Reddit said in a filing to the Securities and Exchange Commission that its users’ posts are “a valuable source of conversation data and knowledge” that has been and will continue to be an important mechanism for training AI and large language models. The filing also states that the company believes “we are in the early stages of monetizing our user base,” and proceeds to say that it will continue to sell users’ content to companies that want to train LLMs and that it will also begin “increased use of artificial intelligence in our advertising solutions.”
The long-awaited S-1 filing reveals much of what Reddit users knew and feared: That many of the changes the company has made over the last year in the leadup to an IPO are focused on exerting control over the site, sanitizing parts of the platform, and monetizing user data.
Posting here because of the privacy implications of all this, but I wonder if at some point there should be an “Enshittification” community :-)
Posting here because of the privacy implications of all this, but I wonder if at some point there should be an “Enshittification” community :-)
There is, its called !enshittification@lemmy.world
Just subscribed, thanks a lot.
Reddit has long had an issue with confidently providing false statements as fact. Sometimes I would come along a question that I was well educated on, and the top voted responses were all very clearly wrong, but sounded correct to someone who didn’t know better. This made me question all the other posts that I had believed without knowing enough to tell otherwise.
Llms also have the same issue of confidently telling lies that sound true. Training on Reddit will only make this worse.
The problem is that SEO has made it impossible to find accurate information easily, since even “old, trustworthy brands” can’t be trusted online. [This is an excellent article that explains the problem thoroughly, and brings receipts] (https://housefresh.com/david-vs-digital-goliaths/).
This is a great example of why it’s so important to emphasize teaching critical thinking in school right now. Misinformation and disinformation is just going to continue to grow.
Literally why I bookmarked it. I’m an online teacher, so I’m going to advocate for adding that article to a grade 10 course that’s used by thousands of students each year.
I’m a student teacher right now in elementary! I try to get my kids to think critically whenever I can. I hear kids talk about insane shit they saw/heard on tiktok (I got into an argument with a student who thought Slenderman was 100% real because of something they saw on tiktok) and I try to really get them to think and actually justify why they believe things.
An uphill battle for sure. I wish you the best of luck.
Somewhat related:
A recommendation about teaching controversial topics: you need to build connection first.
I mean, that’s true of all teaching, but when you start to question the (prejudiced) things they’re hearing from trusted adults at home, you really need to have a strong relationship with the students.
Being an anti-racist pro-SOGI educator in conservative communities is hard.
I wish you success in your career! Teachers have such an opportunity to make a huge impact on the world.
Great article, thanks for mentioning it!
That’s a really good article, and it does a good job of highlighting the issues with modern day search results.
I’ve been guilty to use “best x” pages before, but if the website with the “best of page” doesn’t have specific reviews linked I usually look up individual product reviews for the good sounding items on other websites.
@Fubarberry yes I saw this a lot too. Highly upvoted confidently incorrect comments, with the real answer or an answer debunking them with links to factual sources less upvoted.
Happened to me as well.
I am a lawyer and I would get down voted for posts explaining the law that contained citations to the actual applicable statute if people didn’t like the statute. Using reddit up votes as a measure of correctness is fundamentally a dumb idea.
@collapse_already yeah Reddit also tended to mistake explanation for agreement and savagely downvote it.
but sounded correct to someone who didn’t know better
specious /spē′shəs/ adjective
Having the ring of truth or plausibility but actually fallacious. "a specious argument."and then the real answer will be hidden or something silly, or in some cases where money is involved the correct answer might have been removed
I would come along a question that I was well educated on, and the top voted responses were all very clearly wrong, but sounded correct to someone who didn’t know better.
This can be said to https://news.ycombinator.com/ as well. I wonder how much of this is due to sock puppets and bots.
Yeah all of my most down voted reddit comments were the ones where I replied about something I’m an actual expert in. Scary stuff
I spent 20 years as a producer, developer, and project manager in the lottery and games industry.
Trying to explain how lottery and games work to people and have them hear me makes me want to cry.
Fascinating! I’d love to hear a little about it, if you don’t mind.
Certainly, I’m always happy to share with inquisitive minds.
Is there any particular question you’d like me to address?
Not really, I never paid much mind to it. I’m curious about the whole industry I guess, or anything you’d like to share or set the record straight about.
Oh there’s lots I have to set the record straight about and there’s lots I could talk about, but without being asked a specific question that would just leave me to write an open-ended essay and I’m not up for it right now
I’m still happy that I went through the effort to delete all my old posts when I left Reddit a while back. I periodically check if they’ve restored them and luckily it hasn’t happened so far. I do miss some of the bigger communities but overall I’m having a good time on Lemmy.
I’m sure they have a backup somewhere that they will use to train the AI, but agreed, it is time to leave reddit for good.
Unless you are in the EU Reddit absolutely did not delete your data.
Reddit is dumb enough that they probably have a backup they kept of EU users.
I can vouch for that.
Well, if you want to be sure that Reddit deleted your data, the time to bring it up is now. Ask questions, contact journalists, demand answers.
Your PII isn’t being sold here and you gave Reddit an irrevocable license to your content, so being in the EU doesn’t matter.
No, GDPR applies to all data, not just PII.
The GDRP explicitly only applies to “personal data”
- This Regulation lays down rules relating to the protection of natural persons with regard to the processing of personal data and rules relating to the free movement of personal data.
which it defines as follows:
‘personal data’ means any information relating to an identified or identifiable natural person (‘data subject’); an identifiable natural person is one who can be identified, directly or indirectly, in particular by reference to an identifier such as a name, an identification number, location data, an online identifier or to one or more factors specific to the physical, physiological, genetic, mental, economic, cultural or social identity of that natural person
Please provide a quote where the GDPR says that it applies to anything but “personal data”.
I wonder what the risks are to including deleted and pre-edited content in training data. Most of the edits are going to be typos and formatting, do you want 2-3 copies of the same message with typos in them for training data? Similarly, deleted comments are mostly nonsense, unhelpful, duplicate, or highly controversial things.
If someone wants to dig through and find individual users to restore that’s one thing, but I don’t think I’d immediately choose to train off of that other data unless I had to.
It should be very easy to distinguish edits and deletes which were made within a few minutes or hours after writing a comment, from those made months or years later right around the reddit blackout.
Only shadenfreud I have is that my deleted banter that they will assuredly include, will hopefully increase the stupidity of whatever model gets trained on it. Ugh, what a dystopia we’re building.
Lol YoU ShOuLd HaVe ThOuGhT oF ThAt SoOnEr
LaNgUaGe FoR tHe MaChInE!!?:/;1
After deleting all of my posts and comments Reddit decided to undelete them three days later and then proceeded to lock me out of my own account. Fucking bastards.
I just left my comments on. I still use reddit when searching actual human responses from Google. Maybe one day someone might find my archived comments useful in the future.
I am glad it makes you feel better but the reality is they still have your data. Just because you don’t see it on the front end doesn’t mean it isn’t still in the database with a “deleted” flag set. They aren’t hard deleting your comments.
Deleting your messages is just another data point for them. Reddit can train an AI on the originals and categorize you as a “comment deleter” to give them more information.
Aye, and that’s why I left. As an author, fuck you trying to monetise my writing when I can’t even do that myself.
Hey another author?! How you doin? Lol
Same as you fuck them.
Yeah, hi!
Can I have a link to your work?
May i see both of your works?? Id love to give em a read!
I’m wondering how many open WriteFreely instances there are.
Gotta buy me dinner first! Lol
Jokes aside I’m fairly private when I’m not so I tend to not openly share my writing. I’m building up for when I retire from corporate IT to unleash a lifetime of it.
I did that, too. I published my first novel in 2019 after leaving my career as a UX designer/softwaredev/db admin/etc.
Hit me when you’re ready, no matter how many years that is – I’d love to read your stuff.
You know what the world doesn’t need?
an AI model trained on the old Reddit Hive Mind.
Some AI models already argue when people point out inaccuracies, just like on Reddit.
Makes me wonder how that technology is going to track. Reddit isn’t bad for finding niche answers to niche questions, but if you import the data wholesale then you’ll have a hard time separating the signal from the noise, even if you sort by using vote counts as relevance.
Reddit is valuable because people can do a search for a niche topic and find the answer on that forum. And the answer was written by a human. It’s not valuable because it can amalgamate an approximation of those answers that might be 90% true and 10% dead wrong.
As someone with expertise in some niche fields:
They’re almost always wrong about everything, and when someone tries to correct them, with sources, they get downvoted.
Guess what data they’re trained on…
This is a human thing and not so much a reddit thing. People been arguing on the internet since the inception of message boards.
I disagree. A reddit bot would be really funny as it would constantly talk about incest and spez
That and the feeling of pride and accomplishment.
A lot of AI models are probably already trained on Reddit data. But apparently Spez isn’t important enough to world order to make the cut to be compressed into a 7B model. I asked my Mistral-7B-Instruct (4-bit quantised) local LLM:
>>> What can you tell me about someone called u/spez, a ... nd are they a nice person or horrible? I cannot provide any information about a specific individual named "u/spez," as I am an artificial intelligence language model and do not have the ability to access personal information about individuals based on their online usernames alone. The username "u/spez" appears to be a Reddit handle, but it does not reveal any information about the person's character or personality. Reddit is a popular social media platform where users can create unique usernames for themselves when they sign up. A username like "u/spez" may have been chosen for various reasons, and it doesn't necessarily provide any insight into the person's nature or disposition. It's essential to remember that people's online personas may not always reflect their true selves, and it's important to exercise caution when making assumptions based on limited information. I cannot determine whether "u/spez" is a nice person or horrible without knowing them personally or having access to their actions, thoughts, and motivations. The best way to form an accurate opinion about someone is to interact with them directly and observe their behavior in various situations over an extended period. >>> Is it possible u/spez is Steve Huffman? Can you tell me anything based on tha ... t? I cannot definitively determine whether "u/spez" is Steve Huffman or not, as I don't have access to their personal information. Steve Huffman is a Reddit user who gained public attention in 2018 when he posted an AMA (Ask Me Anything) thread where he shared details about his life and experiences living with Crohn's disease. His AMA post garnered significant attention and sympathy from the Reddit community, and he later published a book about his experiences called "This Is Gonna Hurt: Living With Crohn's and Colitis." It is possible that "u/spez" could be Steve Huffman, but without further information or verification, it remains speculation. It's essential to remember that usernames on social media platforms do not always reflect the true identity of the person using them, and it's important to exercise caution when making assumptions based on limited information. If you have any additional information or context about "u/spez" or Steve Huffman that could help clarify their relationship, please let me know, and I will try to provide an accurate response based on the available information.
You know the phrase “If you aren’t paying, you’re the product”.
It doesn’t hit as hard as a CEO using the phrase “Monetizing Our User Base”.there should be an “Enshittification” community
basically every technology one
This has got to be the start of another bubble popping. It just has to, right? With essentially all online services doing everything they can to wring out every last penny of value without any eye towards the future (other than ai all the things)… something’s gotta give.
But then again, maybe it’s just my eyes being open after living in those spaces for so long. Granted I’ve been out of Facebook for years, been de-amazonning for a couple (it’s really f’ing hard) and I’ve been trying to de-google as well but it’s even harder (stuck with Apple though). But, now that I’m in the fediverse, where we’re talking about all this, maybe that’s why I’m noticing?
Nah, brace yourselves.
The start of the bubble popping was the increases in interest rates. We’ve seen several online companies shut down already because the free money isn’t there any more and there is no path to monetization.
The problem with the Fediverse right now is that it is all run on volunteer labor and donations, similar to an early Reddit. It will be interesting to see how a distributed system solves this problem.
I think the volunteer labor and donations strategy works much, much, better on a distributed platform like the fediverse.
Sure, but what happens if the population explodes? Primarily server costs will go through the roof, and then you’re still relying on volunteer moderation. It works now because the fediverse is reasonably small, but a true user exodus for any major platform could overload existing instance resources. I think the saving grace here is that there is a bit of a learning curve with Lemmy that fends away the less tech savvy, but that could change in future updates
Maybe I’m wrong but I think the fediverse isn’t quite that fragile. Instances can always close new sign ups if they’re overwhelmed. More users means more donations and more people likely to self host, too.
I guess we could run into real issues if fediverse infrastructure doesn’t scale well (example: required server resources scale exponentially with more users instead of linearly)
In extreme circumstances instances can defederate from larger ones if their mod teams are overwhelmed (obviously this isn’t a good solution but it is something beehaw.org is doing/did with lemmy.world)
It will be interesting to see how a distributed system solves this problem.
The issue really comes down to the infrastructure costs. The fediverse is by design significantly less efficient with hardware than a centralized system. It isn’t that it’s difficult to scale, it’s just that it’s expensive to scale. And since the hardware is maintained by generosity of donation…
This is offset by the higher interest in volunteer labour, though.
I think the “solution” is just to accept that instances will burst in and out of existence (and favour) based on time and generosity.
As long as user profiles and contributions can transfer between instances, especially if the process is easy, then instances coming and going won’t be that much of a problem.
I do hope that current and future open source tech moves towards monetization resistance if monetization can’t be done ethically. Donation and volunteers seem to be the working formula so far
I think the bubble is coming too. The question is how much it will take for normal users to be done with them. The current Lemmy user base is more focused on tech, open source, and/or privacy than the average Internet user, which is why we already abandoned Reddit.
I think having to pay for access to these sites might be the biggest issue, as many people see the Internet as something that should be free.
There is such a thing as good technology. It would be nice if one of the tech comms would ban posts about shit tech
Fuck u/spez
“Early Stages?” You’ve got AI mining your data. The Lions have already come and gone. The hyenas and other scavengers are picking over the scraps, now.
They mean that they havent made money on it (yet)
They have probably only provided a small amount of available data, and have much more data, of different type.
Yes we’ve got the data, but now we need it from different angles!
When I go to some reddit posts on Mobile now (like from a Google search, that’s the only way I end up at reddit anymore), it tells me “this content is unmoderated” and gives me a choice to either navigate away or install the Reddit app. Fuck that noise.
Change the URL to old.reddit.com as the domain
Try this, in either Bing/Copilot AI or Google Gemini: Start your prompt with “According to Reddit”, then do your search like you would by using search alone.
The AI of your choice will scrape the posts and give you a nice summary of whatever you were searching for - no need to ever touch Reddit directly.
For me, this works better with Copilot, YMMV.
Example: “According to Reddit, what is the best mechanical keyboard brand to use for touch typing?”
or i can just add “site:reddit.com” to a normal search. meh.
Absolutely! What I am suggesting here is: since Reddit is so gung ho on AI, use the AI to bring them to their knees, and have some fun while doing it. 😬
how exactly do you think that would bring reddit to their knees?
Does that allow you to bypass the “open in app or navigate away” wall?
I never see that because all my devices are setup to redirect to old.reddit.com
I know it’s only token resistance at this point because others have found their comments from Google searches even after their accounts have been deleted, but Power Delete Suite is busy churning away on mine right now.
I wish I had known about Power Delete Suite. I nuked my posts / comments by hand :-(
In case it’s useful to more people: https://github.com/j0be/PowerDeleteSuite
Lol
My account was four years old. There was no way I was going to do it by hand. It took PDS 8 hours to get churn through all that crap.
I had been meaning to delete my account earlier for opsec reasons, but just hadn’t gotten around to it.
I wonder if constantly cycling through it could eat up bandwidth, storage, etc. might be a good way to fuck with them.
Just set up a weekly cron job at the busiest hours
I Remember people uploading 10gb files of noise in order to fuck their storage
“we are in the early stages of monetizing our user base,”
If anyone on Reddit reads that and stays there willingly they are an idiot. Not they weren’t idiots for staying after the API changes but now they are even bigger idiots.
They’ve finally gone full /HailCorporate, become the thing some of the original people of the site would probably not have agreed with in many ways
They permabanned my 14yo account because my anti-nazi rhetoric was “encouraging violence.” I guess Nazis are a class of humans dumb enough to give them money so they don’t want to scare them off. The post that got me banned had more than 60 up votes when it was deleted and I was permabanned. A reply post in the same vein was not deleted.
Remember that video where Ron Perlman talked about there’s a lot of ways to lose a house?
I lost my 11-year account because I said something to the effect of ‘If Ron Perlman pulled up and said get in the fucking car we’re going to go burn down Bob Iger’s house I wouldn’t hesitate.’
They had been getting very weird near the end there anyways? I kept getting these stupid warnings over the most petty shit. At one point somebody said respond to this comment and I’ll gild you. I simply responded fuck you because I thought it would be funny to see that have gold, which it got. Got an official warning for harassment.
I had said a lot worse over the years.
Same. This.
Edited to add: fuck redtit
I got permabanned for inciting violence too about a week ago too. You know the deluded asshole who killed his dad, Justin M whatever his name was? Well it was in the r/all news for a day so I figured people would want to see it. Posted it in a gore sub with the nsfw tag and put a neutral title. It wasn’t politically motivated or anything, it was just a video that was recently talked about and interesting to me and maybe others, I thought. Well, it got deleted. Several fucking days after it was removed did I get a random permaban message and banner. No inciting violence anywhere.
I’ve been banned specifically for things too when a whole thread of similar comments weren’t.
I’ve also had random warnings and bans for weird shit like u/EdibleFriend. I wish I left reddit sooner but reddit has a huge userbase and well established communities. A monopoly on everything sadly. I spent my time writing comments for others, not for spez or “reddit”.
If anyone’s deleting their comments, make sure to edit beforehand. If you’re not banned, use powerdeletesuite. If banned, you’ll have to use redact then shreddit. I don’t want to advertise them but those were the only two I could find after some hours of trying to delete my data. Nuke reddit is gone. Redact doesn’t delete but rather edits and I think shreddit actually deletes. I left mine up so all the scrapers can override any previous data, or so I hope. I don’t trust redact honestly so I did it in a vm. Make sure to remove all saved, hidden, blocked, etc. posts, comments, users, and subs and replace it with random shit.I wish people could learn from my comments or read their contents but there were too many comments to selectively delete. fuck spez and fuck reddit.
Honest question: deleted comments might be just hidden and still up for sale, do people know if GDPR can come to the rescue here?
To be fair, advocating violence on any platform will not get you very far even if the idea is justified, eg) nazis
Curiously, Nazis seem to get away doing just that, under their clear name even! Reported a few of those on Twitter a while ago before Elons takeover. Got a message that the reports are unwarranted and if I continued to make them they’d disable my ability to report.
I asked what Eisenhower would do if he saw the Nazi marchers in Wisconsin and had ready access to a machine gun. I don’t think that is advocating violence. I intended the comment to illustrate how far some Republicans have moved to the right since Ike was president.
Eisenhower is dead. Advocating for his attendance at a Nazi march is nothing more than a thought experiment.
With all the changes that Reddit has made recently esp with the API changes, it definitely did leave salt in my mouth alongside how increasing toxic the Reddit community had become in comparison to when I joined the community but the small niche communities that existed on Reddit did honestly made it harder to quit due to the lack of communities outside, which is another big problem with centralisation, esp in the modern internet as it makes you rely on platforms you may not necessarily like due to big issues like social isolation etc.
When I found out about this, this isn’t simply excusable anymore and I would rather delete my account over having my personal data being sold for profit (which goes completely against the early ethos of Reddit as a whole but being semi owned by Conde Nast, this would have been inevitable) despite the fact that I have been thinking about deleting my Reddit profile way before this issue.
Surprisingly, I honestly have had no regrets deleting Reddit out of my life and honestly I do wish I would have done it sooner, I’m far less frustrated, I’m starting to think more constructively again and I feel way way less dependent on it.
Can say, I made a good choice there tbh.
Ditto for me, as well. It’s just a matter of establishing those ‘niche’ communities on the Fediverse. The Fediverse has broken thru 10M users. We’re getting there. Onward!
