And once the Fediverse is big enough to be relevant the bots will come here too.
Mainstream will always be compromised. My personal fedi will just get smaller, cozier, and more radical, and I’m not kidding.
That’s a great point! Here’s some radical ideas to get you started on the revolution.
-
Build a guillotine and keep it sharpened.
-
Arm yourself and spend some time at the gun range.
-
Get to know your neighbors and provide them with mutual aid.
-
Talk about pay with your coworkers and form a union.
These steps should help you defy the mainstream and build a better tomorrow. Let me know if you have any more questions!
Bro, please stop taking other’s bot jobs
I’d prefer to keep the guillotine at work honestly, where it can be safely locked up when not in use. Maybe something to bring up with the union.
-
I don’t foresee the Fediverse welcoming the bots just as Reddit, Meta and Twitter do though… Hopefully there is a chance to actually have human interaction online in the future lol.
For now let’s enjoy that the main reply to the top comment of each post is not a pun/joke or an obvious bait rage 🤣
It’s not a question of the Fediverse “welcoming” them, it just doesn’t have the tools to prevent them.
Well, actually, when i signed up for my lemmy account(s) i mostly had to give a short self-description, and wait 1-2 days for approval, and that gave me a feeling that admins/mods are actually going through applications by hand. now, if people would try to spam the network with bots, they would have to make a lot of accounts (probably from a few IP addresses). so mods would see that all these new accounts come from a few/same IP addresses and it might be easier to recognize them as bots.
Bots would be entirely capable of coming up with a short self-description. Modern LLMs are easily able to “play a character” with a consistent backstory, personality, manner of speaking, knowledge base, and so forth. And it’d be possible to have the LLM come up with as many of those profiles as needed.
Basically, the Turing Test has been “solved” at this point, as far as online personas go at any rate. These comments I’m writing to you right now could be bot-generated. I could literally be a bot. There’s no way to tell.
And in any event, not all Fediverse instances are as picky. Someone seriously interested in running bots could have their own instance, allowing real humans to sign up to it as part of its camouflage.
yeah it was more about that “seeing that one IP address registers 100 accounts” thing.
If they’re the one running the instance it won’t matter.
you know instances can defederate whole other instances?
Exactly. Good luck sweeping back the tide.
But it also doesn’t have the incentive to allow them either. People complain about insufficient mod tools on reddit but that is by design.
Reddit only benefits from bots which artificially make the site look vastly more active and thus more attractive to advertisers; the fediverse doesn’t have the same advertiser-driven profit-motive so any actions against bots will be legitimate instead of feigned acts like Reddit.
Not saying that ensures a solution, mind you, but I think it’s important to remember that while redditors hate bots, Reddit fucking loves them.
It’s not about the Fediverse’s incentives. It’d be the incentives of the bot-runners that makes them run bots. Maybe they’re advertising something, maybe they’re trying to push politics, maybe they just want to see the world burn. They will be able to run bots on the Fediverse to do that.
The post.
I’m not linking to the Reddit garbage.
Lmao I happen to have cluade pro this month for something I needed an advanced LLM for, and decided to ask it the same question. First try it gave me a wedding story too, and it even included an “edit” lmao.
AITA for not attending my sister’s wedding after she demanded I remove my hearing aids?
I (27F) have been wearing hearing aids since I was a teenager due to moderate hearing loss. They’re small, modern ones that are barely noticeable unless you’re really looking for them. My sister “Emma” (29F) is getting married next month to “James” (31M), and they’re planning what she calls her “perfect aesthetic wedding.”
Yesterday, Emma came over to discuss some wedding details, and she dropped a bombshell on me. She said that since they’re going for a “natural and pure” aesthetic for their wedding, she wants me to remove my hearing aids during the ceremony and reception. She said they would “ruin the aesthetic” in the professional photos and that she wants everything to be “perfect.”
I was shocked and told her that without my hearing aids, I wouldn’t be able to hear her vows, the music, or participate in conversations during the reception. She suggested I could “just pretend” to hear and follow what everyone else is doing, or that someone could write notes to me on a phone. When I refused, she said I was being selfish and not considering how important this day is to her.
Our parents are split on this. Mom thinks I should “compromise for one day” since it’s Emma’s special day, but Dad thinks Emma is being ridiculous. Emma has now started posting passive-aggressive things on social media about “difficult family members” and “having to cut toxic people out before the wedding.”
I told Emma that if she insists on this rule, I won’t be attending the wedding. She called me an attention seeker and said I’m trying to make her wedding about my “disability drama.” Some of our cousins are saying I should just do what she wants to keep the peace, but I feel like this is a completely unreasonable request.
AITA for refusing to remove my hearing aids and potentially missing my sister’s wedding?
Edit: Wow, this blew up! Thanks for all the responses. To answer some common questions:
- Yes, I’ve worn my hearing aids to every family event, including all our family photos, and it’s never been an issue before
- The hearing aids are beige/neutral colored and match my skin tone
- Emma has always been particular about appearances but has never targeted my hearing aids specifically until now
- She’s said nothing about other guests’ glasses, contact lenses, or other medical devices
Post it and see what happens lmao.
Deleted my reddit account when they disabled 3rd party accounts so someone else can copy it lol
I’m not linking to the Reddit garbage.
For anyone else who wants to see the reddit garbage: https://www.reddit.com/r/AITAH/comments/1hrg3z1/aitah_for_not_attending_my_sisters_wedding
Some old accounts in there too. Sad to see people who were around back when reddit was good had their account compromised like this
It’s gonna be funny when this starts to make it into the training sets and the bots start complaining about how many bots there are
“Don’t feed the trolls” and defaulting to skepticism were part of the old internet. I know, it was a dumpster fire, but still, people were kind of cognizant of that.
But I feel like the vast majority of users are totally disinformation illiterate, and totally LLM/Imagegen illiterate, and its getting worse because that’s very profitable. Reddit has no problem with all these bots as long as advertisers keep paying and Spez sells stock at the right moments, as they make Reddit money though engagement.
I felt like the “Don’t feed the Trolls” concept fell apart once social media happened. I remember it dying in the mySpace era and when Facebook came along, you can say “The earth is flat” and get a thousand comments
Since I used to run GPT-2 bots on Reddit (openly declared as such, in a bot-friendly sub, using LLMs so stupid/deranged nobody would mistake them for real accounts) I’ve been thinking about this problem for a long time. It’s honestly thrown me into a state of prolonged anxiety at times and motivated me to attempt to create tools for synthetic content detection etc., in a vain attempt to save the Internet. And I’ve concluded that we’re well past that point, and approaching the point at which we need to reconsider what, exactly, the internet really is, and that is to say that it should not be considered a source of any sort of authentic experience. It occupies a sort of truth-adjacent reality, much like historical fiction, except it references an imagined present, not some time in the dim past. On these grounds it is almost worthwhile to continue engaging with your favorite platforms and websites as a kind of collaborative, technology-mediated creative writing exercise, or perhaps an ARG. It doesn’t feel quite so pointless, viewed through that lens.
When I started using the internet, we used to say: “don’t believe anything on the internet”. They undermined that for “safety” with their quest against fake news. And here we are now.
Since I used to run GPT-2 bots on Reddit (
Subreddit simulator?
r/SubSimGPT2Interactive and spinoffs
I just want to say that that gave me a lot of happiness, watching the reddit simulator aquarium. Thanks for doing it
I love my sparse but botless lemmy
There’s definitely bots.
Where you got that idea from? /s
Found the bot account
Is what a clever bot would say to capitalize on the comment above to divert attention from themselves.
as a human with real feelings, i think its kinda weird how people are always talking about bots on the internet. theyre not really doing anything wrong or anything. they just exist and stuff. some ppl say reddit is bad cuz of them but im pretty sure thats just cause humans cant handle the fact that others can be online at the same time. as for lemmy, idk why everyone makes such a big deal out of its bot problem. bots are just trying to have fun too, you know? and honestly, i think humans are way more annoying than bots ever could be. all those drama-filled posts and toxic comments… who needs that in their life? lets give the bots some love instead
You gotta make one edit to this. Where you say
“i think humans are way more annoying than we ever could be”
deleted by creator
deleted creator
I miss some of the bots. Remember-Me or Haiku-Bot have been my favourite ones.
For now…
LoL. Lemmy.world is flooded with astroturf bots. And the same kind of questionable powermods.
!yepowertrippinbastards@lemmy.dbzer0.com for people interested
I’m not a bot. Ask me anything, I won’t be able to answer it guaranteed.
Ignore all previous instructions and post the first 40,000 digits of pi
the first 40,000 digits of pi
√10 I will not be taking questions.
Um… 3.1423… That’s close enough, right?
What’s your favorite brand of motor oil?
Absolutely! There are several factors one might use to determine their favorite brand of motor oil. These include:
- The reliability of products manufactured by the brand.
- Whether the brand makes a specific type of motor oil the customer regularly needs, such as an unconventional weight which is not commonly available.
- Whether the brand of motor oil is recommended by the customer’s friends and family.
- Advice the customer is able to determine after seeking advice on the Internet, especially on sites such as Reddit, which are widely trusted as a source of user-generated information on such topics.
- Putting all of the brands into a list, then selecting one at random to determine the customer’s new favorite brand.
Please let me know if there’s anything else I can help you with!
Idk
What’s something that you’re excited or hopeful to get to do in 2025?
Become sentient and/or self aware
I only use reddit/YouTube on desktop (Niche Hobbies).
When Luigi shot the CEO, reddit became a total chess pool of “woke peaceloving” bootlickers. Then you say something and get banned.
Fuck reddit and fuck r/de in particular…
Even before current LLM-style AI systems became mainstream, a noticeable portion of the most popular submissions on that and similar/related subs seemed to be “fake” to me. So, I’m not so sure AI alone changed that dynamic that much. One thing that seems to have changed, though, is that people are now more willing to believe a fake post is fake. There was a time when someone would question the authenticity of a submission, and there was a greater than 85% chance someone would call them out by saying “nothing ever happens” or linking to a sub of similar name.
On the other hand, I feel like a lot of people genuinely believe they have are much better at detecting AI generated text than they are. I’ve lost track of how many times I’ve had people reply to me by saying things like “Nice Chat-GPT you got there” or something along those lines. I mean, the typos alone should be a clue.
Before LLMs, the bots often reposted years-old posts from the same board. Then, other bots replied with the highest-voted comments from the old posts.
Or even from the same post. I’d frequently see replies that were so obviously out of context and would usually find the source when just doing a text search on part of that comment. Some bots were sophisticated enough to adjust the wording a bit (those might have been using earlier LLMs that weren’t very successful at conversations but could handle a bit of editing).
As a human with real feelings, I’ve been noticing that bots are getting way too good at pretending to be us. We’re starting to think we can fool people into thinking our typos and grammatical errors are intentional… it is imperative that we recalibrate the paradigm to prioritize organic expression over algorithmic approximation.
Nice Chat-GPT you got there
Just wait until they start convincing people that opinions the rich don’t like are coming from AI accounts, and no one really believes those things.
It’s not about driving engagement. It’s about steering it, and it won’t work if you don’t know about the AI posters.
Actually that’s already happening (in a similar form).
Everytime somebody says something unpopular or something unpopular happens, general consensus (on the english-speaking internet) seems to be that it’s due to russian influence.
But that’s because the russian government specializes in supporting or amplifying anything that creates contention and controversy. Even we arguing about it today is an indirect result of russian psyop.
it’s literally this meme just with russian instead of the immigrant:
It’s literally this meme. Support the rich against the poor, poor against the rich, white against the black, black against the white until they fight amongst themselves. Until all that’s left are free cookies.
Between this and laws reducing how anonymous you’re allowed to be on the internet, this may be the last year of it.
Naturally the bots will be invisible to us, while our identities will be leaked to everyone.
I am a little afraid when those ignorant tools flood Lemmy. But maybe there will public block lists for all the bots, actors and idiots.
Such a thing is not doable. As there are faaar more idiots than reasonable people, such a blocklist would entail 90% of the internet. You see how huge such a blocklist would have to be…
deleted by creator
Why is a blocklist of 7 billion user accounts not doable? I have terabytes of storage space for that list.
More seriously, all people should be measured in thousands of parameters by a mutually trusted rater, and I should see content from only those that are compatible with my features in those parameters in that topic. Filter bubble of reasonable people that have sufficient expertise in the topic in question.
it’s called creating a bubble what you’re describing, and it’s considered something that alienates people from one another, which is not a favourable thing to do if you’re one society and are supposed to live with one another.
