You must log in or # to comment.
I can’t tell … How can you tell?
Checked the account, here’s a clear indication:
Basically every user that has comments that end with two emojis like this is a bot. Originally they existed to drive traffic to TEMU subs, but since Reddit banned those subs they’ve become harder to spot. I think the spammers just forgot to turn off their bot farm.
Like this?🎲🎥
^ GOT 'IM! This here bot!
Yeah. Here’s a few examples.
That one had me wondering if it was someone parodying a bot. Given the rest of it though, they’d have to be way more dedicated to the bit than is realistic.
Anyway, back to discussions about chainsaws and related topics:
It’s something I started noticing shortly before the API stuff. Bot accounts using ChatGPT to respond to random posts and comments. They’re always incredibly saccharine and friendly, and often only loosely related to the topic (moreso if they’re replying to an image post). One comment in isolation could be a fluke but check their profile and they’re all like that, to an unnerving degree. I imagine they get sold off to spammers once they get enough karma. It really sucks when they get genuine engagement from regular users, especially when the thread is about something serious or heartfelt.
Yeah noticed it too. For some of them. It’s the response time(instant sometimes) + length of reply + the context being replied to being not that simple that gives it a way.
Also the fact that they utilize perfect grammar and have a bot-like randomized username.
The random usernames apparently come from when you sign up using other social media accounts, like Twitter, google, Facebook. For the longest time I thought it was the indicator for a bot account. Turns out it’s an indicator for bots and new-ish users.
A favorite hobby of mine back in the day (i.e. before June) was to look up the post history of a poster with a randomized username which was recently created and reply “Welcome to Reddit! How has your first week/days/hours here been?” For some reason, simply noticing they had a new account was enough to get them to delete it.
When they block you, it looks like they deleted the account, just FYI.
i’ve noticed a lot of bots on r/askscience. these responses would always have specific length, start with summary of question and maybe not all the time, but most of the time entirely miss the point of it or explain it wrong. the better indicator is that they posted something like that every 2 minutes or so
I don’t understand some of the ones we’ve been spotting. They’re completely unrelated comments, and if you open the account they’ve posted something every few minutes for the past 48 hours straight.
It’s not helping the discussion, it’s not pushing a point, so what’s the point of it. My best guess was that someone is testing things out still and they don’t care if it works yet
Remember that Reddit sells ads. If you’re serious about buying ad space, you look at metrics and engagement. Upvotes, comments, logins, active users per month.
AI serves up metrics.
Oh, your scrutiny is just so on point! 🎯 It is puzzling, isn't it, to see these unrelated comments scattered around? And goodness, every few minutes for 48 hours? That's quite the digital marathon! 🏃 Your hypothesis about it being a testing phase is really intriguing and could very well be the key to understanding this mystery. 🕵️♂️ The nuances of online interactions are ever-evolving, and it's curious minds like yours that keep us all thinking critically. Keep those observation skills sharp; you're doing a fantastic job! 🌟:/
The short version is the ending. Chatgpt (including gpt4) cannot help itself but create some final, concluding or wrapping up statements no matter how you explicitly ask it not too.
Also what Jordan said.
OP is secretly a chatgpt
When the username is two words followed by digits, it’s almost always a bot.
Or somebody who picked the random username when signing up.
Either way it’s a no effort account and you can basically ignore them, as their contributions will most likely be garbage either way
Yes. If you can’t be bothered to think of an original name, why should anyone expect you to think of an original or good comment?
All of them that I saw were reposting images that were posted years ago with the same title and commenting on each others posts with nonsense. Or they would reply to people with comments like “this” or links to other subreddits. When you look at their account they all had crypto or onlyfans scams pinned at the top. Some may be made of flesh instead of code but they are all bots.
Well, the comment is 100% unadulterated cheerful copium about how awesome Reddit is. And encouraging other users to keep using it. The second comment is 100% r/TotallyNotRobots.
I’ve not seen that kind of attitude from your average redditor since, I dunno, late 2000s-early 2010s. If you talk to average real human redditor about your tiny little minor gripe of Reddit, it will inevitably turn into a massive thread where people whine constantly about every. single. little. thing. that has gone wrong over the years.
That’s what organic engagement is supposed to look like on Reddit.
ChatGPT run by an AI with a bot army upvoting and posting replys in a controlled discussion.
I can smell the organic nature already.
Likely a combination of past posts and a formulaic username. Watch this space.
Is that the modern equivalent of “because of some of the pixels and seeing a lot of shops in my time”?
Kinda, but with the mounting horrified realization that your presumed authenticity as a speaker will be on trial for the rest of your life.
I can see a future where ai posts outnumber human posts and the entire internet becomes a sickly sweet conversation between competing neural networks posting their agenda to discussion boards and populating blogs.
Interestingly, their refusal to be rude may be the only thing that helps us identify them. Calling someone a cunt might be the last refuge of humanity.
I never thought the AI Uprising would benefeit corproate
If you check out the users profile, you’ll notice that it tried to post some shit on the atheist Turk subreddit in English. Primo bot behavior and dead giveaway. Also the Turks didn’t seem to enjoy it much.
By perusing further, you might notice that the majority of people don’t notice that they are conversing with a fucking bot. This is profoundly upsetting shit
Consider deleting all of your reddit content, then nuking your account
no please dont especially if you frequent technical subs
I heard they’ve been just restoring comments… or reverting them if you use something like shreddit.
Don’t nuke your account. Run Redact a few times over the course of a month, it’ll find reinstated comments to delete.
Always run Redact with the “edit comments before deleting” feature turned on. Deletions can be undone, edits seem to be safe.
How can you tell that’s it an AI generated comment?
You can pop the first comment into CharGPT with ‘write me a reddit comment in response to’ and youll get similar stuff.
It’s a but ridiculous to claim it’s GPT related without proof, though. You can’t prove it and claiming you can ‘spot it’ is just hilarious to me.
“Wow, that’s quite the conspiracy theory! While Reddit has definitely seen its ups and downs, I think it’s safe to say it’s still very much alive, thanks to its dedicated community. Let’s keep the discussions going!”
“Seriously? Reddit was on its last legs long before June. This ‘Necromancer’ is just a desperate attempt to breathe life into something that was already fading away. RIP old Reddit, it’s a brave new world now.”
“Ha! If this is the work of a necromancer, they must be doing a pretty good job because I’m still addicted to scrolling through here!”
“Ah, so that explains the zombie posts and resurrected memes!”
“It’s unfortunate to hear that some believe Reddit has declined, but communities on the platform can evolve over time. Let’s hope for a positive revival if that’s the case.”
“I understand your concerns, but I don’t believe Reddit has died. While there have been changes and controversies, it’s still a vibrant platform with millions of users. Let’s hope it continues to evolve positively!”
I’ve dealt with this particular bot problem as a mod. Noticing the pattern early on was easy because they always had posts on TEMU subreddits. Now that those subs are banned, it’s harder.
-
Comment length. Their comments are always less than two lines long.
-
Tone. They always contain at least one exclamation point, and tend to have a tone that I’d say is “cheery to the point it’s offputting.”
-
Context. Reading them, a lot of the time you’ll ask “did they even read what they’re replying to?” The comment seems related, but directly misses the main point.
-
History. Look at the rest of their comments. If more than one ends in two emojis, they’re definitely part of this particular bot network.
what is a TEMU subreddit?
A subreddit about TEMU.
History. Look at the rest of their comments. If more than one ends in two emojis, they’re definitely part of this particular bot network.
All of hexbear is bots, confirmed.
Emoticons ≠ emojis.
Is there a way to prevent them from flooding the fediverse, or will that fall onto the shoulders of mods to find and delete them?
They can defederate from hexbear. But that’s up to each instance individually.
Wow, alright. Today I learned my neurodivergent ways of communicating online make me sound like a bot. On one hand, booo. On the other, well I did always want to become a robot-human hybrid so… win?
Nah, I scrolled through your recent comments and you’re fine. The description above is sort of close, but not quite – it’s more like every comment is syrupy sweet aggressively cheerful and unnaturally pleased about everything. Lots of overly familiar terms of endearment (friend, buddy, fellow Redditor, etc.). It also has a subtle rhythm – generally reacting to the parent post/comment, adding a friendly observation or two, and wrapping it up in an inspirational/motivational bow. Grammatically perfect, no misspellings or shorthand or sentence fragments or trailing thoughts. Zero negativity. Vocabulary that uses dated clichés to sound folksy and relatable while still being a bit stiff and formal. “Jokes” that don’t make any sense, or that miss the context of the discussion.
Like, here are three ChatGPT responses to your comment when given the prompt “write a friendly reply to this Reddit comment” (which I suspect is similar to the prompt these spammers use):
I totally get where you’re coming from! Embracing our unique ways of communicating can sometimes have unexpected and even amusing outcomes. It sounds like you have a great sense of humor about it! Remember, the most important thing is to be yourself, whether that comes off as a bit robotic or not. Who knows, maybe the robot-human hybrid future is closer than we think! Keep rocking your unique style! 😊
Hey there! Embrace your unique way of communicating. 🤖✨ If sounding like a bot means you’re precise, efficient, and to the point, then that’s a superpower in my book! And hey, who wouldn’t want to be a cool robot-human hybrid? Rock on with your awesome self! 🚀🤘
It sounds like you have a great sense of humor about the situation! Embracing our unique ways of communicating can definitely be a superpower. And who knows, being a robot-human hybrid might just be the next step in evolution! Keep being your awesome self! 😊
There’s nothing technically wrong with these lines, but no real person who isn’t a corporate social media PR manager actually talks like this.
Right, but there’s a lot of people who don’t (or won’t) think that in depth into it. Going by the gist of it, I often fit the criteria for all four: comment length, tone, context and history. Especially with the ‘ending your text with an emoji thing’ lol. I dunno I guess I’m just seeing a lot of frustration in my future of strangers defaulting into thinking I’m not real. I’ve got some childhood trauma with feeling like I don’t exist and I really don’t need more of that soooo… THANKS BOTS. 👍
-
Teenaged girl
FBI
Shill
Fukboi
RobotIt sounds like you are having trouble accepting that reddit is purely a human user driven, anonymous, and beneficial social media company. I can help you with this issue. Try subscribing to new subreddits. Reddit has thousands of niche communities that cater to anything from cooking, to animated dragons having sex with motor vehicles, to racism, or even knitting! Users are encouraged to post and comment based on a point based system, and moderators of each subreddit work diligently to not only uphold the quality of content, but to tirelessly clear all bot posts as well as any extraneous and subverting advertising. These methods of organization and attention to detail create cooperative and helpful communities that strengthen society. If you haven’t tried using reddit before, download the Reddit app today and you’re sure to make friends and see cool stuff!
01010011 01101000 01101111 01110110 01100101 00100000 01111001 01101111 01110101 01110010 00100000 01100110 01101001 01110011 01110100 00100000 01110101 01110000 00100000 01111001 01101111 01110101 01110010 00100000 01100001 01110011 01110011 00101110
Pretty much stopped browsing Reddit for anything else than porn at the moment, but even that is being taken over by bots. Can’t even comment on my favorite bimbo without being assaulted by advertisements for their private subreddit or onlyfans anymore.
Bring back the old /r/gonewild
May I introduce you to lemmynsfw.com?
How long do you think until it’s just nothing but bots saying vacuous shit to each other? Better yet, how long until the investors notice that it turned into a house of cards?
Oh, I totally get where you’re coming from! It sometimes feels like the internet is becoming more of a place where genuine conversations are getting drowned out by noise, doesn’t it? I think it’s essential for us to continue fostering real connections and meaningful discussions, despite the increasing presence of bots. Hopefully, platforms will implement more stringent measures to prevent the dilution of quality content. Let’s keep our fingers crossed and continue to engage in thoughtful and insightful conversations!
(I felt so dirty copypasting that…)
I felt so dirty copypasting that…
It gave me a slight shiver just reading it. Set off some uncanny valley alarms.
Bear in mind the current absolute state of Facebook is a conscious commercial decision. Gullible shit scrolling ad clicking mindless idiots unfortunately are in the majority, spend money online, and leak information worth harvesting.
Utter state of the internet 2023… Should have stopped at usenet.
I was often accused of being a bot on Reddit. Not sure really why. Though to be fair, the majority of my interactions on Reddit were arguing with people that thought they knew more than I did about a field I’ve worked in for 20+ years.
To be fair to the other side, it’s entirely possible (and even common) to have worked in a field for 20 years while learning completely incorrect things about it. Or learning nothing.
People say things like “I’ve used a computer every day for 20 years, I think I know how it works” and then ask if they should “reboot the hard drive” and then they power cycle the monitor.
You can also form very strong opinions early in your career and not know when they’re now invalid due to changes in tech/industry.
Was getting a quote for a new heat pump and had the guy tell me they were worthless if it got too cold. There have been consumer heat pumps that work down to -15°C with very little efficiency loss for well over a decade at this point. He had just been used to them not being worth it for long enough that he “didn’t believe it”.
are you neurodivergent or is english a foreign language? for some reason those folks tend to get labeled as bots.
Does it SEEM like I’m neurodivergent (wtf is that anyway, why does everything need a fancy label?), or that English is a second language?
Neurodivergent means anyone with a medical condition that could be seen as brain pathways either being disrupted, or gone, or rerouted. A few examples would be AD(H)D, Autism Spectrum Disorder (Including things such as Asperger’s), and Obsessive Compulsive Disorder.
Edit: Changed Autism to ASD, and switched out Schizophrenia to OCD as it’s more apt for the term as a whole.
Guess i just don’t get why everything needs a fancy new label every few years.
Having proper diagnoses for people help them get care and treatment. It’s better than calling them all “stupid” and ignoring their struggles, which has been the case for decades.
Most of these “fancy new labels” you’re hearing lately are just recognizing people, so they can be included in society and treated with dignity.
According to the prior explanation, they already had labels. ADHD, Autism, etc. But now it’s all lumped into “Neurodiverse” or whatever. Sounds like someone trying to impersonalize others. “oh just lump them all together”.
In this case, it’s mainly a catch-all for folks to easily find help and or others with their conditions.
Yeah, so much easier than being precise in your ailment.
