionierte, aber die Umbenennung nicht (bei anderen Kanlen hat das reibungslos geklappt).
Deshalb habe ich nun einen frischen Kanal auf dem neuen Hub angelegt: "pepecybhub.hubzilla.hu"
Und das wird mein neuer und zuknftiger Hauptkanal. Also nicht wundern, wenn Ihr jetzt Verbindungsanfragen bekommt oder feststellt, dass Euch ein
"Der Pepe (Hubzilla) pepecybhub.hubzilla.hu"
folgt. Das bin ich und das wird mein aktiver Kanal sein. Den alten (hier) lasse ich bestehen, werde ihn aber nicht mehr "fttern".
brigens... hat jetzt auch mal einen "hbscheren" Namen, als mein "PericlesHub" (wie einfallslos) von dem hier: Whoville.
Mehr dazu:
#fediverse #hubzilla
#Long #LongPost #CWLong #CWLongPostYou can't enforce either of them Fediverse-wide.
Friendica has had "excluded + long name" () firmly hard-coded for 14 years now, almost 6 years longer than Mastodon has been around, and its descendants Hubzilla and (streams) have the same mention style hard-coded, too.
Mastodon and its forks have "included + short name" () hard-coded.
Misskey and the Forkeys have "included + short name + domain" () hard-coded.
An acquaintance of mine, himself on Mastodon, actually asked me to turn these freaky-looking long-name mentions off and switch back to Mastodon-style short-name mentions. I had to explain to him that I'm not on Mastodon, Hubzilla isn't Mastodon, Hubzilla has never been Mastodon, and on Hubzilla, mentions with long names and excluding the are hard-coded with no way to change them.
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #Mention #Mentions #MentionTag Because the technology isn't there. And making this absolutely safe, 100% guaranteed, is impossible.
First, almost all Fediverse protocols would have to be upgraded with an extra property that can contain domains to which an object must never be sent. That is, at least ActivityPub, Zot6 and Nomad would need this extension.
And then, full support for this property must be added to dozens upon dozens upon dozens of Fediverse projects immediately, no matter how slow their development is. And all their instances must be updated ASAP.
This is even less likely to happen. Some projects simply have extremely slow development or none at all.
Chances are that a post which you absolutely don't want to end up on Threads is forwarded to someone on Meisskey. Meisskey, a Misskey fork, hasn't seen a new release in a year and any activity in its Git repository in half a year. Of course, it won't have that new property implemented.
That Meisskey user a) has at least one follower on Threads, provided that Threads is compatible with anything in the Fediverse that isn't Mastodon, and b) likes your post so much that they decide to boost it.
And you've lost.
Such a feature is only any good if it's absolutely, 100% water-tight. But it will never be absolutely, 100% water-tight.
For example, I could easily circumvent that "don't send to server XYZ" property by quote-posting your post. A feature that has been available here on Hubzilla since at least 2012. Instead of forwarding your original post with all its properties, it copies the contents of your post into a new post that formats it as a kind of quote, mentions it's your post, links to your profile, links to your original post and actually causes you to be notified about it.
But still, that copy will not have the "don't send to Threads" limitation, and everyone can boost or quote-post it to wherever they please.
CC:
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta

Cox and Box

Cox and Box, also known as The Long-Lost Brothers, is a one-act comic opera with a libretto by F. C. Burnand and music by Arthur Sullivan, based on the 1847 farce Box and Cox by John Maddison Morton. It premiered in 1866 and was Sullivan's first successful comic opera. The story concerns a landlord who lets a room to two lodgers, one who works at night and one who works ...

-LostBrothers

That's what happens when people are lured to Mastodon with false promises. Such as getting a 1:1 identical Twitter clone, without Elon Musk, but otherwise identical.
Typical on-boarding tweet:

join mastodon its literally twitter w/o musk

And then they join Mastodon, actually and honestly expecting that 1:1 clone, a centralised corporate silo with a billion users and a secret-sauce algorithm that automatically throws content at you which it's certain that you might be interested in it, all before you've done anything else than load the app and register an account.
I guess thousands upon thousands of people have noped away from Mastodon again when they thought it's absolutely dead because The Algorithm didn't shovel any content into their timelines. Thousands upon thousands of other people left when they were told that they'd have to take steps themselves to populate their timelines. Too complicated, too inconvenient, too much work. Nope, I'm outta here.
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #Twitter #

The Long-term Impact of Infection with Novel Coronavirus ( ) study is a collaboration of researchers looking for who tested positive for -19 to understand the changes that happen after recovery from the virus.

UC San Francisco will launch the worlds first with samples donated by patients with .
The move follows research indicating that the virus can continue to linger throughout the body and may hold the key to understanding the cause of the debilitating disorder and lead to effective treatments.
By October 2023, an estimated
14% of Americans had or had had long COVID, according to the Centers for Disease Control and Prevention.
The disorder may appear as a continuation of the original COVID symptoms or manifest as new symptoms affecting any part of the body.
In serious cases multiple body systems are affected, including the , , , and .

Based on our work so far, we believe that long COVID is a - disease, said Michael , MD, principal investigator of the UCSF Long COVID Tissue Program and an infectious disease physician-scientist in the UCSF School of Medicine.

This program will allow us to comprehensively study the biological processes occurring across tissue compartments
in the blood, gut, lymph nodes, spinal fluid and bone marrow
in people living with long COVID.
This will help us better understand the underlying mechanisms of long COVID, said Peluso, who co-led recent research with Timothy , MD, a UCSF physician-scientist, that showed the virus was present in colon tissue up to 676 days following infection.

If you ask experienced users of Friendica, Hubzilla and (streams), they'd prefer doing away with poster-issued CWs altogether.
For one, they force CWs upon everyone, including people who don't need that particular CW. Besides, they leave sensitive people fully at the mercy of the posters and their willingness to write CWs.
Instead, automated, individually-generated, reader-side CWs based on keyword lists should become the new standard. On Friendica, Hubzilla and (streams), this feature is called "NSFW". It has been available since Friendica's earliest days, and Friendica is almost six years older than Mastodon.
Also, Mastodon itself has been able to generate reader-side CWs using filters since the 4.0 update last year. It just takes more awareness on the users' side that filters exist and what filters can do plus one-click or two-click CW filter creation for those who don't even know that Mastodon has filters in the first place, and that has to be implemented in all mobile apps as well.
It's actually dead-simple, and it doesn't require any W3C ActivityPub standardisation because it doesn't need a dedicated field. It uses keywords or hashtags or other strings or substrings found in the post body.
For example, you have "NSFW" in the word list of your NSFW app on Friendica/Hubzilla/(streams) (you do have it by default) or in the word list of a Mastodon filter. A post contains these four letters, "NSFW". Bam, post automatically hidden behind a CW. And Friendica, Hubzilla and (streams) even tell you that it's "NSFW" that was found and triggered the CW creation.
Of course, awareness is necessary because posters still do have to support this in their posts by adding keywords or hashtags that trigger the creation of such CWs. But that's no more difficult than writing a current Mastodon-style CW. In fact, you don't even have to jump to the CW field. And Friendica users can have sensitive stuff hidden behind automatically generated CWs even if they don't know the abstract/abstract tags.
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #CW #CWs #ContentWarning #ContentWarnings #CWMeta #ContentWarningMeta

Well, Mastodon's CW field is proprietary it abuses the subject field of ActivityPub. So, Hubzilla does not have subjects. If it had, Mastodon would mistake them for a CW.

Actually, Mastodon does use the summary field. Which Hubzilla has, but labelled "summary" and not "CW", but it works the same. It is the very field into which I've entered the CW of the start post. And you can clearly see the CW.
Don't confuse this with the subject/title field. Hubzilla has both. In Note objects/microblogging posts, Mastodon ignores and silently discards the content of the title field.
Trust me, I've been using Hubzilla for many years now.
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #CW #CWs #ContentWarning #ContentWarnings #CWMeta #ContentWarningMeta If there are three attributes that describe Diaspora*, it's lack-lustre, developed at a snail's pace and not interested in the outside world.
For a first alpha release, it took Diaspora* four developers, a crowd-funding campaign and significantly longer than it took Mike Macgirvin to develop Mistpark, which would later be renamed Friendika and which is known as Friendica today, all alone in only four months.
Diaspora* can't do nearly as much today as what Mistpark could do when it was first released in July, 2010, months before Diaspora*.
Diaspora* took until 2018 for a first beta release, not to mention that the entire dev team had been replaced meanwhile.
Within the same timespan plus two months, Mike developed Mistpark/Friendika/Friendica to stable releases, invented nomadic identity, forked Friendica into Friendica Red, re-wrote it entirely into Red, later known as the Red Matrix, led the Red Matrix to stable releases, redesigned it into Hubzilla, brought Hubzilla to stable releases, forked Hubzilla to Osada and forked Osada to Zap. All alone.
I'm not even sure if Diaspora* has an API now. When Friendica federated with it, it didn't. The whole Friendica-to-Diaspora* federation was 100% Friendica's work. Federating Friendica with Diaspora* was like connecting an external device to a computer by drilling a hole into the computer case with a diamond drill and soldering wires directly onto various circuit boards with only the circuit board layouts and some self-made measurements as documentation.
Diaspora* itself never cared for federation outside itself. It didn't welcome Friendica or Hubzilla or GoToSocial, it didn't take any measures against them either. It just silently ignored them and acted as if they weren't there.
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #Diaspora #Diaspora*phanisvara (streams)

i understand why people don't want to use a separate tool for every other thing they're doing. this gets complicated quick.

I don't complain about that as long as people choose a tool that's actually appropriate for these purposes.
But they use Mastodon for everything. They say, "I don't care how much better XYZ is at it, Mastodon can do it, and I don't want to move/I can't move/XYZ doesn't work as perfectly with my favourite Mastodon app, so I'll stick with Mastodon."
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta

-lasting

A lot of people are using the wrong tool for the job. They want a community of like-minded people, but are posting on a broadcast platform instead. That's like broadcasting a private get together with your friends on YouTube. Sure, you can do that, but there are consequences of doing so.

People do all kinds of stuff with Mastodon even though other Fediverse software is better for that. From podcasts that are MP3 files attached to Mastodon toots to groups grafted onto Mastodon. Even though there's not only Funkwhale, but even a dedicated podcast project named Castopod. And even though group discussions require conversations, and hardly anything in the Fediverse has such a lack of conversation support as Mastodon.
They don't do that because they think Mastodon is the best at it. They do it because Mastodon is all they know. They've spent their first months in the Fediverse thinking the Fediverse is only Mastodon because nobody told them about there being anything else. Either that, or the step from Twitter to Mastodon was so big that they're still recovering from it, and they don't want to learn something new again, so they use what they already know.
And if you tell them there's something better for the job, they refuse to adopt it because they "can't" move away from Mastodon for some reason.
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta I'm just used to having to pick Mastodon users up at either "The Fediverse is only Mastodon" or "Yeah, well, so there's other stuff in the Fediverse as well, but it can't be so much different from Mastodon."
I keep seeing Mastodon users come up with ideas for "the Fediverse" that might work if limited to Mastodon, but cause issues in combination with other projects in doing so, that are rather unlikely to work with other typical ActivityPub-based microblogging projects, and that have no chance of being the least bit compatible with Friendica, Hubzilla and (streams) because they work so vastly differently even from Pleroma and Misskey and their forks, not to mention Mastodon. And I always feel like having to comment before a campaign to actually introduce this and try to force it upon the whole Fediverse is launched.
Easily the worst case was that issue in Mastodon's GitHub repository that suggested the introduction of "quote-tweets". Which meant that Mastodon should invent that feature from scratch. Allowing other Fediverse users to "quote-tweet" you should be opt-in. And any and all Fediverse instances that can "quote-tweet" and don't respect this opt-in should be Fediblocked. This was meant as a counter-measure against rogue Mastodon instances and potential Mastodon forks that try to circumvent the opt-in with malicious intent.
Sounds good so far, doesn't it
Well, a lot of Fediverse *blogging projects can already "quote-tweet", and some of them could even before Mastodon was made. Misskey can, Firefish can, Iceshrimp can, Sharkey can, Catodon can, all the other Forkeys can, Friendica can, Hubzilla can, (streams) can... And that's so natural to them and so much part of their culture that they don't have any opt-in, not even an opt-out, much less one that's universally understood across the Fediverse.
Mastodon would not only re-invent the wheel from scratch, it would also publish no specifications for its opt-in. The developers of the other projects wouldn't have a chance to graft compatibility with Mastodon's opt-in into their projects in time.
So the day before Mastodon introduces "quote-tweets" and the opt-in, nobody would know how this opt-in works because it isn't finalised in the code yet, and the code is the only source for how the opt-in works. One day later, when Mastodon instances roll out the new version with "quote-tweets" plus opt-in, the new rules demand they Fediblock all instances of the aforementioned projects immediately for "quote-tweeting" without respecting the opt-in.
Misskey and all its forks, as well as Friendica and its whole family, would have been cut off from Mastodon due to the ignorance of another "Fediverse = Mastodon" believer.
Or a more recent example: the Bluesky bridge debate. Not only was the Mastodon community so enraged that they basically stopped just short of murder threats, but many made clear that they don't want anything to be bridged to Mastodon's ActivityPub.
What they obviously didn't know: Hubzilla is bridged to Mastodon, too. As is (streams).
Okay, the bridge is not third-party, it's an official part of the respective project. Okay, there's one bridge per channel, operated by the channel owner, and not one bridge for everything. And yes, Hubzilla supported ActivityPub through this bridge two months before Mastodon supported ActivityPub at all.
But still, they're bridged instead of having ActivityPub as their main protocol. A ban on bridges to different protocols would ban both Hubzilla and (streams) from the Fediverse.
The only people who pointed this out in that heated debate were Hubzilla and Friendica users. But the Mastodon crowd was ready and willing to push a ban on all bridges through.
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta Richtig. Und dann fangen die Leute an, einen fr verrckt zu erklren, nur weil man eine Bildbeschreibung auch dazu nutzt, das Bild und/oder Teile davon zu erklren. Weil, Bildbeschreibung ist ja nur fr Blinde und soll ja nur eine grobe visuelle Beschreibung sein.
Fr noch verrckter werde ich wahrscheinlich erklrt, wenn ich komplette, detaillierte Bildbeschreibungen und -erklrungen im Post selbst unterbringe. Und nicht im Alt-Text, wo nur eine kurze visuelle Beschreibung steht plus der Hinweis darauf, wo die detaillierte Beschreibung mit Erklrungen zu finden ist. Weil, "Bildbeschreibung" und "Alt-Text" sind ja dasselbe und meinen dasselbe.
Aber meine Posts behandeln im allgemeinen eine derart obskure Nische, da die allermeisten Menschen mit den Bildern ohne ausschweifende Erklrungen nichts anfangen knnen.
Auch in diesem Punkt knnen Bildbeschreibungen und -erklrungen hilfreich sein, wobei allerdings Erklrungen niemals im Alt-Text stehen drfen, weil nicht jeder den Alt-Text aufrufen kann.
#Long #LongPost #CWLong #CWLongPost #LangerPost #CWLangerPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta

The Fediverse is far more diverse than only Masto,

Not so much for . When they and many others on Mastodon write, "Mastodon and the Fediverse," what they really mean is only Mastodon.

& at least some if not possibly several of the alternatives pre-date Masto.

This.
Hubzilla, where I am, is from the year before Mastodon. When Mastodon was launched and joined the Fediverse, Hubzilla had already been there for ten months. Including the Red Matrix from which Hubzilla was renamed, it's almost four years. And Friendica can be traced back to almost six years of existence before Mastodon was made.

Some other platforms have IMO considerably less easy tools to add image #AltText, or possibly no tools at all.

Friendica, Hubzilla, (streams). All three with a common ancestor, namely Friendica itself when it was still MIT-licensed. They aren't inspired by Twitter. They're more like Facebook and even more like blogs.
Neither of the three has a nifty alt-text field like Mastodon.
If you add pictures the Mastodon way by attaching them as files, you've got no way at all to edit the alt-text. The alt-text is the file name, and that's hard-coded with no way around.
However, the usual way of adding pictures is completely and utterly different from how Mastodon does it. It is to first upload them to your own file space (all three give you file space with a file manager) and then embed them into the post like into a blog post.
But this doesn't give you an alt-text field either. It gives you raw code that you'll have to edit. With no documentation in at least Hubzilla's and (streams)' case, and with absolutely no help from the UI except for a preview button.
Friendica gives you BBcode like in a forum, but with some enhancements.
Hubzilla and probably also (streams) give you BBcode, too, but with so many enhancements that one could call it "Hubzilla-flavoured BBcode" or "Zot-flavoured BBcode".
Here on Hubzilla, you get this:

zrl=https://hub.netzgemeinde.eu/photos/jupiterrowland/image/6c9c16db-79af-41a2-9faa-5b22929fdd26zmg=800x533https://hub.netzgemeinde.eu/photo/6c9c16db-79af-41a2-9faa-5b22929fdd26-2.jpg/zmg/zrl

And you have to manually edit it into this:

zrl=https://hub.netzgemeinde.eu/photos/jupiterrowland/image/6c9c16db-79af-41a2-9faa-5b22929fdd26zmg=https://hub.netzgemeinde.eu/photo/6c9c16db-79af-41a2-9faa-5b22929fdd26-2.jpgThis is the alt-text./zmg/zrl

Heads buzzing already, everyone That was my very intention.
But this is literally the only way to add alt-text to images on Hubzilla and (streams). Unless you, as a (streams) user, are crazy enough to write the image-embedding code from scratch in Markdown or HTML. Which, truth be told, isn't any better.

So, it would be nice when Masto peeps rail against posts sans-AltText, check first from where the post originates, coz its author might be acutely aware of & sympathetic to the need for it, but be technically unable to provide it.

This won't happen.
For one, many Mastodon users still think the Fediverse is only Mastodon, so why check
Of the rest, the majority can't imagine that something that isn't Mastodon could possibly be so much different from Mastodon. So why check
Of the rest of the rest, the majority doesn't know how to check where a post came from. Remember Mastodon isn't Friendica. It doesn't tell people which project a post came from.
Oh, and besides, my experience is that the vast majority of Mastodon users refuse to read anything that goes beyond 500 characters altogether. Or anything that goes beyond what feels like 500 characters by Mastodon standards.
That's why I'm telling Mastodon users about Hubzilla in little chunks of 500 characters or fewer, even though Hubzilla doesn't have any character limit at all.
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #AltText #ImageDescription #ImageDescriptions #ImageDescriptionMeta #CWImageDescriptionMeta #Friendica #Hubzilla #Streams #(streams) I keep explaining this again and again: This won't work for the entire Fediverse. Mastodon users would not be able to edit alt-texts in posts from

Friendica (originally DFRN instead of ActivityPub with own bridges to ActivityPub, but recently switched to ActivityPub)
Hubzilla (Zot6 instead of ActivityPub with own bridges to ActivityPub)
(streams) (Nomad instead of ActivityPub with own bridges to ActivityPub)

These three aren't Twitter-like microblogging projects. They handle more like blogs, and images are usually embedded like in blog posts and not attached as files. They also don't have dedicated alt-text fields either.
If you want to add alt-text to an image coming in from Friendica, Hubzilla or (streams), you'd have to edit the post itself. Which would be impossible.
Mastodon doesn't receive Friendica, Hubzilla or (streams) posts in their original, raw source code. But you'd have to have the original, raw source code to be able to edit these posts and add alt-text.
Even if you had it, you'd have to get your hands dirty on raw BBcode with no WYSIWYG real-time preview. If the post in question comes from (streams), chances are it isn't in BBcode, but in Markdown or HTML.
Mastodon users would have to know how to graft an alt-text into the image embedding code in a post. Something that even Friendica, Hubzilla and (streams) users often don't know at least the latter two have no documentation whatsoever for it.
Not to mention that you'd have to have the power to edit any and all post anywhere in the Fediverse. The same power that'd let you add an alt-text to a post from Hubzilla would also let you manipulate and falsify other people's Mastodon toots.
Lastly, to make matters worse, laypeople on Mastodon usually can't tell where a post came from. Okay, stuff like bold type or bullet-point lists are dead giveaways that this comment here does not come from Mastodon because Mastodon can't do bold type and bullet-point lists. But plain text plus a picture, and nobody can tell where that post came from.
So you'd wonder how come you can't edit alt-text into that Mastodon toot because you wouldn't know that it isn't a Mastodon toot, and it came from Hubzilla instead.
#Long #LongPost #CWLong #CWLongPost #FediMeta #FediverseMeta #CWFediMeta #CWFediverseMeta #AltText #ImageDescription #ImageDescriptions #ImageDescriptionMeta #CWImageDescriptionMeta #Friendica #Hubzilla #Streams #(streams)phanisvara (streams)

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

The alt-text for the image:

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."

Having the full, detailed image description in the post comes with another advantage: If I have multiple images in one post, then the description of the first image can be referenced by that of the second and third images. I don't have to describe everything over and over again for each image. In fact, if I have multiple images, my descriptions start with a common preamble which includes an explanation where these images were taken.
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.

This article makes it appear like linking to the KnowYourMeme page of a meme template in the post text is a big no-no, and the meme has to be fully explained either in the alt-text which is bad for those who can't access alt-text or in the post.
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

Last updated: 2024-03-13

Cox and Box

Wills for Ireland