Image description

Maybe this is interesting for you:
(streams) had almost all nodeinfo code intentionally removed. This was done to keep (streams) from being crawled by instance-listing websites and dragged into competitions between server applications and particular servers.
Also, (streams) does not have a unified instance type identifier. Server admins may not only enter their own name for the server, but also their own custom instance type. If no instance type is given, (streams) uses the first word in the server name as the instance type.
Likewise, Forte's stats being reported as zero is fully intentional in order to keep it out of competitions. I'd be very surprised if there was an ActivityPub-compliant way around this.
By the way, here is a correction: Iceshrimp.NET is not a Misskey fork. It is being rewritten from the ground up in C# whereas Misskey and all Forkeys are written in TypeScript and Vue.js.
A few more Forkeys, dead or alive:

• Tanukey (you've listed it elsewhere)
• Neko
• Catodon
• Hajkey
• Metaskey
• Backspacekey

# # # # # # # # # # # # # # This is my personal analysis of the AI-generated image description, quote-posted from my original comment in the thread linked in my first comment:
RE:
(6/6)
# # # # # # # # # # # # # # # # After I have written the long description, distilled the short description from it and posted the image with both, I have asked a LLM AI for a description.
The AI of my choice was LLaVA 1.6:
The prompt was, "Describe the image in detail."
LLaVA took about half a minute to generate this image description:

The image depicts a modern architectural structure with a distinctive design. The building features a large, curved roof that appears to be made of a reflective material, possibly glass or polished metal. The roof is supported by several tall, slender columns that are evenly spaced and rise from the ground to the roof's edge. The structure has a circular emblem on the front, which includes a stylized letter 'M' and a series of concentric circles, suggesting it might be a logo or emblem of some sort.
The building is situated on a landscaped area with a well-maintained lawn and a few trees. There is a paved walkway leading up to the entrance of the building, which is not visible in the image. The sky is clear with a few scattered clouds, indicating fair weather conditions. The overall style of the image is a digital rendering or a photograph of a 3D model, as indicated by the smooth surfaces and the absence of any visible texture or imperfections that would be present in a real-world photograph. There are no visible texts or brands that provide additional context about the building's purpose or location.

(5/6)
# # # # # # # # # # # # This is the alt-text with the short description which I've distilled from the long description. It is exactly 1,500 characters long, a bit over 1,400 of which are image description.

Digital shaded rendering of the main building of the Universal Campus, a downloadable island location for 3-D virtual worlds based on OpenSimulator. The camera position is about three metres or ten feet above the ground. The camera is tilted slightly upward and rotated slightly to the left from the building's longitudinal axis. The futuristic building is over 200 metres long, stretching far into the distance, and its front is about 50 metres wide. Its structure is mostly textured to resemble brushed stainless steel, and almost everything in-between is grey tinted glass. The main entrance of the building in the middle of the front has two pairs of glass doors. They are surrounded by a massive complex geometrical structure, very roughly reminiscent of a vintage video game spacecraft with the front facing upward. Four huge cylindrical pillars carry the roof end, the outer two of which extend beyond it. All are tilted away from the landing area in front of the building and at the same time outward to the sides. The sides of the building are slightly tilted themselves. In the distance, a large geodesic dome rises from the building. There is a large circular area in front of the main entrance as well as several wide paths. They have light concrete textures, and they are lined with low walls with almost white concrete textures. Furthermore, various shrubs and trees decorate the scenery. A more detailed description including explanations and text transcripts can be found in the post.

(4/6)
# # # # # # # # # # # This is the long description that went into the post text. It is over 60,000 characters long. It took me two full days, morning to evening, to research and write. It takes about three hours to read it. Apologies for it being somewhat outdated by my current standards.

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 the main building of the Universal Campus as mentioned in this post.

What OpenSimulator is

, OpenSim in short, 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 Lab 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 in mainstream media broke away, but in fact, it celebrated its 20th birthday in 2023, and it is still evolving.
OpenSimulator was first published in January, 2007. It was made possible when, in 2006, Linden Lab open-sourced the official Second Life viewer, which is how client applications for Second Life and OpenSim are called, thus laying its viewer API open. This led to the development of third-party viewers. After the development of third-party viewers had started, OpenSim was developed against them and the Second Life viewer API. It does not have its own official viewer, but most of the popular third-party Second Life viewers are compatible with OpenSim as well.
Unlike Second Life, OpenSim 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.

What grids, regions and sims are

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". Regions can be empty, in which case they're shown as ocean, but they can't be entered. In order for any actual content to exist in a region and for avatars to be able to enter regions, a simulator, sim in short, has to run in a region.
In Second Life, a sim is always one region. OpenSim had a hack from 2009 on that was called "mega regions". It exploited a feature in third-party Second Life viewers that was not used by Second Life itself, and that made it possible to extend a sim across multiple regions in a square arrangement. The Universal Campus itself is built as a mega region of two by two standard regions. Since this hack was buggy and limited, varregions, now known as varsims, were first developed for the OpenSim fork Aurora-Sim. Eventually, they were officially introduced into OpenSim in 2014. They theoretically allow for a sim to stretch across as many as 32 by 32 standard regions with no borders in-between.
Unlike Second Life, OpenSim also has the option to save entire sims into archives and load them from archives, so-called OARs which is short for OpenSimulator Archives. Many of these are available online. Mega regions are saved in one OAR for each region, and as the Universal Campus was designed as a mega region and pre-dates varsims, it is divided into four individual OARs. A varsim, on the other hand, can be entirely saved in and loaded from one OAR.

Where the pictures were made

Particularly, the picture was created at UniCampus, an instance of the Universal Campus in OSgrid () owned by one of the grid admins. Launched in July, 2007, OSgrid was the first public OpenSim grid and intended as a testbed for OpenSim's development. Next to Wolf Territories Grid from 2021 (, ), it is one of the two biggest OpenSim grids each one of these two grids has more landmass than Second Life.
OSgrid also adopted the early OpenSimulator slogan "The Open Source Metaverse" immediately after its launch. It still uses that slogan, and the term "metaverse" has been commonly used by the OpenSimulator community ever since.

Camera position and general setting

The picture was taken from a point of view higher than the eyes of an avatar, ca. three metres or ten feet above the ground. The position of the camera is near the inner edge of a wide path that describes an eccentric path of three quarters of a circle around the likewise circular main landing zone as well as just a bit south of the southern edge of a wide, straight path that least eastward fromo the main landing zone. The direction of view is almost northward and slightly to the west. Also, the camera is tilted upward by a few degrees due to its low position and the height of the building.
All dimensions in this description are estimated.

Main building, southern end and main entrance

The main building of the Universal Campus is the centre-piece of the image. It is a gigantic building that towers high above all surrounding trees, although it is not actually a tower, nor does it have one. It is rather a lengthy building that stretches from north to south. In the image, the middle of its front is at one third of the width of the image from the left-hand edge, reaching to the left as far as one sixth of the width of the image from the left-hand edge. The conference hall at the far end is at one third of the width of the image from the right-hand edge with parts of the building almost reaching the edge. Its supporting structure mostly shows textures with highlights included which suggest that it was made of stainless steel. Otherwise, glass with a horizontal gradient between lighter grey and darker grey on the outside and a plain darker grey tint on the inside is the most commonly used material. The building does not have any exterior walls.
The southern entrance, the main entrance to the building with the main landing area right outside the doors, is surrounded and marked by a tall geometrical structure which is rather complex in spite of only having straight edges. It resembles a spaceship from an early video game as roughly as it resembles the letter A or an upside-down V. It is almost perfectly symmetrical around both vertical planes. Its medium grey surfaces are untextured otherwise and don't mimic any particular material.
On each far side is a vertical "column" with a footprint with the shape of a trapeze, very roughly four metres or thirteen feet wide and four metres or thirteen feet thick. The short side of the trapeze, measuring only a bit over three and a half metres or twelve feet, is on the outside. These columns rise up some nine metres or 30 feet on the inside. The top slopes downward towards the outsides, so the columns are less than eight or about a half metres or 27 feet high on the outside.
The centre and top piece of the structure, right above the doors and roughly seven and a half metres or 25 feet above the ground, is roughly ten metres or 33 feet tall and roughly four and a half metres or fifteen feet wide. It has a rectangular cross-section when looked at from inside the building or from the main landing area, but a heptagonal cross-section when looked at from the sides. Its seven visible faces are all rectangular. At the bottom, it is roughly five metres or roughly sixteen and a half feet thick with only one surface. The top is roughly five metres or roughly sixteen and a half feet thick, too, but with a pair of surfaces of the same size at an angle of under five degrees, forming a slight ridge at the top.
The inner and outer sides of this centre-piece are each made up from an upper surface which is a square and sloped outward from the top and a lower surface which is a rectangle and sloped outward from the bottom. They meet at an angle of roughly 20 degrees.
On each side, two irregularly-shaped structures of seven surfaces each connect the seven edges of the sides of the centre piece with the four edges of the inner sides of the columns. Six of these surfaces are more or less slightly twisted because they connect edges at different angles with each other. The only planar surface is the one that connects the bottom edges which are all horizontal.
Two pairs of double glass doors make up the actual main entrance. Each door blade is about two and a half metres or eight feet wide and about five and a half metres or eighteen feet high. The glass has the same horizontal gradient texture both on the inside and on the outside so that all door blades can be identical. The only difference between the door blades is whether the door script opens them clockwise or counter-clockwise. The texture is arranged in such a way that there are narrow lighter areas along both vertical edges when the hinge is on the left, and there is a wide lighter area on the lock side and a narrow lighter area on the hinge side when the hinge is on the right. The narrow sides of the door blades are opaque when looked at from the outside but, due to OpenSim's limitations, not when looked at from the inside. The doors open inward by 90 degrees, and they do so when they're clicked, or when an avatar approaches them. They can be closed manually by clicking them again, otherwise they close automatically after ten seconds.
Each door blade has one simple door handle on the inside and the outside tinted the same generic grey as the large structure surrounding the doors. The handles are only a few centimetres wide. The grips have a square cross-section. Above and below, there are thicker parts which connect the grips to the doors while being flush with them on the sides and facing away from the door blades. Altogether, each handle is half a metre or one and five eighths feet long. The top of each handle is about one and three quarters metres or five and three quarters inches above the ground.
Between the two door pairs and on their sides, there are altogether three columns with a rectangular footprint of roughly 90 centimetres or three feet width by 30 centimetres or one foot thickness, each roughly seven and a quarter metres or 24 feet tall. Above each pair of doors, they are connected with a horizontal beam that fits between the top surfaces of the columns and the top edges of the doors while being half as thick as the columns.
The spaces between the large structure around the entrance, the columns and the horizontal bars are filled with glass panes.
The whole door ensemble does not sit exactly at half the thickness of the large structure. It is shifted outward by about half a metre or one and five eighth feet.
A structure shaped like an almost flat pyramid, but with a flattened top, is mounted upside-down against the bottom surface of the centre of the large structure around the main entrance. The glass pane above the doors passes right through its middle. A square light is installed on the flattened top which is actually the bottom now, illuminating the entrance area when it is dark. Otherwise, this flat structure has the usual brushed stainless steel texture which appears rather dark here.
On each side of the entrance area, a cylindrical column with a diametre of roughly four metres or thirteen feet rises some 20 metres or 66 feet upward. Each column is slightly tilted inward along the longitudinal axis of the building and outward to the sides. On each side, farther outside, there is another, even taller column, easily over 30 metres or 100 feet tall. These columns are tilted along the longitudinal axis of the building at the same angle, but outward to the sides at a smaller angle. They make up the southern corners of the main building. All four columns are textured to resemble brushed stainless steel.
A semi-cylindrical structure connects the complex main entrance structure through the inner columns with the outer columns on the ground. Its diametre is roughly 2.40 metres or eight feet. It uses the usual brushed stainless steel texture, but the brushing direction is radial, and the texture is stretched along the axis of the cylinder so much that its nature is anything but obvious.
Between the columns and the main entrance structure, there are three more glass panes. The panes between the inner and outer columns are mounted halfway into the building whereas the one around the main entrance structure is almost all the way inside the building. Three horizontal stainless steel rods of about 30 centimetres or one foot lead through each pane. They are roughly evenly spaced, but closer to the upper and lower edges of the glass panes than to each other. The rods that pass through the panes between the columns grow to a diametre of roughly 45 centimetres or one and a half feet towards their ends before ending in short cylinders with diametres of about 1.80 metres or six feet.
On top of the inner columns and partly intersecting with the outer columns, a massive, upright, flat structure with stainless steel textures serves as the southern end of the roof. It has to be about 50 metres or 160 feet wide, about 15 metres or 50 feet tall and about 3.60 metres or 12 feet thick. The front and rear surfaces are slightly countersunk with margins of slightly varying thickness all around except for the bottom. The top edge has a fairly short horizontal section of ten metres or 33 feet in the middle from which it curves downward in sections of ellipses. The bottom edge is almost horizontal and leads to corners from which short 45-degree slopes lead upward. The slopes from the bottom and the ellipses from the top meet in rounded corners. Unlike the columns below, this roof end is mounted vertically.

Main building, Universal Campus logo

The roof end also carries the logo of the Universal Campus, sitting at half the height of the outer countersunk area of the roof end and ever so slightly to the left of its middle. Its base is a circular, conical structure with a diametre of ten metres or 33 feet, the sloped edge being black. The actual logo is part of the texture on the front surface of the cone. It has a diametre of about seven metres or 23 feet.
The inner 80% of its diametre are filled with a gradient from medium dark grey at the top to medium light grey at the bottom. Three shaded three-dimensional primitive shapes are displayed in this area, a cube with one corner each pointed to the top and the bottom at the top, a sphere in the bottom left, a tetrahedron in the bottom right. At the bottom of this area, "Patefacio radix" is written in medium dark grey letters, in a wide sans-serif typeface and in what is likely to be small caps. It is Latin for "open source". Below, the Roman number MMXI, 2011, marks the year of the first public release of the Universal Campus.
A thin dark grey circle separates this area from the outer 20% which are light grey. Re-using the same typeface as in the inner part, and in dark grey with blue shading, "Universal" is written at the top and "Campus" at the bottom, both capitalised with otherwise small caps and following the circular shape of the logo.
29 identical black circular spots, very roughly evenly spaced, protrude from underneath the logo all around it by a bit more than their own diametre. They separate the logo from the surrounding white area which, in turn, is surrounded by the aforementioned black conical slope.
The Universal Campus logo is illuminated from below. The light source sits in a slot in a cylinder on top of the main entrance structure, about two metres or six and a half feet long and a diametre of about 30 centimetres or one foot. This cylinder has spherical end pieces, and the whole arrangement has a simple, glossy, medium grey surface.

Main building, side

Each side of the building, all the way to the conference hall at the northern end, is tilted outward at the same angle as the corner columns around the front and much simpler in design. Starting north of the side entrances right behind the front, a semi-cylindrical structure on the ground, similar to those at the front, extends northward towards the conference hall, only interrupted by another set of side entrances shortly before the conference hall. Farther up, there is another cylindrical structure of the same diametre and with the same texture on each side, but with a cutout on the upper inner side of a bit over 90 degrees to help carry the upper floor on the right, actually semi-cylindrical on the left and stretching all the way between the columns on both sides. Even farther up, right below the roof, another cylindrical structure is installed, but cut out on the inside by 60 degrees upward and 75 degrees downward.
Eight cylindrical beams with a diametre of roughly 90 centimetres or three feet and the usual stainless steel texture serve as the near-vertical supports. Nearly evenly spaced, except for the first being closer to the second, and running from the bottom to the top, they divide each side into eight full-sized sections and one small section right in front of the conference hall.
As mentioned above, the building has four sets of side entrances. One on each side is right behind the front behind the colour and the first support beam, one on each side is just south of the conference hall between the seventh and eighth support beams. The doors are identical to the ones that make up the main entrance, but each side entrance has three pairs of doors instead of two.
Between the three double doors, there is a filler column with a rectangular vertical cross-section, a width of about 45 centimetres or one and a half feet and a thickness at ground level that is slightly less than the width. While the inside surface is vertical, the outside surface is sloped in parallel to the outward tilt of the side of the building. Similar but wider columns are installed on the sides of the doors, being the closest that the building has to outer walls. Another structure with a rhomboid north-south cross-section sits on top of each set of four pillars, connecting them and carrying a glass pane on top. Its inside surface is sloped outside, its outside surface has a stronger slope than the outer side of the building. Also, its texture is lighter than that of the pillars.
Everything else between the vertical and horizontal structures on the sides of the building is filled with glass panes, all with a light vertical streak down their centres, blurred by the gradients on its sides.

Main building, roof

On the visible right-hand side of the building, right above the positions of the first seven of the eight support beams, curved brackets reach down from the roof, holding the upper horizontal cylindrical beam from the outside. They appear to be dark grey, but they actually have the usual brushed stainless steel texture. These brackets are installed on both sides across the outer parts of the roof, and slightly larger versions span across the centre of the roof as can be seen from below through the windows of the building.
A little bit of roof is visible underneath these brackets. The roof has four identical sections from its end to the conference hall. All are mostly planar with a rounded outer side. From above, they have the most elaborate surface of the whole building. It is almost black. A bump map or a normal map divides it into slightly embossed and slightly less rough rectangles, slightly countersunk and slightly rougher rectangles and the another bit smoother lines in-between. The rectangles are of varying size. They have an aspect ratio of four to five along the building's longitudinal axis by three to four along its transversal or vertical axis. In addition, the texture on these roof segments is glossy, giving it a plastics-like appearance. From below, however, it is smooth and transparent with the same tint of grey as the glass panes.
Between the inner and outer sections of this kind on each side, there is one long textured strip, on top of which rest the larger brackets across the centre of the roof. Its texture is slightly glossy, but hard to identify as resembling something: It consists of stretched rectangular fields of medium grey, arranged transversally, with very thin dark grey outlines, surrounded and interrupted by narrow areas of medium light grey which are emphasised by bump-mapping or normal-mapping which makes them appear embossed as well as specular-mapping which makes them appear glossier than the rest. Within these fields, but at some distance from its outlines, there are more nested rectangles, from outermost to innermost: medium dark grey, dark grey, medium dark grey, medium grey and slightly bumpy, medium light grey and bumpier as well as appearing to be slightly countersunk, light grey and appearing to be even more countersunk. This pattern repeats over a hundred times over the length of the southern part of the building. It is on the bottom face of these two strips as well, but not on its narrow sides.
The very middle of the roof is simply one long glass pane. It is separated from the dark sections to its side by what seems to try to resemble rectangular aluminium profiles with the long sides oriented vertically. On each side, at a height right above the glass pane, there is a stripe that glows white in the dark while not actually being a light source this is another OpenSim limitation.

Main building, domed conference hall

Beyond these parts of the building, a large geodesic dome rises up, below which is the conference hall. It is assembled from triangular glass panes in seven rows, four of which the image shows from outside, and untextured light grey cylindrical rods. The glass panes have the same tint or texture on both sides. The ones in the two bottom rows have the usual grey tint. The two rows above have the same lighter texture which most of the other panes on the building have on the outside. Unusually, this geodesic dome has no points at which five triangular panes meet. On all points which aren't on the bottom edge, six panes meet except for the very top where only four panes meet.
The dome is surrounded by a huge, disc-like object of varying thickness, but very thin on the eastern side which is revealed in the image, that is well over a hundred metres or 330 feet in diametre. It is bascially an eccentrical cone with a circular outer shape and a way off-centre hole towards it slightly slopes down. The geodesic dome mostly rests on the edge of the hole which means that the outer edge of the disc is shifted way to the east. There is also a cutout towards the south all the way to the circular hole, uncovering the roof of the southern part of the building. The western edge of the cutout deviates from being parallel to the longitudinal axis of the building by a few degrees to the right. The eastern edge of the cutout points at the centre of the circular hole.
Along the outer edge, the top surface of the disc is tapered over a distance of about seven and a half metres or 25 feet so that the outer edge is almost razor-sharp. For unknown reasons, the western edge of the cutout shows a similar sharpness by being tapered at the bottom.
The upper and lower surfaces of the disc shows variations of the usual brushed stainless steel texture. The cutout faces, however, show a dark grey texture with four darker grey grooves upon zooming in.
Right below, there is a second, similar asymmetrical cone, but smaller in diametre, even thinner and with a bigger slope. Its outer edge touches the first disc from below. Being dark coffee brown, it is the only outward part of the building that is not a shade of grey. Also, while it is half-transparent like tinted glass from above, all other surfaces are opaque and glossy, so it's possible to look through it from above, but not from below.
The inner edge of the brown cone connects to a ring around the conference hall at about roof height on the outside or the top. The ring describes about three quarters of a circle with the opening oriented towards the southern parts of the building. It has a slightly darker tint on its brushed stainless steel texture.
The ring also serves as the upper connection between the seven cylindrical pillars that surround the conference hall, four of which are hidden behind the building itself in the image. They have a diametre of about six metres or 20 feet, and they vary in length by a few metres. They all stand on the ground, and they are sloped outward from the conference hall, partly intersecting with the two cones above.

Main building, interior

Since the outer surfaces of the building are mostly glass, more can be seen inside the building than just the underside of the roof. Horizontal support cables are mounted between the textured roof strips and underneath each of the seven central roof brackets. They are similar to those through the side window-panes in the front, but longer and thinner. From all of these but the southernmost one, two darker, thinner and shorter support cables lead downward. Another pair is mounted farther south against the textured roof strip on its side. These fourteen vertical cables support the upper floor on its inner sides.
The upper floor is roughly U-shaped with the opening towards the south and the main entrance. It also serves as the ceiling for the ten seminar rooms on the ground floor, five on each side, above each of which it extends inward with a semi-elliptic shape. Its bottom side, the ceiling, is light grey. It has a bump map or a normal map which not only roughens it up but also divides it into octogonal pads with rectangular spaces in-between. The vertical surfaces towards the aisle have a texture that simulates small, square, dark grey panels in four rows held in place with one rivet in each corner. The seams between the panels are black. On some surfaces, the textures have obviously been stretched horizontally, making the panels rectangular, the rivet heads elliptical and the vertical seams wider than the horizontal seams. The upper side with its bluish-grey patterned carpet texture cannot be seen in the image.
The entire inner edge of the upper floor is protected by a railing. It consists of one mostly light grey rail with a rectangular cross-section on the floor, an identical rail that is a bit over 1.20m or four feet high above the floor and a number of small, slightly darker grey vertical beams with a square cross-section which connect them. The whole railing lacks texture and gloss.
Of the seminar rooms on the right, only the separation walls can be seen through the panes on the right of the building. These have mostly tan textures but with coarse and blurry stripes of various greys at the top and bottom.
Through the right-hand pane in the front, two seminar rooms on the left are visible, the rooms A7 and, north or to the right of it, A8. The seminar rooms A7 through A9, as well as A2 through A4 on the right, have a variety of untinted glass doors each: one in the northern corner towards the central aisle, another one in the southern corner, and one in each of these two corners that leads to the neighbouring seminar room. Apart from the lack of tint or texture, the glass doors are identical to the entrance doors.
The aisle-side wall of each seminar room can be described as convex although it is not rounded. It rather consists of four segments separated by narrow vertical columns with square footprints. They are connected by a number of horizontal rods with a rectangular cross-section. One is always right under the ceiling. Three more are roughly at 65%, 50% and 33% height above the ground. For the outermost segments, this is the height of the glass doors, so underneath the rod at 33% height above the ground, they have another vertical rod to separate the doorway from a narrower piece of wall. At some 12 or 13% height above the ground, there is another rod, and the last one is on the ground, in both cases except where there's a doorway.
The space between the latter two horizontal rods is filled with a wooden panel, showing the same reddish wood grain as all wooden-textured furniture in the building and on the sim. The other spaces have untinted glass panes in them. To illustrate the dimensions: The wooden panels are about 1.80 metres or six feet high, so for realistically-sized avatars, the only way to look into or out of the seminar rooms is through the doors.
On the vertical rod next to each aisle door, a sign with the room number is installed. The sign itself is simple, flat and rectangular. It is entirely black except for the white room number written on it in a regular Helvetica sans-serif typeface. It is attached through a glossy white cuboid that serves as a very simple mounting bracket.
Furthermore, there is an easel with a blank whiteboard standing next to each aisle door. It is a simple construction from cuboids, cylinders, a tetrahedron at the top and small spheres for feet and joints. Apart from the whiteboard which is mostly white and untextured except for the plywood texture on the back, the whole thing shows a brushed stainless steel texture with some gloss added.
Inside each seminar room, visible through the window-pane behind the easels, there is a whiteboard which is a much more elaborate construction. Each room has two of these. There is also a dark grey HDTV screen attached to the middle one of the three columns with a wall-mount swivel arm. A bit of furniture is barely visible through the closed glass door: Each room has seven quite long tables with elliptical ends, one long light grey foot on two legs with a wooden plank between them and a dark grey surface surrounded by wood grain. Six of these tables are for seminar participants with two chairs each. These chairs consist of two wooden parts in the shape of a stretched U with rounded sides and dark grey padding, two small metal rods connecting them and four conical metal legs. The seventh table is for the teacher whose chair is identical to those for the participants, only that it has an extra headrest in the same style as the rest of the chair plus a pair of elliptical armrests.

Main building, further interior objects

The large object that appears to be standing in front of seminar room A7 is a teleporter that was specifically designed for the Universal Campus due to its size. It is actually standing in the middle of the aisle, the control panel turned southward towards the main entrance. It is mainly a rectangular console on a massive angled stand. The frame around the control panel included, the console itself is about one and a half metres or five feet high and about three metres or ten feet wide. Above the control panel, there are two tiny spherical light sources on small trapezoid arms. They actually emit light to illuminate the control panel of the teleporter.
The control panel is labelled in a typeface not entirely dissimilar from Futura. On its left, there is a top-down view of the entire Universal Campus with the north oriented to the left. It shows the various buildings and other places. Ten circular markers are placed on the map, all with a glossy grey frame and a black number from one to ten. All markers but one are yellow one is always glow-in-the-dark green. In this case, it is marker number 6 to the right of a rectangular building with a circular extension in its bottom corner. Below the aerial view, there is another, slightly bigger yellow circular marker, but with a red frame surrounded by a glowing red aura while not glowing itself. It has the number 2. Next to it is a label with an arrow-like point to the left that reads, black on white, "This is currrent (sic) location". It is up to the user, however, to find the marker with the same number on the map.
On the right of the control panel, there is a touchable list of destinations with their numbers in markers of the same size as the glowing red one in the bottom left, but with the usual shiny grey frame. The labels with the names of the destinations are identical in style with the current location marker:

• 1: Main Landing Zone
• 2: Main Building Lobby
• 3: Main Conference Hall
• 4: Recreation and Conference Center
• 5: Observation Deck and Sea Lab
• 6: Science Lab and Conference Room
• 7: Campfire and Beach Zone
• 8: The Light House
• 9: Engineering Conference Center
• 10: Helicopter Landing Pad

Just like on the map, destination number 6 is the only one with a glow-in-the-dark green marker and a glow-in-the-dark green label background. It is the currently chosen teleport destination. Upon clicking another one, it would be marked green, as would be its marker on the map. Below the list, there is another white label, but with an upward arrow point on its left-hand end that points to the column of numbered markers. It reads, "click to select location then right click and teleport!" This means that if the user were to right-click the panel, thus opening a pop-up menu, and then choose the option "Teleport", the avatar would instantly be relocated to whichever location is selected on the teleporter. To the right of this label, there are two small red triangles with glowing auras pointing upward they appear to be non-functional.
The background of the control panel is glossy medium grey. The rest of the structure is glossy with a gunmetal-like dark grey texture.
There are also quite a few potted plants inside the building. On the sides of the teleport panel, there are two identical aa palms in square terracotta pots with wide rims. Like the other potted plants, these mostly dark green plants with long pointy leaves are kept at an indoor-compatible size, namely about three and a half metres or eleven and a half feet tall. Also, like the other potted plants, they are made of only four flat and surfaces with partially transparent pictures of the plant on them, arranged in angles of 45 degrees to one another.
Through the main entrance, a slightly taller Jacaranda tree with dark lilac flowers can be seen. It is planted in a bulgy terracotta pot with a smaller rim than the square ones which is supposed to be round. In order to reduce the impact on graphics performance, however, the pot is actually hexagonal. There is also one of the two angled flights of wooden stairs leading to the upper floor and, outside the building again, a small but wide maple tree with brown autumn leaves. A look through the side entrance to the right shows an even slightly taller Bougainvillea with purple flowers. Above these doors, the underside of the upper half of the other flight of stairs is shown. The steps are not covered from below, and the spaces between them are open.
Some of the unusual dividers on the upper floor can be seen through the windows, too. The main element is a half-arch of a bit over 90 degrees from the floor to the tilted structures on the side of the building. Its core is a thin, roughly 1.80 metres or six feet wide circle segment with an inner radius of about four and a half metres or fifteen feet and a dark grey texture which resembles some kind of rock. It is lined on both the inside and the outside with arches with a brushed stainless steel texture. The inner arch is about 45 centimetres or one and a half feet wide, the outer arch is slightly narrower, and both are significantly thicker than the core arch. From both ends of the arch, narrow brushed stainless steel bars extend to the centre of the arch where they meet. They are thinner than the stainless steel arches, but thicker than the core arch. Finally, the area between the two bars and the inner arch is filled with a grey tinted glass pane.
On each side of the upper floor, there are six such dividers. The southernmost ones are installed right above and north of the stairs and attached directly to the vertical structures on the sides. Between the other ten and the side structures, there are horizontal extensions in much the same style. The arches themselves are extended to the sides by two rhomboids in the same style, a longer one of some four and a half metres or fifteen feet with four cylindrical connectors of roughly 60 centimetres or two feet of diametre on its corners underneath which avatars can pass and a shorter one of some three metres or ten feet which connects to the vertical structures. The latter one also has a third stainless-steel-framed rhomboid all the way down to the floor underneath itself which is filled with a grey tinted glass pane.

Avatars in OpenSim and the avatar vendor rooms

On the eastern side of the building, barely visible through the large glass surfaces, there is an area that offers complete classic avatars as well as classic avatar accessories.
Unlike in most other 3-D virtual worlds, avatars in OpenSim-based worlds, just like Second Life, are not monolithic. They are highly modular, they are highly configurable, and they have evolved over the years. The most basic classic avatar consists of five components that always have to be there. The only one that cannot be replaced is the system body which is automatically generated by the viewer application. OpenSim has the same system body as Second Life. The four components that can be replaced but never removed are the shape which greatly defines the look of the avatar with 88 parametres, the skin which is a set of three textures for the head and which can be tinted with parametres, the upper body and the lower body, the hair which defines the shape and length of the classic hairdo growing out of the head as well as its texture, and the eyes which are basically only a texture again.
Classic clothes are also referred to as layer clothes because they are just that, layers of textures painted onto the system body. Their order is defined by nine categories, in each of which a classic avatar can only wear one kind of clothing. A few of these have an influence on the shape of the avatar: The shirt and the jacket can widen the arms to simulate sleeves. Likewise, the pants can widen the legs downward to simulate pants legs and even bell-bottoms. And the shoes can both raise the avatar in general and grow a sort of spike out of the heel, lift the whole avatar except for the toe area because the system body does not actually have toes and thus generate high heels. A separate layer is for skirts it textures a part of the system body which is usually fully transparent and thus invisible. In 2011, four tattoo layers were added between the skin and the two underwear layers.
It is also possible to attach objects to an avatar at 30 different points, and it has been for as long as OpenSim was around. This was quickly used not only for things carried by the avatar, jewellery or other accessories, but also for more realistic hair, for better-looking shoes in comparison with the painted-on classic shoes, for various ways of having new shapes of skirts, for collars, for pants legs et cetera.
Originally, these attachments were made from primitive objects or "prims" in short: basic shapes like cubes, spheres, cones and the like which can be generated and manipulated a lot in-world without needing external software except for making textures. Since building complex objects from them is somewhere between highly complicated and impossible, it was made possible to import sculptmaps as exported from 3-D software like Blender and use them to create more complex prims. All kinds of prims can be made flexible with a little bit of physics which is used for hair and skirts as well as for flags, but the physics don't have collision detection.
The next step was the introduction of mesh. Mesh allows the user to directly import 3-D files in the Collada format, texture mapping included, without having to resort to sculptmaps. Mesh came to Second Life in 2011, as did experimental mesh support in OpenSim. The first stable release of OpenSim with mesh support came out in 2014. On avatars, mesh was originally used for hair, shoes, jewellery and other accessories. It really started a revolution with the introduction of rigged mesh which automatically latches itself to multiple points on the avatar. This made it possible not only to create clothes that move with the avatar's movement, but even to create all-new, better-looking bodies and heads. Nowadays, most avatars consist entirely of mesh.
The newest technological advancement for avatars was Bakes-on-Mesh which came up from 2019 on. This allows classic layer textures to be put onto worn mesh, especially mesh bodies, and in greater numbers than on the system body. The main purpose was to get away from skin appliers, scripted devices that have to be put on and used to put a different skin onto the mesh body. Also, the remaining onion layers around mesh bodies that were necessary for tattoos, but made mesh bodies unnecessarily complex, had become obsolete because Bakes-on-Mesh allows for wearing classic layer tattoos on mesh bodies. But it also makes wearing layer clothes possible again which can make sense in the case of skin-tight clothes.
The latest version of the Universal Campus from 2012 already uses mesh for a few things, mostly rocks. The main building itself and everything else shown in this image is still put together from prims and sculpties.
As for the contents in the avatar vendor area, none of it is newer than from 2011. Everything is still from times before mesh. The complete avatars come with layer clothes, but no attachments. They, like the skins and hair attachments, were created by Ina Centaur under the OS Avatars label around the same time as the Universal Campus. Many of the other items, the majority of which were made by Nebadon Izumi himself, are even older. All of them are offered under free licenses, however. In order to announce their availability, three of the divider extensions have signs mounted above them which can be made out in the picture. They are oval, black with a stainless steel frame, and they have the glowing, but not light-emitting white word "AVATARS" written on them in all-caps and in a typeface which looks to me like a regular Linux Libertine. The writing even uses proper kerning between the "A"s, the "V" and the "T".
In the first two of the three avatar vendor rooms, the rear sides of four stainless steel vendors each, lined up on the outer side of the room along the longitudinal axis of the building, and especially the signs above them on thin cylindrical stands can be made out, the only ones that aren't hidden behind something. The first four vendors offer one female skin each, the other four offer one male skin each. The displays on these eight vendors are oriented away from the camera.

Main building, upper floor, western side

The first two rooms on the western side of the building are conference areas, the other two are empty. Not much of them is visible except for three of the dividers, a semi-circular couch with a wooden frame and ten seats, a small banana tree in a hexagonal white concrete pot, another whiteboard and two HDTV screens in stainless steel casings on floor stands. One of them shows the monochrome test pattern which is actually on all of them, and which includes several screen-testing elements as well as a large medium grey circle in the middle with a white, a black and a thinner medium grey border around it and the digit 2 in black and in a heavy, condensed sans-serif typeface and a white square grid on medium grey ground with the capital letter "C" in two combined fields at the bottom.

The main landing area outside the main entrance

In front of the main entrance, there is the main landing area of the sim, a part of which is still within the image towards its bottom left. It is circular in shape with a diametre of about 40 metres or 130 feet. The centre of this circle is about 35 metres or 115 feet south from the main entrance of the main building. It shows the same light grey texture reminiscent of concrete that is used on most paths on the island. The texture is not shrunk to a realistic size, so it appears coarse and having a low resolution.
The outer edges of nearly all concrete surfaces on the island are lined with low walls of varying height and width. They all have the same concrete texture, but at a smaller scale and without the light grey tint so it appears almost white. The main landing area actually has two rows of walls around it. The inner walls are a bit over 1.20 metres or four feet high and about 1.50 metres or five feet wide. The outer walls at a distance of roughly three metres or ten feet are about 1.65 metres or five and a half feet high and about 1.80 metres or six feet wide.
At the ends, the gaps are closed with walls a bit lower than the inner walls and roughly 90 centimetres or three feet wide. The spaces between the walls are filled with dirt. They form planters with identical shrubs in them the short planters in the northwest and the northeast visible in the image have five plants each. These shrubs are not named in-world. They appear to be of tropical origin, and they have flowers with petals that are mostly white, yellow towards the centre and magenta along their edges. Like all trees on this sim, the shrubs are made of simple, textured sculpty prims for the trunks and branches, and the twigs, leaves and flowers are semi-transparent textures on intersecting two-dimensional surfaces, a popular way to make plants in Second Life and OpenSim before the arrival of mesh. The textures used for all plants on this sim are photo-realistic as far as the maximum possible or feasible texture resolution allows.
On the left-hand edge of the image, in front of the northwestern planter, there is another teleporter which is almost identical to the one that can be seen inside the building. There are two differences, however: Its current location is number 1, and the selected location in the image is number 4. Another one of the unidentified shrubs appears between the teleporter and the left-hand edge of the image, partly hidden behind the teleporter.
Another single-target teleporter is standing on its right. It is a custom addition to this particular instance of the Universal Campus. It was built by Neovo Geesink, formerly of Metropolis Metaversum fame and now involved in OSgrid, in his trademark style. This style includes a particular brushed stainless steel texture which, unlike those used by Nebadon Izumi, emulates the surface having been brushed circularly. The stand under the panel is a simple cone, flattened to an extremely elliptical footprint. The panel is as high as that of the original teleporter, but only slightly wider as it is high. The frame around the image in the centre is slightly narrower than that on the original teleporter.
The image itself shows an aerial view of its single hard-coded target, a sim named TeleHub, built and operated by Neovo. It is nothing more than a single region, a square of 256 by 256 metres or 280 by 280 yards, surrounded by blue ocean and a wall made of beige bricks which is about ten metres or 33 feet high. The ground is tan and divided into four triangular areas by two diagonal lines. In each area, there are 141 single-target teleporters similar to this one, but with a higher panel, in rows of eleven. A few show previews of their targets, but most are unused with black screens. In the very centre, there is a small circular platform on which avatars land after teleporting in. It has a beige top surface with a hexagonal tile pattern and a woodgrain texture on the sloped surface all around. Four arches with textures resembling rough taupe stones and black signs on them lead to one triangular area each. The position of the camera is off one of the corners and pointing diagonally downward to one of the yellow division lines.
Yet another one of the identical unidentified shrubs is behind this teleporter and shown to its right.
In the background, the low walls on the sides of a path appear between the shrub behind the teleporter to TeleHub and the main building. The path is straight and leads northward along the western side of the building.
Even farther in the background, behind the two teleporters, there is some vegetation. From left to right, it starts with an unidentified tree of about eight metres or 26 feet of height. It has reddish-brown bark, medium green leaves in pairs and what could be taken for pale yellow-ish fruit. Below it, there is a large bushel of khaki-coloured grass that stands about two and a half metres or more than eight feet high. The tree intersects with another maple tree with brown and tan leaves that is about ten metres or 33 feet tall with more massive greyish trunk and branches. Immediately to the right again and partly intersecting with the maple tree, there is an even unidentified tree, about 17 metres or 56 feet tall, with grey bark on a fairly slim trunk and a messy crown of dark, brownish-green leaves which are so small that the texture makes it impossible to tell individual leaves. This tree is partly hidden behind the building already. It has another two bushels of the same tall grass underneath it which, due to the point of view, only seem to stand immediately to the right of the trunk.
Behind this vegetation, right below the crowns of the trees, the horizon separates the sky from the sea. What little sea the image shows is medium light blue. The sky right above the horizon is very light cyan, and around half the height of the image, it gradually changes into a tone of blue similar to that of the sea. From the top left corner of the image downward and to the right, more than half of the sky is covered by a cirrus-like thin cloud with a small hole above the roof end of the main building. On the right, the cloud dissolves into smaller clouds above the geodesic dome and the surrounding thin cones.
Further additions to the Universal Campus include five easels of the same type as seen inside, but with custom writing in it. They are lined up next to each other in front of the northeastern planter, starting right next to the wide path towards the main entrance. The writing on all five easels is done in black and in an unidentified humanist sans-serif typeface which appears condensed due to the texture having been stretched vertically, thus losing its original aspect ratio. Only the writing on the first of the five is visible from the camera's point of view, though. It reads in three lines, "To download a free copy of the Universal Campus Var Region." This is followed by a blank line and one more line that reads, "Click here for notecard". Upon clicking the easel, it gives the avatar a notecard with an Amazon cloud storage URL following an explanation that it contains the Universal Campus as a varregion archive and followed by a full copy of the Creative Commons Attribution-ShareAlike 3.0 Unported license.

Around the main landing area and the main building

Due to limitations in construction with prims, the ground of the main landing area is slightly higher than that of the three paths which lead away from it. The widest one of these paths is about one third of the diametre of the landing area in average width that leads to the main entrance. It is trapezoid in shape, and its sides line up with the centre of the main landing area. Two more trapezoid paths, also widening with the distance from the centre of the main landing area but only half as wide as the first one, lead westward and eastward from an imaginary point a little north from the centre of the main landing area. The western one is not visible in the image except for on the aerial view on the teleporter. The eastern one makes up most of the foreground along the bottom edge of the image.
On the outer corner of the northeastern planter on the eastward path, there is a lamp post standing on an almost white, cylindrical concrete block of about 1.80 metres or six feet of both height and diametre. From the camera perspective, it is in front of the main building and near the westernmost front column. It appears to be almost parallel with the column, but the lamp post is vertical while the column is tilted roughly northwestward.
The lamp post itself is about seven and a half metres or 25 feet high and very slightly conical with an elaborately-shaped round foot. At the top, it describes a sharp 90-degree angle towards the path, rounded on the outside, forming a corner on the inside. It then extends conically towards the path by another roughly 1.50 metres or five feet before ending in a small sphere. The bottom of the sphere is flattened, and the actual light source is installed on this flat surface. It is round, glowing and emitting slightly yellowish light. The rest of the lamp post is light grey or white and highly glossy.
The walls lining the paths to the sides of the main landing area rise no more than about 30 centimetres or one foot above the paths themselves while being twice as wide.
In the bottom right corner of the image, the path to the east intersects with a circular path around the main landing area that begins and ends near the southern side entrances of the main building. Its centre is some ten metres or 33 feet north of that of the main landing area, and its outer diametre is about 100 metres or 330 feet. Due to the aforementioned limitations, it is a little bit higher than the trapezoid spoke path at the bottom. Its walls rise about 60 centimetres or two feet above itself and about 80 centimetres or a little less than three feet above the path to the east, and they are about 2.40 metres or eight feet wide.
Between the main building, the path to the main building, the planter northeast of the main landing area, the path in the very foreground and the circular path on the right, a large patch of sim ground is still unused. It shows a green texture with some slightly darker or minimally more yellow-ish areas. The texture has a fairly low resolution. It is coarse and blurry, and at the same time, even this patch of ground reveals the repeating texture tiles. The ground itself is rather bumpy as though it has been manually treated to be like this. All the same applies to the corresponding area to the west of the path to the main building of which fairly little of it is revealed in the image.
Right before its end near the right-hand entrance, the circular pathway first branches diagonally to the right to another path three small steps down. On both corners of this junction, there are fairly cylindrical platforms inserted into the walls. Both have a diametre of about 3.60 metres or twelve feet and a height of about 1.20 metres or four feet above the branched-off path or a bit under 90 centimetres or three feet above the circular path. The walls along the branched-off path are fairly small, only some 45 centimetres or one and a half feet high and about 60 centimetres or two feet wide.
After about 15 metres or 50 feet of length, the branched-off path continues down a set of stairs. Due to how low the camera position is, the stairs itself are hidden from the camera, but the block and guide rails along the far side of the stairs, the northwestern side, are not. The block is the same shade of grey as the surfaces of the paths. It serves as a primary guard on the sides of the stairs. It is about 90 centimetres or three feet wide. It ascends from the usual wall on the side of the path which it overlaps by the same amount on both sides, and it does so at an angle of roughly 25 degrees. It reaches its peak right above where the stairs start at a height of about two metres or six and a half feet above the path. From there, it descends at an angle of about 35 degrees which, curiously, is a little less steep than the stairs themselves.
The guide rails are dark blue flat slabs, about 30 centimetres or one foot wide and about seven and a half centimetres or three inches thick. They come in stacks of four, arranged above one another with round about one and a half times the thickness of one rail worth of space between them. They are parallel to the descending surface of the block. The lowest one has a distance to the block of circa 30 centimetres or one foot. Each set of rails is held together and in place by two shiny, textureless blocks of 120 centimetres or four feet of height and a square top surface which, however, slightly narrows downward to the large concrete block below when looked at from parallel to the rails. Upstairs, the four rails extend beyond the stairs by roughly seven and a half metres or 25 feet. Their upper ends are lined up almost exactly vertically. The whole arrangement is slightly shifted out of centre on top of the block, away from the stairs. A second, identical set of rails is installed further downstairs for no apparent reason other than looks. Such rails are actually on both sides of the stairs, but the image only shows them on one side.
Shortly before the stairs, one lamp post like the one is installed on the wall on each side of the path towards the stairs, complete with the cylindrical block underneath. In the image, the lamp post on the right with the exception of the foot and the cylindrical concrete block underneath is almost entirely obscured by two trees. One is identical to the tree with the chaotic brownish-green leaves to the left that is partly hidden behind the main building. It has another bushel of grass around where its roots were if it had any. Another much larger one is standing to its right, its trunk and most of its crown outside the image already. It is unidentified, too, but it shows some signs of being an acacia tree. Its bark is mostly greyish-brown with some rusty red patches on it. Its leaves are long, pointy and various tones of pale light to not-quite-as-pale medium green.
Immediately after the path towards the stairs branches off, the circular path leads into a straight path that runs parallel to the eastern side of the main building. The walls on its side have the same size as those on the sides of the circular path. On both of its ends, short, wide platforms lead to the side entrances of the building, connected to the path via two small steps each. These platforms do not have walls on their sides. At the far end, the straight path leads into another circular path, this time around the conference hall.
Some more vegetation is to the right of the path along the eastern side of the main building, all standing on sim ground. Right behind the unobstructed lamp post next to the path that leads downstairs, there is a fairly large unidentified tree that almost reaches the edge of the roof of the building. Its crown has rather dense foliage in a quite saturated medium green tone. The bark texture on its thin trunk and branches is mostly taupe with bits of copper brown and fairly smooth except for long dark rifts along the trunk and the branches as well as a few dark holes.
Behind the block and the dark blue rails along the stairs by the right-hand edge of the image, a gigantic version of the unidentified shrubs in the planters is located on the edge of the downhill slope which necessitates the stairs. It is about five and a half metres or eighteen feet high, and its flowers are up to 60 centimetres or two feet in diametre.
Farther in the background, also behind the lamp post and a little behind the shrubs, there is a group of seven pine trees of varying size. They have semi-transparent, conical surfaces around their trunks with textures which give the impression of very dark green needles. There are also bushels of tall grass on the ground between the pines.
Lastly, one of the four main light sources is the simulated Sun. Since it is shortly before noon, it is standing almost vertically above the sim and shining what is technically grey light down on it. The sim uses OpenSim's default daycycle in which the Sun always goes through the zenith. The same applies to all converted older daycycles originally available in OpenSim. The Sun is also the only light source on the sim whose light casts shadows. The other four main light sources are three types of ambient light in darker taupe, bluish slate grey and Prussian blue. These three neither have a specified direction of light, nor do they produce any shadows.

(3/6)
# # # # # # # # Allow me to give you an example.
This is the image I'm talking about: (linked instead of embedded so I don't have to go through the hassle of having to describe it right here right now).
This is the thread in which I've posted the image before, including image descriptions, also including a comment with the AI description and an analysis of the AI description in comparison with my own descriptions: (yes, this is part of the Fediverse it's on the same Hubzilla channel that I'm commenting from right now).
(2/6)
# # # # # # # # # # # # # # # # # # I've pitted an image-describing LLM AI against my own 100% hand-written image descriptions twice so far. I have first described an image myself, twice even, with a "short" description for the alt-text and a long, fully detailed description with text transcripts and all necessary explanations for the post text.
However, I'm always at an unfair advantage. My images are renderings from very obscure 3-D virtual worlds. LLMs know next to nothing or actually nothing about these worlds whereas I dare say I'm an expert on them. An AI couldn't even tell whether the image is from a game or from a virtual world, much less which virtual world. I can not only exactly pinpoint where the image was taken (which place on which sim in which grid), but also explain the location and these virtual worlds in general.
Besides, an AI would describe the image by examining the image. I describe my images by going in-world and looking at the real deal instead of at the image of it. I can see everything at a vastly higher resolution. I can transcribe text that is so tiny in the image that it's invisible. I can even look around obstacles and see what's behind them if necessary. No LLM AI can do any of this.
(1/6)
# # # # # # # # # # # # # # Only if you have a significant number of following connections, though.
And if you're on Mastodon. My experience is that roughly the same number of following connections gives you much more reach if you're on Mastodon than if you're on e.g. Hubzilla.
And if you always play by Mastodon's unwritten rules and refrain from doing anything in your posts and comments that's impossible on vanilla Mastodon, including exceeding 500 characters, regardless of how many characters you could actually post.
I mean, I put more effort into image descriptions than anyone else. But the reach of my two channels on (streams) for image posts (, ) is so minuscule that I'm not sure if it really makes so much of a difference. Maybe the advantage I get by adding accurate, sufficiently detailed, 100% hand-written alt-texts to all my images is defeated by the long visual descriptions and explanations that inflate my posts to thousands or tens of thousands of characters.
# # # # # # # # # # # # # # # # # # # "Forkey" bezeichnet Forks von Misskey, Forks von Forks von Misskey usw.
Iceshrimp.NET fllt da nicht drunter, weil es komplett neu geschrieben wird. Es ist vom Funktionsumfang her noch ziemlich mager. Das Ziel des Rewrite war, soweit ich wei, zum einen, die Macken loszuwerden, die alle Forkeys von Misskey geerbt hatten, und zum anderen von JavaScript wegzukommen (Misskey und alle Forkeys sind in TypeScript und Vue.js geschrieben).
Aber gut, es gibt auch viele, die sich nicht vorstellen knnen, da gute Serversoftware in PHP geschrieben sein kann. Mike Macgirvin entwickelt seit jeher in PHP. Und was er baut, ist nicht nur sehr mchtig und fortschrittlich, sondern auch noch leicht zu installieren und zu administrieren und weniger leistungshungrig als Mastodon.
auf meinem Fediverse-Meme-Kanal.
# # # # # # # # # # # Add your location to a Google Map

<>

Was jetzt, Friendica oder Hubzilla
Jedenfalls hatte Mastodon in mehrerlei Hinsicht Glck.
Erstens sind schon 2016 die deutschen Medien auf Eugen Rochkos Werberei fr Mastodon angesprungen, als Twitter noch gut war. Das hat Mastodon einen ersten riesigen Popularittsschub gegeben.
Zweitens hat der aber nicht auf das brige Fediverse abgefrbt, auch deshalb, weil seit damals das Fediverse entweder komplett ignoriert oder als das Mastodon-Netzwerk angesehen wird, also als "dezentraler Walled Garden". Bis heute glaubt so ziemlich jeder Mastodon-Newbie, das Fediverse bestnde nur aus Mastodon, und Mastodon sei das einzige dezentrale Netzwerk berhaupt. Dieser Glaube verbreitet sich schneller, als man dagegen ankommen kann.
Drittens hat Mike Macgirvin, der zum einen schon 2010 Friendica ins Leben gerufen und zum anderen auch schon 2015 Hubzilla gestartet hat, immer gesetzt auf "Wenn du es baust, werden sie kommen". Er hat bis 2023 nie fr irgendwas geworben und auch ab 2023 nur zaghaft und nur innerhalb des Fediverse.
Deswegen glauben viele, der beste Facebook-Ersatz im Fediverse ist Mastodon, weil sie noch nie von Friendica gehrt haben. Deswegen wissen selbst die Tech-Medien nicht, da es fr Friendica lngst freien, quelloffenen, dezentralen Ersatz la Mastodon gibt, der sogar mit Mastodon verbunden ist. (brigens ist auch Hubzilla nicht das Ende der Fahnenstange. Mike hat danach noch weitergemacht und noch andere Sachen rausgebracht, von denen (streams) und Forte heute noch existieren (wobei Forte ja erst 2024 entstand und 2025 den ersten stabilen Release hatte). Die kennt aber endgltig keiner.)
Deswegen geniet auch Bonfire so eine groe Popularitt auf Mastodon. Die htte es nicht, wenn mehr Mastodon-Nutzer wten, da Bonfire im Grunde Hubzilla auf Wish bestellt ist. Was Bonfire jetzt versucht, hat Hubzilla vor zehn Jahren schon geschafft, noch bevor es Mastodon gab. Das und noch mehr obendrauf.
Viertens wre die Zielgruppe fr Friendica nicht der Twitter-Nutzer, sondern der Facebook-Nutzer. Aber Facebook ist noch nicht zu so einer unertrglichen Nazi-Bar geworden wie Twitter, so da der Fluchtdrang lngst nicht so gro ist.
Fnftens bekommt man Leute aus Facebook eh schwerer raus als aus Twitter. Twitter ist ein soziales Medium. Da zhlt nicht, wer dir folgt, sondern wieviele dir folgen. Und da geht es auch nicht um Kontakt und Interaktion, sondern um das Rauspumpen von Content.
Facebook ist dagegen ein soziales Netzwerk. Da gibt es nicht Followers und Gefolgte, sondern "Freunde", also bidirektionale Kontakte. Und da geht es eben genau darum, mit wem man "befreundet" ist. Im allgemeinen ist man auf Facebook nmlich "befreundet" mit Leuten, die man eh schon von woandersher kennt.
Die typische Hrde, von Twitter nach Mastodon zu gehen, ist, da da insgesamt nicht genug Leute sind und man einfach nicht die 850.000 Follower zusammenkriegt, die man auf Twitter hat.
Die typische Hrde, von Facebook nach Friendica zu gehen, ist, da da die eigenen Real-Life-Kumpels nicht sind. brigens war das 2007 auch das Argument, weshalb niemand von StudiVZ/MeinVZ oder Wer-kennt-wen zu Facebook wechseln wollte: Die eigenen Real-Life-Kumpels waren nicht auf Facebook, also war Facebook nutzlos.
Sechstens schreckt an Friendica ab, da die Weboberflche in den frhen 2010ern stehengeblieben ist. Die von Hubzilla auch, und noch dazu ist die von Hubzilla ziemlich konfus und eine regelrechte Kapitulation vor Hubzillas Funktionsumfang, weil teilweise die Bedienelemente neuer Features planlos mal hier, mal da angeklebt worden sind.
Siebtens gibt es weder im Apple App Store noch im Google Play Store eine App namens "Friendica" oder "Hubzilla". Wenn es keine App namens "Mastodon" gbe, wre Mastodon auch nur einen Bruchteil so gro wie jetzt. berhaupt gibt es einfach mal so installierbare Smartphone-Apps fr Friendica nur fr Android, nicht aber fr iOS, und fr Hubzilla gleich gar nicht.
Achtens: Wenn Mastodon-Nutzer von Hubzilla schreiben, dann am ehesten davon, wie kompliziert und wie schwierig zu handhaben es ist. (Wenn Hubzilla-Nutzer von Hubzilla schreiben, kriegt das kurioserweise auf Mastodon kaum jemals jemand mit.) Zugegeben, Hubzilla ist kein Fall von "Website laden, registrieren, loslegen" und schon gar kein Fall von "App laden, registrieren, loslegen".
Neuntens glaube ich, Hubzillas eigene Community ist ein bichen hin- und hergerissen zwischen "Hubzilla mu populrer werden und braucht mehr Werbung", "vorher mu auf Hubzilla noch dies und das und jenes verbessert werden, damit es tageslichttauglich wird" und "fr viele Use-Cases wre Hubzilla Overkill und (streams) oder Forte eigentlich sogar besser, die sind ein ganzes Stck eleganter und moderner in der Handhabe, und die haben auch mehr Nutzer verdient".
CC:
# # # # # # # # # # # # # Wieso ausgerechnet Mastodon Wieso nicht etwas Leistungsfhigeres wie Sharkey oder Akkoma oder so
Ich sage ja nicht gleich Hubzilla. Aber warum mssen sich noch mehr Leute diese unterausgestattete Software antun und dann glauben, das Fediverse sei nur diese unterausgestattete Software und habe insgesamt nur die Features dieser unterausgestatteten Software
Das wre jetzt die Chance gewesen, Leute ins Fediverse zu holen und dann direkt auf etwas, was von vornherein eine vernnftige Ausstattung hat. Ich habe wei Gott gengend schlechte Erfahrungen gemacht mit Leuten, die monate- oder jahrelang glaubten, das Fediverse sei nur Mastodon, und dann ihren Erstkontakt mit dem Nicht-Mastodon-Fediverse hatten.
# # # # # # # # # # # # # The categories are not about how well something works together. They're only about how something is perceived by the majority of the Fediverse, i.e. Mastodon.
The second category means that Mastodon users perceive it as something that was explicitly created as a third-party add-on to Mastodon, like an extra feature that was bolted onto Mastodon.
Like, Pixelfed is seen as a Mastodon add-on that adds Instagram functionality to Mastodon. PeerTube is seen as a Mastodon add-on that adds YouTube functionality to Mastodon.
This is why so many Mastodon users try to log into Pixelfed with their Mastodon accounts: They actually think that Pixelfed is a Mastodon add-on, just like Friendica, Hubzilla and the like do actually have add-ons, just not off-site, but on the same server.
Basically, the next step after seeing the Fediverse as only Mastodon is seeing the Fediverse as Mastodon with extra stuff bolted on.
I cannot see PieFed being perceived as a Mastodon add-on that was created as a Mastodon add-on to add Reddit functionality to Mastodon.
In fact, it cannot be seen as a Mastodon add-on because, by its features and functionality, it can replace Mastodon. Technically speaking, it's a direct competitor of Mastodon, and Mastodon's competitors cannot rank higher than 3rd class. I mean, why would someone build a Mastodon add-on that can also do the same stuff as Mastodon
Besides, if it ranked higher than third class, it'd be as well-known as Pixelfed and PeerTube, when in reality, it isn't even as well-known as Lemmy which is third-class, too.
If it was more well-known, Mastodon users wouldn't sit and wait for "the Fediverse" (= Mastodon) to introduce groups. Rather, it'd be common knowledge that PieFed has groups. PieFed would be seen as the drop-in replacement for a.gup.pe, and everyone on Mastodon would agree that FediGroups is a dirty kluge.
Rather, it isn't even common knowledge that Friendica has groups, and it isn't common knowledge either that Friendica is federated with Mastodon. I speak from personal experience here.
# # # # # # # # # # # The categories are not about how well something works together. They're only about how something is perceived by the majority of the Fediverse, i.e. Mastodon.
The second category means that Mastodon users perceive it as something that was explicitly created as a third-party add-on to Mastodon, like an extra feature that was bolted onto Mastodon.
Like, Pixelfed is seen as a Mastodon add-on that adds Instagram functionality to Mastodon. PeerTube is seen as a Mastodon add-on that adds YouTube functionality to Mastodon.
This is why so many Mastodon users try to log into Pixelfed with their Mastodon accounts: They actually think that Pixelfed is a Mastodon add-on, just like Friendica, Hubzilla and the like do actually have add-ons, just not off-site, but on the same server.
Basically, the next step after seeing the Fediverse as only Mastodon is seeing the Fediverse as Mastodon with extra stuff bolted on.
I cannot see PieFed being perceived as a Mastodon add-on that was created as a Mastodon add-on to add Reddit functionality to Mastodon.
In fact, it cannot be seen as a Mastodon add-on because, by its features and functionality, it can replace Mastodon. Technically speaking, it's a direct competitor of Mastodon, and Mastodon's competitors cannot rank higher than 3rd class. I mean, why would someone build a Mastodon add-on that can also do the same stuff as Mastodon
Besides, if it ranked higher than third class, it'd be as well-known as Pixelfed and PeerTube, when in reality, it isn't even as well-known as Lemmy which is third-class, too.
If it was more well-known, Mastodon users wouldn't sit and wait for "the Fediverse" (= Mastodon) to introduce groups. Rather, it'd be common knowledge that PieFed has groups. PieFed would be seen as the drop-in replacement for a.gup.pe, and everyone on Mastodon would agree that FediGroups is a dirty kluge.
Rather, it isn't even common knowledge that Friendica has groups, and it isn't common knowledge either that Friendica is federated with Mastodon. I speak from personal experience here.
# # # # # # # # # # # Hubzilla ist die mchtigste Fediverse-Software berhaupt.
Vergleichen wir es mal mit Mastodon.

• Es ist zehn Monate lter als Mastodon.
  Es wurde im Mrz 2015 releaset.
  Dafr wurde es aus etwas umgebaut, was 2012 umgeschrieben wurde aus etwas, was 2011 von etwas geforkt wurde, was 2011 vom schon 2010 gestarteten Friendica geforkt wurde.
  Das heit, sein Familienstammbaum fngt fnfeinhalb Jahre vor Mastodon an.
• Es wird unabhngig von Mastodon entwickelt und nicht etwa als Extra oder Erweiterung fr Mastodon.
• Es kann sich trotzdem mit Mastodon verbinden. Und mit diaspora*. Und mit einigen anderen Sachen. (Dieser Kommentar kommt brigens von Hubzilla.)
• Es war die erste Serveranwendung berhaupt, die ActivityPub untersttzte (seit Juli 2017). Mastodon war die zweite (seit September 2017).
• Es braucht kein Ruby on Rails. Es ist fast komplett in PHP gebaut.
• Es ist mchtiger als alles andere im Fediverse von Mastodon ber Friendica bis Bonfire. Gleichzeitig ist es modular.
• Es ist kein bloer Twitter-Klon, sondern es kann eine Facebook-Alternative, eine vollwertige Blogging-Plattform, ein Cloudspeicher inklusive Kalender und Adrebuch, ein Host fr einfache Webpages und noch viel mehr sein.
  Die offizielle Hubzilla-Website () luft selbst auf einem Hubzilla-Kanal.
• Dein Konto/Login ist nicht deine Identitt. Deine Identitt ist von deinem Konto/Login entkoppelt.
  Du kannst auf einem Konto mehrere vllig voneinander unabhngige Kanle/Identitten haben.
  Du kannst Kanle komplett mit allem Drum und Dran auf andere Server umziehen.
  Du kannst Kanle sogar ber mehrere Server klonen und damit auf mehreren Servern gleichzeitig betreiben.
• Es hat viel umfangreichere Profile als Mastodon.
• Man kann mehrere Profile anlegen und die zustzlichen Profile bestimmten Kontakten zuordnen. (Funktioniert nur mit Kontakten, die bestimmte Fediverse-Anwendungen benutzen funktioniert nicht mit Mastodon-Kontakten.)
• Es ist extrem sicher. Es hat das zweitbeste Berechtigungssystem im Fediverse mit 18 verschiedenen Berechtigungen auf bis zu drei Ebenen (fr den ganzen Kanal, pro Kontakt, inhaltsbezogen). Das schliet sogar Antwortenkontrolle ein.
• Es hat nicht 500 Zeichen, sondern 16,7 Millionen.
• Es kann pro Post nicht vier Bilder haben, sondern unbegrenzt viele.
• Es kann Bilder nicht einfach nur als Dateianhnge an den Post anhngen, sondern sie mitten in den Post-Text einbetten, also mit Text darber und mehr Text darunter oder kleine Bilder auch mitten in der Zeile. Das kann Mastodon nicht mal anzeigen.
• Es kann mehr Textformatierung erzeugen, als Mastodon anzeigen kann.
• Es kann Titel. Mastodon kann die normalerweise nicht mal anzeigen.
• Auf Mastodon ist ein Thread lose mittels Erwhnungen aus einzelnen Posts zusammengezurrt.
  Auf Hubzilla ist eine Konversation ein in sich geschlossenes Gebilde mit genau einem Post und ansonsten Kommentaren, die immer dieselben Berechtigungen haben wie der Post.
• In der Mastodon-Timeline sieht man nur einzelne Beitrge.
  Im Hubzilla-Stream sieht man standardmig immer komplette Konversationen mit Post und Kommentaren.
• Wenn man erstmal einen Post im Hubzilla-Stream hat, bekommt man auch alle Kommentare dazu.
• Es konnte schon immer quote-posten. Es kann auch Mastodon-Trts quote-posten, seit es Mastodon gibt. (Ernsthaft, Friendica kann seit 15 Jahren quote-posten.)
• Es hat Gruppen in verschiedenster Form.
  Moderierte Gruppen.
  Private Gruppen.
  Gruppen, die im Verzeichnis nicht angezeigt werden.
• Es hat sehr viel mehr Mglichkeiten, Posts an bestimmte Zielgruppen zu schicken, z. B. an eine bestimmte Liste oder an eine beliebige Kombination aus Kontakten und Listen, wo man dann sogar noch bestimmte Kontakte und Listen nachtrglich ausschlieen kann.
• Es hat viel mchtigere und gleichzeitig einfacher bedienbarere Filter als Mastodon:
  
  • nicht ein Filter pro zu filterndem Begriff, sondern eine Blocklist fr den ganzen Kanal, wo man einfach neue Schlsselwrter eintragen kann
  • zustzlich eine Allowlist fr den ganzen Kanal
  • optional zustzlich je eine Blocklist und Allowlist pro Kontakt
  • optional eine separate Filterliste, die bestimmte Inhalte hinter Inhaltswarnungen versteckt (so eine Funktion haben Mastodons Filter erst seit drei Jahren Friendica hat sie seit 15 Jahren)
  • regulre Ausdrcke in Filtern
  • Boolesche Funktionen in Filtern
  • mchtige Filtersyntax, die z. B. Boosts, Kommentare und Direktnachrichten erkennen kann
• Es hat einen eingebauten, fderierenden Event-Kalender. Also, zustzlich zum CalDAV-Kalenderserver. Mastodon kann mit Events nichts anfangen.
• Es kann RSS- und Atom-Feeds abonnieren.
• Es hat noch einiges mehr an optionalen Features, z. B. OpenStreetMap-Einbindung, nicht fderierende Artikel (die kann man, wenn man will, in Posts verlinken), Wikis, Planungskarten oder automatisch generierte QR-Codes.
• Es hat ein sehr flexibel konfigurierbares Standardthema, und es stehen inzwischen mehrere Third-Party-Themen zur Verfgung, die vom Serverbetreiber installiert werden knnen.

Links:

(kann man auch von Hubzilla und Mastodon aus folgen: hz-workshophub.hubzilla.hu)
(enthlt auch mglicherweise interessante Videos)

Direkte Vergleichstabellen zwischen

• Mastodon
• Friendica
• Hubzilla
• (streams) (= Fork eines Fork dreier Forks eines Forks (eines Forks) von Hubzilla)
• Forte (= Fork von (streams))

(die sind brigens auch auf Hubzilla)
Hier mal ein paar mehr Kontaktempfehlungen:



# # # # # # # # # # # # # # # # # # # # # # # # # # # # I will continue to describe my images by hand. I will not resort to have them described by an AI, no matter how much time that'd save. I see more than any AI because while the AI only has the image, I can look at the real deal. And I know more about the topic than any AI ever will.
AI can't pinpoint where exactly I've taken an image because it knows nothing about the worlds that my images are from. I can, and I will, and while I'm at it, I'll explain the location down to the very basics.
AI doesn't know what an OpenSimWorld beacon is. I know, and I can and will explain it.
AI can't transcribe the text on a sign that's a four-by-three-pixel blot in my image. I can and will transcribe it because when I look at it in-world, I can see its 1024-by-768-pixel texture in all its glory.
As for WCAG: They don't cover the special case of 3-D virtual world renderings posted into the Fediverse from something that is not Mastodon, and that offers vastly more characters than Mastodon.
The only alternative to posting my images with hand-written descriptions is to not post them at all.
# # # # # # # # # # # # # # # # # # # Actually, I strongly recommend not to explain images in the alt-text, and I strongly recommend not to add any other exclusive information in the alt-text that is neither in the image not in the post. That's because not everyone can access alt-text. For example, depending on the frontend, reading alt-text may require at least one working hand, so a physical disability may make alt-text inaccessible to certain people.
So explanations and the like must always go into the post text. Granted, that's often easier said than done. Mastodon has a hard-coded character limit of 500, changing which technically speaking requires a soft fork. Sharkey has a configurable limit that defaults to 3,000. I'm on Hubzilla whose character limit is imposed by the database, and it's over 16.7 million.
That said, I myself always have a lot to write when I post images which is why image posts from me are extremely rare. I've only posted new images twice in 2025 before anyone goes looking for them, they aren't on this channel.
That's because when I post an image, it's always about a very obscure topic. It's either a meme about the Fediverse where Fediverse does not mean only Mastodon. Or it's a meme about usually super-obscure 3-D virtual worlds. Or it's an in-world rendering from one of these super-obscure 3-D virtual worlds, and these image posts need the most work.
Whenever I post images, I follow three premises.
One, next to nobody knows anything about the images in and the topic of my post. After all, just about anyone anywhere in the Fediverse could be my audience. For my virtual world pictures, this means that those who can't see them don't even have a remote idea what anything in them looks like.
Two, on the other hand, my posts about virtual worlds demonstrate something highly unexpected: 3-D virtual worlds, something that was considered the hottest thing ever in the early 2020s and that's now widely considered dead, are not dead after all. So while people don't know anything about them, they might pretty well be super-curious about them.
Three, especially some Mastodon users don't like to look up for themselves what they don't know. And they don't like to ask either. They prefer all information necessary to understand a posed served to them on a silver platter right away in the same post. This goes even more for image descriptions: Having to ask for a detail to be described is almost as bad as having to ask for an image description in the first place.
This means that my meme posts come with appropriate alt-texts including transcripts of all relevant text for all images. But they also come with explanations for a) the meme templates and b) the topic in the post text. I simply cannot assume that absolutely everyone who comes across the post will be familiar with both and able to understand my post with no explanations.
That is, if I can link to useful explanations, I do so. This means that I always link to KnowYourMeme for meme template explanations. And if I can link to someplace that explains or helps explain the topic, I do so as well. But if I can't, I write my own explanations, and I often have to do that. This leads to posts with several thousand characters worth of explanations.
When I post original images from within virtual worlds, it gets even worse. Not only does next to nobody know anything about these worlds, but nobody who can't see the image knows what anything in the image looks like. But they may be curious about what everything in the image looks like because they may be curious about these virtual worlds in general.
In addition, when I post an image from a virtual world, I often don't want to show just one specific element of the image. I rather want to show the entire scenery with everything in it. So there isn't that one element in the image that's important within the context of the post because everything in the image is important within the context of the post all the same. Even more so to those who are super-curious.
So I end up having to describe these images twice.
I start with a fully detailed description that includes everything within the borders of the image. It also includes transcripts of any and all text that's at least partially within the borders of the image, regardless of whether or not it can be read in the image itself. If I can read it in-world, I will transcribe it. And it includes all necessary explanations.
This description alone usually ends up exceeding all known character limits in the Fediverse by magnitudes. For example, it always takes me well over 1,000 characters alone to explain where the image was made. I've once had to describe an in-world object that doesn't exist in real life, and I ended up describing what it looks like in over 1,000 characters and explaining what it is and what it does in another over 4,000 characters. All in all, the long description regularly ends up tens of thousands of characters long. It goes into the post text, of course. I guess it inflates my posts to such sizes that Misskey and its forks reject them due to being too long.
But I also need an appropriate image description in the alt-text. So I start with an explanation that there is a longer, more detailed image description with text transcripts and explanations in the post text itself and where and how to find it this is a relic from times when Mastodon only hid the post text behind a content warning, but not the images. Then I take the long description and distill a shorter one from it, short enough that this description plus the note about the long description aren't longer than 1,500 characters.
Some people say it takes 20 seconds to describe an image. Well, it tends to take me literal days to describe one virtual world rendering. I haven't posted any virtual world images since 2024 because I have had the image descriptions for a series of avatar portraits in the making since late 2024.
(By the way: Don't go looking for image posts on this channel. I no longer use Hubzilla for posting images because Hubzilla can't make Mastodon blank out sensitive images. (streams) can do that, and so I use two separate (streams) channels for posting images now: for virtual world images and virtual world memes and for Fediverse memes.)
# # # # # # # # # # # # # # # # # # #

Time keeps moving forward : : /11: : 1930 sec: 2025-12-08:

In other news:
Christmas is over, and so is almost the year. Snow-covered themes are being shut down again, and it won't be long after New Year's Day that OpenSim is back to its usual eternal summer until October. And then we'll have one month of autumn in a few places because autumn and Halloween are basically the same here.
Good thing there are a few exceptions. 's Novale on his own grid probably still changes its seasons along with real-life Qubec. Jimmy Olsen's Norge in the Wolf Territories shares its weather and daycycle with real-life northern Norway his Alfheim used to do the same. And there are a few permanent winter or Christmas places Dorenas World has three of them.
# # # # # # # # # # # # #In other news:
Christmas is over, and so is almost the year. Snow-covered themes are being shut down again, and it won't be long after New Year's Day that OpenSim is back to its usual eternal summer until October. And then we'll have one month of autumn in a few places because autumn and Halloween are basically the same here.
Good thing there are a few exceptions. 's Novale on his own grid probably still changes its seasons along with real-life Qubec. Jimmy Olsen's Norge in the Wolf Territories shares its weather and daycycle with real-life northern Norway his Alfheim used to do the same. And there are a few permanent winter or Christmas places Dorenas World has three of them.
# # # # # # # # # # # # # Yes, you do. And you'd better write good, accurate, sufficiently detailed alt-text by hand.
AI is not nearly reliable enough to describe every image properly. In particular, AI cannot describe images within the context of a post.
If you don't add proper alt-text to your images:

• People will give you unsolicited lectures on why alt-text is important.
• People will attack you.
• People will insult you as ableist.
• People will mute or even block you upon first strike. Like, you post one image without a good alt-text, and dozens or hundreds of Mastodon users will block you.
• If you're a repeat offender, people will talk about you and tell everyone how ableist you are for not providing proper alt-texts.

Judge for yourself whether not describing your images is worth all this.
# # # # # # # # # # # # # # # Because most went Instagram -> Pixelfed without ever having been on Mastodon.
As opposed to Twitter -> Mastodon -> being lectured about Mastodon's culture -> Pixelfed.
Not everyone in the Fediverse has first been on Mastodon. For example, many Friendica users came from Facebook, and they did so long before Mastodon was even launched. Most Hubzilla users got there from Friendica after having been on Facebook first.
Both Friendica and Hubzilla have their very own cultures that predate Mastodon's, and they will never throw away their own cultures in favour of Mastodon's. For that'd also mean abstaining from most of their own features because Mastodon's culture either doesn't cover these features or explicitly forbids them.
Just in case you wonder why image posts from one of these rarely have alt-texts.
(Sent from Hubzilla)
# # # # # # # # # # # # # # # # Und da wundern sich dann die Leute, warum ich teilweise 10, 15, 20 Hashtags oder mehr unter einem einzelnen Beitrag habe.
Die dienen mindestens zur Hlfte dazu, meine Beitrge zu filtern. Ich schreibe ja sehr viel Zeugs, was vielleicht nicht unbedingt jeder lesen will.
Beispielsweise schreibe ich hufig bers Fediverse, das heit dann aber nicht, da ich nur ber Mastodon und dann auch noch positiv darber schreibe. Wenn, dann schreibe ich entweder ber Sachen, die nicht Mastodon und deshalb ziemlich obskur sind, oder ber Mastodon eher negativ oder beides.
Generell schreibe ich hufig sehr lang. Da, wo ich bin (Hubzilla), gibt es weder ein 500-Zeichen-Limit noch irgendein definiertes Zeichenlimit noch eine Kultur, alles schn kurz zu halten. Das stt aber vielen Mastodon-Nutzern sauer auf, die der felsenfesten berzeugung sind, Eugen Rochko habe das Fediverse als Mikrobloggingdienst erfunden (hat er nicht). Also gibt's auch hier wieder Hashtags zum Filtern.
Was hier aber schon sehr viel lnger Teil der Kultur ist, als es Mastodon berhaupt gibt, ist, sich individuelle CWs mittels Wortfilter vollautomatisch generieren zu lassen, statt da sie im Zusammenfassungsfeld allen gleichermaen aufgezwungen werden. Deswegen dopple ich viele Hashtags mit "CW" am Anfang, um klarzumachen, da sie genau dafr sind. Diejenigen, die sich ihre eigenen CWs generieren lassen, knnen dann meine Hashtags dafr nehmen.
Dann kommt noch dazu, da es fr viele Sachverhalte einfach irre viele Hashtags gibt und ich nicht vorher wissen kann, wer jetzt welches dieser Hashtags filtert. Das fhrt zu noch mehr Hashtags zum Auslsen von Filtern.
Alleine, um einen Beitrag mit mehr als 500 Zeichen zu markieren, brauche ich vier Hashtags und noch einmal zwei dazu, wenn er auf Deutsch ist. Wenn ich generell ber das Fediverse schreibe, brauche ich noch einmal vier. Und so weiter.
# # # # # # # # # # # # # # # # # # # # Na ja, Plume hat einen speziellen Status.
Bei den *keys gibt's welche, die einfach eingeschlafen sind, bekanntesterweise Calckey. Ansonsten ist es blich, da Software offiziell abgekndigt wird (Firefish, /kbin, alles zwischen Hubzilla und (streams), letztilch auch Lotide, irgendwann auch Iceshrimp-JS etc.), wenn die Entwicklung eingestellt werden soll.
Plume ist ja eigentlich noch in Entwicklung, nur haben beide Entwickler im Moment keine Zeit dafr. Aber sie haben das Projekt nicht gnzlich aufgegeben, d. h. wenn sie wieder Zeit haben, wollen sie weitermachen. Das ist auch gut, weil Plume leider WriteFreely in kritischen Features (Kommentare, eingebauter Filespace fr Bilder) schlgt.
WriteFreely ist im Moment am ehesten interessant, wenn man den schlichten, aufgerumten Stil von Medium haben und eh keine Bilder posten will und auch an Kommentaren nicht interessiert ist. Auerdem kommt man nur schwer rein, was wohl daran liegt, da WriteFreely von Spambots berrannt wird.
Wer nicht selbst hosten will, ist im Moment bei Friendica oder Hubzilla am besten aufgehoben, je nachdem, wie man lngere Texte posten will.
# # # # # # # # # # # # # # Ideally, one day, the highly advanced permissions system available on Hubzilla (based on Zot, ActivityPub optional), (streams) (based on Nomad, ActivityPub optional) and Forte (based on ActivityPub) would be cast into one or multiple FEPs.
This would solve this issue by not only controlling who receives a DM, but also who is permitted to see the DM. In combination with FEP-171b Conversation Containers (which was invented on (streams), inherited by Forte and backported to Hubzilla), the permissions of the DM would be inherited by all comments and replies to the DM with no way of ever changing these permissions anywhere in the conversation.
See, if I send a DM to Alice and Bob, then only Alice, Bob and I are permitted to see the DM. Also, only Alice, Bob and I are permitted to participate in the conversation, and Alice, Bob and I can see each comment and reply, but only the three of us are permitted to see them. The entire conversation has the exact same permissions all over, inherited from the initial DM.
Anyone of us can mention Carol all we want. But that does not give her permission to see anything in the conversation, not even the comment/reply that mentions her. Once the initial DM is out, its permissions are set in stone, and it's also set in stone that any and all follow-ups in the same conversation have the same permissions as the initial DM.
This does not even require encryption. That said, at least Hubzilla does offer encryption on top of the permissions system however, it's only compatible within Hubzilla AFAIK.
# # # # # # # # # # # # # # # # # # # # # #Waiting (3).
It's 3D Saturday for me but I've decided to end up with (somewhat) last shot in 2025 (so far), which was done on December 17th. I don't have any new 3D shots anyway!
It wasn't a stroll, but rather an idea for a long exposure that I've been thinking of for a while. As soon as I got ready to leave the house to the playground around the corner, it started to rain. However, I've decided to continue, putting the camera under my jacket to protect it from the rain, while other stuff in a plastic bag.
The idea was to do a long exposure for this playground leaving the breeze or wind to shake the swings. Strangely, it was raining, but not much wind or breeze going on. The shade was also leaking here and there and I was afraid water would come down on the camera. It was all before 5 a.m. already and too dark for my eyes to discern details. Unfortunately, I've wasted a lot of time trying to figure out a way to block the flare from a light on the far left. Finally, I couldn't find a way to block it properly except to stand there. The exposure was about 9 minutes.
Finishing the first exposure, I've turned the camera away to the right, in hope that I would catch something interesting (like effects of the hammering rain), again for 9 minutes. Originally, the plan was actually for 2 separate shots, but then decided to merge them in a panorama of 2 images since there was a proper overlap between the two shots. With all of that, there was a considerable struggle to counteract the effect of the flare or blown out highlight on the far left. I regret though not including all of the seesaw on the far right - but that would have required another 9 minutes exposure with a third shot.

: Ancien commissaire au March intrieur, figure cl des rglements sur le numrique (DSA, DMA). et : Co-directrices de .

It doesn't fit the timelines in the official Mastodon phone app. Which has the only Fediverse user interface out there that cannot fold longer posts in.
The Mastodon Web UI can do that. All third-party Mastodon apps can do that. The Web UIs of just about the whole rest of the Fediverse from Pleroma and Misskey to Friendica and Hubzilla can do that. Phone apps for stuff that isn't Mastodon can do that.
Only the haphazardly developed official Mastodon app can't do that because it's geared towards a Fediverse with only 500 characters, a Fediverse of a kind that has never existed.
Mastodon is not the reference implementation of the Fediverse. And the official Mastodon app is not the reference implementation of Mastodon apps, much less of Fediverse apps. It only exists for there to be something official named "Mastodon" in the Apple App Store and the Google Play Store.
Just because Mastodon tossed out a lack-lustre app in 2022 for those who absolutely need something named "Mastodon" on their phones to access the Fediverse, doesn't mean that Fediverse software that has existed for almost six years longer than Mastodon and twelve years longer than that app must adapt to the existence of that app and cut down its character limit from 16,777,215 to 500 for all those who can't use Mastodon through something with another name on it than "Mastodon".
By the way: Mastodon's way of cutting longer posts up into tiny chunks of no more than 500 characters goes onto the nerves of users of Pleroma, Akkoma, Misskey, Calckey, Firefish, Iceshrimp-JS, Iceshrimp.NET, Sharkey, CherryPick, GoToSocial, snac, Hollo, Socialhome, Friendica, Hubzilla, (streams), Forte and others. But they are not allowed to complain about that, much less tell Mastodon users who do that to move someplace that offers them more characters.
# # # # # # # # # # # # # # # # Fifth class. All of them.
As I've said, everyone talks about Mastodon as "the" Twitter alternative in the Fediverse. This means that microblogging server apps that aren't Mastodon, and that don't have the same level of publicity and fame as GoToSocial and snac, are next to unknown by Mastodon's standards.
Mind you, this ranking is extremely Mastodon-centred. But Mastodon-centrism has been the default in the Fediverse for many years now.
# # # # # # # # # # # Fifth class. All of them.
As I've said, everyone talks about Mastodon as "the" Twitter alternative in the Fediverse. This means that microblogging server apps that aren't Mastodon, and that don't have the same level of publicity and fame as GoToSocial and snac, are next to unknown by Mastodon's standards.
Mind you, this ranking is extremely Mastodon-centred. But Mastodon-centrism has been the default in the Fediverse for many years now.
# # # # # # # # # # #We have a five-class Fediverse nowadays.
First class: Mastodon. It's what everyone knows (everyone outside of Lemmy at least). It's what more Mastodon users than not take for the one and only Fediverse and ActivityPub gold standard (while literally nobody outside of Mastodon does, go figure). And it's the only Fediverse server application which many Fedizens take for the entire Fediverse. (Lemmings don't refer to Lemmy as the Fediverse, although many are still completely unaware that Lemmy is connected to anything else.)
Second class: the stuff that looks like add-ons glued onto Mastodon to enhance Mastodon. Pixelfed, an Instagram clone glued to the Twitter clone as an add-on. PeerTube, a YouTube clone glued to the Twitter clone as an add-on. Loops, a TikTok clone glued to the Twitter clone as an add-on. WordPress, a blogging engine and content management system eventually glued to the Twitter clone. I guess you get the idea.
It's only up to the second class that Fediverse server software is generally recognised and accepted from the usual Mastodon-centric point of view.
Third class: other halfway well-known "clones" of or replacements for corporate online platforms that do not look like they're glued onto Mastodon as add-ons. This is limited to the Threadiverse (Lemmy, what's left of /kbin, Mbin, PieFed) as Reddit replacements and Friendica as "the" Facebook replacement.
Fourth class: anything that doesn't fall into the first three classes, but that has enough publicity. Like Bonfire and WriteFreely. Also, minimalist stuff for self-hosters like GoToSocial and snac. Hubzilla is ever so barely teetering on this class, if at all.
Basically, it's only up to the fourth class that Fediverse server software is known at all.
Finally, fifth class: the whole rest. I mean, why is Mastodon known as "the" Twitter alternative in the Fediverse if there are loads of others that are better, more powerful, sometimes even closer to Twitter in certain features Why is Friendica known as "the" Facebook alternative in the Fediverse if Friendica's own creator has built a whole family tree of successors that outclass Friendica in various ways
# # # # # # # # # # # # # # # # # # # # # # # # # # # # #We have a five-class Fediverse nowadays.
First class: Mastodon. It's what everyone knows (everyone outside of Lemmy at least). It's what more Mastodon users than not take for the one and only Fediverse and ActivityPub gold standard (while literally nobody outside of Mastodon does, go figure). And it's the only Fediverse server application which many Fedizens take for the entire Fediverse. (Lemmings don't refer to Lemmy as the Fediverse, although many are still completely unaware that Lemmy is connected to anything else.)
Second class: the stuff that looks like add-ons glued onto Mastodon to enhance Mastodon. Pixelfed, an Instagram clone glued to the Twitter clone as an add-on. PeerTube, a YouTube clone glued to the Twitter clone as an add-on. Loops, a TikTok clone glued to the Twitter clone as an add-on. WordPress, a blogging engine and content management system eventually glued to the Twitter clone. I guess you get the idea.
It's only up to the second class that Fediverse server software is generally recognised and accepted from the usual Mastodon-centric point of view.
Third class: other halfway well-known "clones" of or replacements for corporate online platforms that do not look like they're glued onto Mastodon as add-ons. This is limited to the Threadiverse (Lemmy, what's left of /kbin, Mbin, PieFed) as Reddit replacements and Friendica as "the" Facebook replacement.
Fourth class: anything that doesn't fall into the first three classes, but that has enough publicity. Like Bonfire and WriteFreely. Also, minimalist stuff for self-hosters like GoToSocial and snac. Hubzilla is ever so barely teetering on this class, if at all.
Basically, it's only up to the fourth class that Fediverse server software is known at all.
Finally, fifth class: the whole rest. I mean, why is Mastodon known as "the" Twitter alternative in the Fediverse if there are loads of others that are better, more powerful, sometimes even closer to Twitter in certain features Why is Friendica known as "the" Facebook alternative in the Fediverse if Friendica's own creator has built a whole family tree of successors that outclass Friendica in various ways
# # # # # # # # # # # # # # # # # # # # # # # # # # # # # Flipboard nimmt vom Fediverse jenseits von Mastodon berhaupt keine Notiz. Fr die besteht das Fediverse nur aus Mastodon und Flipboard.
Dazu kommt erschwerend, da sie so corporate sind, da sie selbst etwas, was keinen CEO und keine Inc. hat, gar nicht als existent wahrnehmen.
Also tun sie, was die allermeisten Fediverse-Entwickler tun: Sie entwickeln nur gegen Mastodon. Nicht einfach gegen die Mastodon Client API, sondern auch gegen Mastodon-Interna und Mastodon-Spezifika.
Siehe vorher auch FediDevs, das sogar "Fedi" im Namen trgt, aber hart ausschlielich gegen Mastodon gebaut wurde, weil die Entwickler so lange der felsenfesten berzeugung waren, da das Fediverse nur das Mastodon-Netzwerk ist, bis es zu spt war. Weil das ganze Backend von FediDevs darauf ausgelegt ist, direkt gegen bestimmte Serversoftware gebaut zu werden statt gegen allgemeine Standards, mssen sie jetzt die Untersttzung fr jede einzelne Serveranwendung hndisch nachtrglich reinbauen.
# # # # # # # # # # # # # # #

His balls, his cock--his whole package--- is absolutely mouth watering!

hangers, cock, bush, face, chin, nose, nose = long cock, body, & pits, watering, as fuck

Eine beschreibt ein tragbares Gert zur Beurteilung von #Gebrechlichkeit, das in kleinen Invivo-Studien eine KI-Inferenz auf Gerten zu Gangbiosignalen mit hoher Rate durchfhrt und damit der GoldStandard-Gebrechlichkeitsdiagnostik entspricht, whrend es 10 Tage lang ohne Benutzerinteraktion kontinuierlich luft.

Eine zur kontinuierlichen berwachung der Vitalzeichen auf Station berichtet ber eine der ersten prospektiven Auswertungen automatisierter Warnungen in Krankenhausumgebungen, die auf eine frhere Erkennung einer Verschlechterung des Zustands des Patienten abzielen.

Neue legen nahe, dass passive, kontinuierliche Datenstrme die Erkennung von #LongCOVID-Phnotypen im Vergleich zur herkmmlichen Nachverfolgung allein verbessern knnen.

Irlanda, 1887 (Edwin , 1829-1891) coleccin privada Maestro de la pintura victoriana, especializado en historias y La mujer fue uno de sus temas pictricos favoritos

Whenever someone announces to "bring" something "to the Fediverse", chances are that Friendica has actually had it since 2010, for five and a half years longer than Mastodon has been around.
For example, just about everyone on Mastodon is fully convinced that Eugen Rochko has brought quote-posts to the Fediverse this year. That's because next to nobody on Mastodon knows that Friendica has been able to quote-post practically everything in the Fediverse, including Mastodon toots, for 15 years now.
And if Friendica doesn't have it, chances are still that Hubzilla has it, and that Hubzilla has probably had it for longer than Mastodon has been around, too.
For example, private messages that are actually private. Mastodon doesn't have them because the "privacy" of Mastodon DMs is only "guaranteed" by limiting whom a DM is sent to. Hubzilla does have them and has had them since 2012, since it was still named Red. How Because Hubzilla also limits who is permitted to see a DM.
Oh, and Hubzilla even offers optional encryption on top of that.
Or how about server-independent identity Everyone still waiting for Bluesky to finally be the pioneer who invents this and implements it for the first time LOL! Once again, Hubzilla has had this since 2012. Not a vague concept, not an unstable proof-of-concept, but daily-driven by production-grade channels on production-grade servers. (streams) has it, too, inherited from Hubzilla through a whole number of forks. Forte has it, too, and Forte is the first and, so far, only Fediverse server software that uses ActivityPub for nomadic identity.
Now I'm waiting for someone to announce that something will "bring" actual groups "to the Fediverse". A feature that was actually introduced to the Fediverse by StatusNet in 2008, and that's also available on Friendica, Hubzilla, (streams) and Forte. Not to mention that the very principle of the Threadiverse (Lemmy, the remains of /kbin, Mbin, PieFed) is based on groups.
This is what happens when you think that the feature set of the whole Fediverse is the feature set of Mastodon and maybe Pixelfed because that's all you know.
Speaking of Mastodon: Just because it's being "brought to the Fediverse", doesn't mean it'll be adopted by Mastodon.
# # # # # # # # # # # # # # # # # # # # # # # # # # #Whenever someone announces to "bring" something "to the Fediverse", chances are that Friendica has actually had it since 2010, for five and a half years longer than Mastodon has been around.
For example, just about everyone on Mastodon is fully convinced that Eugen Rochko has brought quote-posts to the Fediverse this year. That's because next to nobody on Mastodon knows that Friendica has been able to quote-post practically everything in the Fediverse, including Mastodon toots, for 15 years now.
And if Friendica doesn't have it, chances are still that Hubzilla has it, and that Hubzilla has probably had it for longer than Mastodon has been around, too.
For example, private messages that are actually private. Mastodon doesn't have them because the "privacy" of Mastodon DMs is only "guaranteed" by limiting whom a DM is sent to. Hubzilla does have them and has had them since 2012, since it was still named Red. How Because Hubzilla also limits who is permitted to see a DM.
Oh, and Hubzilla even offers optional encryption on top of that.
Or how about server-independent identity Everyone still waiting for Bluesky to finally be the pioneer who invents this and implements it for the first time LOL! Once again, Hubzilla has had this since 2012. Not a vague concept, not an unstable proof-of-concept, but daily-driven by production-grade channels on production-grade servers. (streams) has it, too, inherited from Hubzilla through a whole number of forks. Forte has it, too, and Forte is the first and, so far, only Fediverse server software that uses ActivityPub for nomadic identity.
Now I'm waiting for someone to announce that something will "bring" actual groups "to the Fediverse". A feature that was actually introduced to the Fediverse by StatusNet in 2008, and that's also available on Friendica, Hubzilla, (streams) and Forte. Not to mention that the very principle of the Threadiverse (Lemmy, the remains of /kbin, Mbin, PieFed) is based on groups.
This is what happens when you think that the feature set of the whole Fediverse is the feature set of Mastodon and maybe Pixelfed because that's all you know.
Speaking of Mastodon: Just because it's being "brought to the Fediverse", doesn't mean it'll be adopted by Mastodon.
# # # # # # # # # # # # # # # # # # # # # # # # # # # But this will take a lot of time. A whole lot of time.
The situation right now is still that Mastodon has considerably more users than the whole rest of the Fediverse combined. Within Mastodon itself, well over 90% of all messages are from Mastodon.
The majority of Mastodon users think the Fediverse equals Mastodon. The majority of the rest think the Fediverse equals Mastodon with PeerTube and Pixelfed and the like glued onto it as add-ons. The majority of those remaining cannot imagine for the lives of them that you can follow Friendica accounts from Mastodon because you can't follow Facebook accounts from either.
Apart from Reddit-to-Lemmy refugees, every single last Fediverse newbie enters the Fediverse via Mastodon without being told that the Fediverse is more than just Mastodon. In fact, many don't even learn about the Fediverse itself, only that there's a phone app named Mastodon that's allegedly "literally without Musk".
Remember the early days of smartphones When 99% of all commercial apps were only developed for iOS because developing for Android wasn't worth it, because Android was "too small"
You know when this changed This didn't change when Android had gained a significant market share. This din't even change when Android had a market share of over 50%. This only changed when the Samsung Galaxy S, one specific Android phone model, had been outselling the iPhone for long enough for market analysts to notice.
In Fediverse terms, this means it isn't sufficient for the non-Mastodon Fediverse as a whole to outgrow Mastodon in numbers of users or in content. Even if most content seen on Mastodon doesn't originate on Mastodon anymore, that wouldn't be sufficient to break Mastodon's dominance.
It's sad to say, but we need one Fediverse server application to outgrow Mastodon in users and activity. Ideally, that'd be a server application that's both standards-compliant and state-of-the-art in technology and blistering with technology that goes beyond Mastodon's wildest imagination.
In other words, what we need is to channel a Facebook exodus of several tens of millions of users to Forte. I'd say hundreds of millions to also outgrow Threads, but Threads will block every last Forte server because Forte is incompatible with Forte's federation requirements by its design and its philosophy.
Imagine a Fediverse in which, whenever one Mastodon user speaks of Mastodon as either "the Fediverse" or the best Fediverse software ever, two or three Forte users disagree.
Trouble is, Forte isn't fit to take a Facebook exodus infrastructure-wise. It doesn't have a single public, open-registration server. It probably has fewer than 20 daily-driving users, all of whom are on single-user servers.
This also means that nobody knows whether Forte is fit to take a Facebook exodus technology-wise. Nobody knows how many users a Forte server can handle if none has ever even had half a dozen users. And, in fact, nobody knows how well Forte's implementation of nomadic identity works if only Mike Macgirvin himself has evern cloned a Forte channel and even that only under lab conditions. I mean, why clone your channel when you can just as well back up the whole server because it's yours
(streams) doesn't look much better, unfortunately. It has about two public, open-registration servers. There should be another one in Europe, but it's currently broken. Otherwise, it's like Forte: People try it by first setting up their own server. And hardly anyone is willing to host a public one, much less enough of these for cloning to be viable. So, again, even (streams)' nomadic identity is only ever tested by Mike under lab conditions.
It doesn't help that both have only one developer who is officially retired.
As much as I personally love (streams) for being sleek and more fitting into today's Fediverse, it's probably Hubzilla that's the most solid candidate for a state-of-the-art Facebook alternative.
It's the most well-known of the bunch (except non-nomadic, account-equals-identity Friendica). It has been around for a decade. It has two main devs, none of whom have ever retired from Fediverse development. It has quite a bunch of open-registration hubs. It has enough active users for bugs to be spotted quickly and even a few who occasionally submit pull requests. It has an active community, albeit a small one, but better than having only a few dozen users world-wide. I've even read somewhere that Hubzilla needs fewer server resources than (streams). And yes, it's more versatile. Also, it has a community-maintained help system where (streams) and Forte barely have a public tech spec.
On the other hand, however, Hubzilla has the steepest learning curve in the whole Fediverse. It feels like geared towards Friendica converts first and foremost, although Friendica and Hubzilla have been developed away from each other.
Its default settings are still adjusted for a Zot-based "Grid" that was envisioned as a successor to the Federation in the first half of the 2010s, but not for today's ActivityPub-based Fediverse. This means that you will have to configure your brand-new channel before you can start using it. And there's nothing on Hubzilla's Web UI that tells you that you have to "install" an "app" to be able to connect to Mastodon. Not to mention that many permission settings are only available in the shape of templates rather than individual switches like on (streams) and Forte.
It's hard enough for Mastodon users who are already used to decentralised things to switch to Hubzilla, the difference in philosophy (Twitter clone vs grand-son of a Facebook alternative with a side of WordPress) notwithstanding. But it'd be considerably harder for Facebook users to switch to Hubzilla than it is for users to switch to Mastodon.
I can't see Hubzilla dominate the Fediverse for other reasons as well, even in the event of a huge Facebook exodus.
First of all, the vast majority of Facebook refugees will be on-boarded by people who barely or not at all know the Fediverse beyond Mastodon, and who therefore think that Mastodon is the Fediverse's only viable alternative to Facebook. And by people who may know that Friendica exists, but who want to stay in contact with their old Facebook friends, and who cannot imagine that you can follow a Friendica account from Mastodon. So these Facebook refugees will end up adding millions upon millions of new users to Mastodon.
Besides, the Friendica community will try to reel in as many Facebook refugees as possible. The Friendica community is bigger than the Hubzilla community. Also, they've probably got some considerable foothold on Facebook whereas your typical Hubzilla user is hardly anywhere else except maybe for an experimental (streams) channel. Friendica will use its advantage of being widely considered "the" Facebook alternative in the Fediverse.
At the same time, the Hubzilla community won't even know how to tackle this situation, much less profit from it. They'll probably get stuck in discussions that don't lead to anything productive, in this case also being hindered by the notion that "Hubzilla is not a social network" (even though it'd work just fine as one).
Lastly, people will join whatever has its own official app in the Apple App Store and the Google Play Store with the same name as the whole project and the server software. And that's Mastodon.
In the meantime, Friendica only has a bunch of third-party Android apps and a few semi-open beta iOS apps, but no official one named "Friendica". The other three have no apps at all, save for a Web-based Hubzilla app that hasn't seen any development activity in over six years. And the Hubzilla community can't even agree upon whether any Hubzilla app would be feasible in the first place, much less which features it has to include, also due to the false assumption that people will use the app only occasionally when they're out and about rather than daily-drive it as their only frontend.
# # # # # # # # # # # # # # #

Last updated: 2026-01-02

thinking