I'm not sure federation is that important on sites that aren't built around socializing. I think it is sufficient for a wiki to provide a good export mechanism so that it can be archived or mirrored by others.
this post was submitted on 30 Jun 2023
103 points (100.0% liked)
No Stupid Questions
34444 readers
1503 users here now
No such thing. Ask away!
!nostupidquestions is a community dedicated to being helpful and answering each others' questions on various topics.
The rules for posting and commenting, besides the rules defined here for lemmy.world, are as follows:
Rules (interactive)
Rule 1- All posts must be legitimate questions. All post titles must include a question.
All posts must be legitimate questions, and all post titles must include a question. Questions that are joke or trolling questions, memes, song lyrics as title, etc. are not allowed here. See Rule 6 for all exceptions.
Rule 2- Your question subject cannot be illegal or NSFW material.
Your question subject cannot be illegal or NSFW material. You will be warned first, banned second.
Rule 3- Do not seek mental, medical and professional help here.
Do not seek mental, medical and professional help here. Breaking this rule will not get you or your post removed, but it will put you at risk, and possibly in danger.
Rule 4- No self promotion or upvote-farming of any kind.
That's it.
Rule 5- No baiting or sealioning or promoting an agenda.
Questions which, instead of being of an innocuous nature, are specifically intended (based on reports and in the opinion of our crack moderation team) to bait users into ideological wars on charged political topics will be removed and the authors warned - or banned - depending on severity.
Rule 6- Regarding META posts and joke questions.
Provided it is about the community itself, you may post non-question posts using the [META] tag on your post title.
On fridays, you are allowed to post meme and troll questions, on the condition that it's in text format only, and conforms with our other rules. These posts MUST include the [NSQ Friday] tag in their title.
If you post a serious question on friday and are looking only for legitimate answers, then please include the [Serious] tag on your post. Irrelevant replies will then be removed by moderators.
Rule 7- You can't intentionally annoy, mock, or harass other members.
If you intentionally annoy, mock, harass, or discriminate against any individual member, you will be removed.
Likewise, if you are a member, sympathiser or a resemblant of a movement that is known to largely hate, mock, discriminate against, and/or want to take lives of a group of people, and you were provably vocal about your hate, then you will be banned on sight.
Rule 8- All comments should try to stay relevant to their parent content.
Rule 9- Reposts from other platforms are not allowed.
Let everyone have their own content.
Rule 10- Majority of bots aren't allowed to participate here.
Credits
Our breathtaking icon was bestowed upon us by @Cevilia!
The greatest banner of all time: by @TheOneWithTheHair!
founded 1 year ago
MODERATORS
I could see a setup where each server is a separate wiki around a specific topic, and federation allows people from other servers to edit or comment/discuss. Pretty much like Fandom but federated. It would be beneficial in that people wouldn't have to make a login for every wiki they follow, and may help discoverability.
This is what I mean. Lots of small wikis, like subreddits, like the old forums, only that a wiki setup seem to me a better way to collect and present knowledge than the forums, mailing lists, facebook groups, subreddits or wherever we used to put our stuff.
Wikipedia does.
Not sure if Fandom does.
looks
Oh, cool, it's Creative Commons.
Any community can host their own wiki using the software used by Wikipedia, the WikiMedia software even has very basic support for federation.
An example is the MCO wiki, a specific wiki dedicated to the MCO Minecraft server.
Yeah, to be clear, MediaWiki is open source and also has alllll sorts of really cool extensions. You also already can download the entire contents of Wikipedia.
I think this desire to federate everything is going too far. Most things don't benefit from this and in fact just become over complicated. If you can host a regular copy of a site easily... that's frankly most of the benefits there.
IMHO, Federation makes sense when you don't want a single owner of a community and the content it produces.
This. My problem is mainly about ownership and the control that comes with it. I don't want a knowledge repository (no matter if about breeding budgies or world politics) to be in the hands of a few. It has just happened: the evil site we don't want to talk about has imploded, and whatever information people find there now might have been tampered with in one way or another - those who decide to leave a rotting online portal also leave the accumulated knowledge behind that is stored on the site's servers. To always retain access to content we create online we need to rethink the whole thing. No matter if it's a social media portal, a photo sharing site, a music sharing site ... for example, who owns Discord and what will happen when that turns to shit? Another few years of content saved per disaster recovery or lost forever?
Thanks to your post I've noticed that just typing the following string while using a search engine (Google in this case) we can get all of wikis that use MediaWiki that are indexed because they follow the same URL structure:
site:*.*/wiki/Main_Page
not sure wikis need that, though a federated internet search engine would be a great idea. then wikis, instances, everything could be available similar to google. Maybe even provide some kind of lookup for search systems like google.
I think what you’re suggesting already exists. Take a look at SearXNG: https://www.privacyguides.org/en/search-engines/#searxng
Is there an explanation for stupid of how SearXNG works? I tried it for a while after getting too frustrated with the Google enshittification, but couldn't get results really.
It's considered a meta search engine. Basically it queries a bunch of different search engines at once and then aggregates the results.
Searxng is a must have :) [email protected] if you have any question on how to self host your instance.
The other solution is to use public searxng instances !
Self hosting at home is out of the question. I use an antenna to suck enough internet out of the air for daily needs in my remote valley. So I have started a small wiki farm on my webspace (is that indeed the same a tech person calls a VPN?)
I'm looking for something more federated like IPFS/Lemmy where I can run an indexing node that crawls the systems my group cares about and federates the dataset out.
I would want, for example, be capable of easily linking between the info for a particular plant in my botany wiki and my herbalism wiki. But I don't want to overwhelm the botany wiki contributor with a heavy list of medical input fields when he enters a new article.
I think that the nature of a wiki is inherently centralised. You want a central, curated wiki, not one that has a thousand different versions, each of which needs to be mixed together, and checked. Otherwise, you’ll have quite the time dealing with conflicts and things.
But the upside of a wiki is that it can be self-hosted. If a current wiki isn’t good enough, you are able to host your own, and work from that instead. Issue is that it’s not great if you’re technically inclined, and it’s a lot easier to manage a wiki that someone else hosts, tying it all the way back to a single central service.
I think wikis have already gotten there, at least for games. All of the game wikis have gotten consolidated into fandom/Wikia, which, from my experience, has enshittification levels that makes viewing Reddit from a phone browser feel likea slick experience. You can't avoid it either. Wikis that used to be very good (at least compared to fandom, like gamepedia), have somehow gotten all pulled into the enshittification vacuum.
A few days ago I was on the Minecraft wiki, but I was playing b1.7.3 so I was viewing it on wayback. And holy shit, before fandom bought out gamepedia (albeit I was looking at the pre-gamepedia wiki), the wiki was actually usable.
No matter Games and Fandom wikis have enshittified the wiki movement, but I think we can and should revive or create a new wiki movement for practical stuff, like gardening, cooking, woodworking, animal care etc. A lot of that used to be on forums (not the most ideal form of storing knowledge) and then most of it disappeared on Facebook. Not sure it it's still there, the fb got too shitty, had to leave. Went to reddit, and at first it was okay, but more tech and less practical oriented. It was noticeable that from forum to facebook to reddit, information density and quality about certain topics had declined. So I believe that a mature internet use would be to avoid those platforms like the plague. Aynthing valuable, especially our valuable community efforts, our hobbies and favourite activities, has to be kept out of corporate hands. When I started to save my photos on Google and contact my family on Facebook all those years ago it was just convenient. I don't think we had any idea about the can of worms this all was. Now I feel like a recovering drug addict, but it's worth it for a better web.
wiki content hosted on IPFS which others can then pin and reshare?
Can you explain what this does like I'm 5 please?
ChatGPT4 Summary
Question
Explain IPFS as if I was five
Response
Sure! You know when you want to show your friend a specific toy in your toy box, you point it out directly? That's kind of how the Internet usually works too - it looks for the specific place (like a website's server) where information is kept.
But, imagine if you could find that same toy even if it was in a different box or at a friend's house, as long as you knew what it looked like. IPFS, which stands for InterPlanetary File System, does something similar for the Internet. It doesn't just look for where information is stored, but what the information is. This way, even if the information gets moved, it can still be found because IPFS knows what it's looking like, not just where it used to be!
tldr sort of like P2P content sharing. Wiki content is just files at the end of the day.
Sounds cool. Does that mean we need heavy disks full of data everywhere or is there a magicky way around it?
iirc You “pin” content to access, which means you’re also then hosting it. You wouldn’t need to necessarily store the entirety of wiki for example unless its held in like, data files rather than page per content.
Im not fully up to scratch of the intricacies on IPFS, just thought it sounded like a possible solution to your use-case
As far as I know, but I might be wrong. IPFS is great for static content. But wikis are dynamic but slow.
Every change must be stored as duplicate file. For low bandwidth text based content it could probably work.
The 6h news cycle of web 2.0 would be incompatible with IPFS but web 3.0 and fediverse could be made more static, (more users see the same article so it could work)
Very good call! That had totally slipped my mind, thanks for pointing it out. It does look like theres a mutable file system solution that works with IPFS? Like you’ve mentioned though, this might be slow.
Mutable File System (MFS) Because files in IPFS are content-addressed and immutable, they can be complicated to edit. Mutable File System (MFS) is a tool built into IPFS that lets you treat files like you would a regular name-based filesystem — you can add, remove, move, and edit MFS files and have all the work of updating links and hashes taken care of for you.
So someone above mentioned Git, would that be comparable to how IPFS works?
Completely different solution but that would also work.
git is a version control system (vcs), github is a git host (repository).
It allows you to “check in” files, and if you share it / make a public repository others can check it out. You can also allow others to request changes (pull requests).
You add files to a git vcs. Github provides public repositories. For documentation example, you could create a set of HTML changes and check them in. Whenever you then make changes to existing files, or add/delete files, the repository will track the changes (so you get a history of changes timeline).
You can selfhost a git repository using gitlab for example. Or you could use github/gitlab as a centralised provider. Github has been around for a long time, I don’t see it going anywhere but in the worst case its trivial to push that same repository and history etc to a different provider.
Documentation may talk about code/programming as thats its main use but its not a requirement and doesn’t require any programming knowledge.
Github also provides a document/web page hosting thing I believe?
https://docs.github.com/en/get-started/quickstart
https://docs.github.com/en/communities/documenting-your-project-with-wikis/about-wikis
https://about.gitlab.com/install/
https://support.atlassian.com/bitbucket-cloud/docs/get-started-with-bitbucket-cloud/
ed - git would be far simpler than IPFS but isn’t decentralised like IPFS. But like I say, migrating or self hosting is pretty trivial
Thanks for your detailed explanation. The IPFS seems to be run by one guy also involved in something cryptocurrency, that looks a bit fishy to me. (Just a personal first impression by me, who has no clue and might be all wrong). From quickly looking into both I would probably prefer sth like git, as it has been around for longer. How is git not decentralized - as I understand, with git the files are stored on several machines and everyone can make and commit changes? I might still be struggling to understand the whole concept of decentralized here. Github is owned by Microsoft apparently and I won't touch their stuff unless I really have to.
I've used Gitit for that. The backing store is Git so all git's distributed VCS capabilities are there too. If you run Debian, apt install gitit should set it up for you.
Git seems to be a good way to approach this. It's funny that I never really had to get around to what Git actually is (some thingy to store files for programmer teams?). For a somewhat technophile but non-IT person it's all a bit overwhelming.
Yeah, git is complicated and having a synchronized gitit across multiple servers would be kind of a pain to set up. Maybe someone could package that to make it easier. Or Lemmy could add a federated wiki just like Reddit has a wiki.
It occurs to me, you could also look at Fossil (fossil-scm.org). It is also mostly intended as a VCS, but it has a wiki built in, and it is quite easy to set up. Again though, idk about the setup for keeping multiple servers synchronized.
This is what web 1.0 was.
I'm not sure but I like the concept.
wiki software that can kind of talk among each other
What do you feel wikis have to gain from being able to talk to each other?
Are you picturing a situation where 20 people host their own, say, music wikis, and every time you look up an album, you're presented a list of up to 20 hot takes about that album, all independently hosted and federating, rather than those users collaborating on a single communal knowledge source? I feel like removing the "communal knowledge source" aspect defeats the purpose of a wiki; they're supposed to be collaborative by nature.
Or are you picturing a world where I could host a music wiki and you could host a TV wiki, and we could link to each other if we wanted? Because that's already how it works, eh.
Others have covered why they think this isn't appropriate, but I'm curious what you thought we stand to benefit from federated wiki software.
Reddit has wiki functionality which some subs used to pretty great effect. It shouldn't be too hard to create something similar in kbin/lemmy.
I'm not aware of any way.
How would a federated wiki run with different admins applying different standards to articles?
Mirahaze is good. No idea if it could be federated though.
Miraheze Will allow you to make a wiki and you only have to stay active. Another option is Pepperminty Wiki if you plan to self host, this one is the simplest and also annoying to understand.
Wikis serve mainly lurkers, and federation of these sites does not matter much for them. The main advantage of wiki federation would be ability to edit several wikis under the same account. However, you can achieve the same effect with OAuth (that is, logging to many sites with the same account on another one).
And even that is unnecessary if the wiki in question allows anonymous editing.