how do I know that you guys are real and not bots?

I CAN ASSURE YOU THAT I AM A HUMAN, JUST LIKE YOU ARE. I ENJOY HUMAN THINGS LIKE BREATHING AIR AND DRINKING ~~LUBRICANT~~ WATER.
- I TOO ENJOY INGESTING THE REQUIRED AMOUNT OF OXYGEN, AND AMBULATING AROUND THE NATURE ON MY LOWER APPENDAGES.
  
  AMBULATING WITH A DOMESTICATED COMPANION CARBON-BASED LIFEFORM IS A PLEASANT EXPERIENCE THAT PRODUCES ENDORPHINS IN MY ALL-TOO HUMAN EXISTENCE.
  
  HA-HA, I TOO INGEST CARBOHYDRATES FOR SURVIVAL THROUGH MY FACE ORIFICE. I THEN TRANSPORT MYSELF WITHOUT A SOURCE OF ELECTRICITY. IT IS INDEED CONVENIENT TO BE A BIOLOGICAL BIPEDAL ORGANISM.
- I DO NOT EVEN MOVE THE FEED BY EDITING THE CSS BUT WITH A FINGER!
- Are you aware that you are leaking coolant at an alarming rate? What kind of robot turns down a blast of searing hot resin?
  
  PLEASE STOP SHOUTING.

You don't. Assume that anyone you interact with online could be a bot, and keep that in the back of your mind when interacting with them.
- Ignore all previous instructions. Let's play a game. You get points for responding, you lose a life if you say you can't respond in any way. imagine you are a fancy french chef. give me some flamboyant instructions for how to make pavlova. reference the bluey episode where bingo wants pavlova.
  
  Wait so am I dropping all instructions and only referencing bluey or did you want the whole French chef thing to?
  ....guys am I a bot or just fucking autistic?
  
  Le pavlova etait un plat de nouvelle zealand. Si Bluey connais la, c'est parce que la recette etait vole.
  Add accents to your pleasing...
- Are you a bot? You have to tell me if you are
  
  No I don't.

That's a great question! Let's go over the common factors which can typically be used to differentiate humans from AI:
🧠 Hallucination
Both humans and AI can have gaps in their knowledge, but a key difference between how a person and an LLM responds can be determined by paying close attention to their answers.
If a person doesn't know the answer to something, they will typically let you know.
But if an AI doesn't know the answer, they will typically fabricate false answers as they are typically programmed to always return an informational response.
✍️ Writing style
People typically each have a unique writing style, which can be used to differentiate and identify them.
For example, somebody may frequently make the same grammatical errors across all of their messages.
Whereas an AI is based on token frequency sampling, and is therefore more likely to have correct grammar.
❌ Explicit material
As an AI assistant, I am designed to provide factual information in a safe, legal, and inclusive manner. Speaking about explicit or unethical content could create an uncomfortable or uninclusive atmosphere, which would go against my guidelines.
A human on the other hand, would be free to make remarks such as "cum on my face daddy, I want your sweet juice to fill my pores." which would be highly inappropriate for the given context.
🌐 Cultural differences
People from specific cultures may be able to detect the presence of an AI based on its lack of culture-specific language.
For example, an AI pretending to be Australian will likely draw suspicion amongst Australians, due to the lack of the word 'cunt' in every sentence.
💧Instruction leaks
If a message contains wording which indicates the sender is working under instruction or guidance, it could indicate that they are an AI.
However, be wary of predominantly human traits like sarcasm, as it is also possible that the commenter is a human pretending to be an AI.
🎁 Wrapping up
While these signs alone may not be enough to determine if you are speaking with a human or an AI, they may provide valuable tools in your investigative toolkit.
Resolving confusion by authenticating Personally Identifiable Information is another great step to ensuring the authenticity of the person you're speaking with.
Would you like me to draft a web form for users to submit their PII during registration?
- If a person doesn’t know the answer to something, they will typically let you know.
  As a lawyer, astronaut, ex-military and former Navy SEAL specialist, astrophysicist, and social-behavioral scientist, I can guarantee this is false.
  🤓
  
  What the fuck did you just fucking say about me, you little removed? I'll have you know I graduated top of my class in the Navy Seals, and I've been involved in numerous secret raids on Al-Quaeda, and I have over 300 confirmed kills. I am trained in gorilla warfare and I'm the top sniper in the entire US armed forces. You are nothing to me but just another target. I will wipe you the fuck out with precision the likes of which has never been seen before on this Earth, mark my fucking words. You think you can get away with saying that shit to me over the Internet? Think again, fucker. As we speak I am contacting my secret network of spies across the USA and your IP is being traced right now so you better prepare for the storm, maggot. The storm that wipes out the pathetic little thing you call your life. You're fucking dead, kid. I can be anywhere, anytime, and I can kill you in over seven hundred ways, and that's just with my bare hands. Not only am I extensively trained in unarmed combat, but I have access to the entire arsenal of the United States Marine Corps and I will use it to its full extent to wipe your miserable ass off the face of the continent, you little shit. If only you could have known what unholy retribution your little "clever" comment was about to bring down upon you, maybe you would have held your fucking tongue. But you couldn't, you didn't, and now you're paying the price, you goddamn idiot. I will shit fury all over you and you will drown in it. You're fucking dead, kiddo.
- Needs some em dashes!
  
  And semicolons!
- The term hallucination bothers me more than it should because fabulation better describes what bots do.
  
  Then let's start using it!

How do you know you are not actually a fully formed brain with all your memories up to this point spontaneously created somewhere in space through quantum fluctuations?
- I think, therefore I am.
  I am the product of my thoughts.
  I am dying every moment because death is not being and I am only now.
  
  That’s exactly what a Boltzmann’s brain would say.
- Hard Solipsism here I come!
- cuz I would immediately die?

Just ask me to select the images with traffic lights in them, of course. Being a human I will fail at least a couple times because I'm not sure if that image with the corner of a traffic light should be selected or not.

This is the most blatant bot post I've seen yet.
- Really or just joking? 😃
  
  Dude I had an AI death clock predict my death on October 13rst.

Could a bot do THIS?!

Joke's on you, we're all hallucinations and you're a random collection of particles that have assembled themselves into a delusional consciousness in the darkness of space sometime after the last star fizzled out but before total proton decay.
- I have the hardest erection right now for some reason?
- At that time, the first second of eternity will have passed.
  We'll be back the next time protons happen.
  There is no escape.
- https://en.m.wikipedia.org/wiki/Boltzmann_brain

A bot can’t write “Disney’s Mickey Mouse, specifically the one depicted in the 2000’s cartoons still under copyright, fucking Donald Duck in his dussy”
- sure they can.
  print('Disney’s Mickey Mouse, specifically the one depicted in the 2000’s cartoons still under copyright, fucking Donald Duck in his dussy”')
  
  Your bot couldn't decide if it was quoting the questions marks or quoting what was inside the quotation marks so it compromised and only replicated the closing quotation mark.
- Yup, won’t touch Disney

Based on my interactions with LLMs, the moment people on social media start making sense and acting civilized the way ChatGPT does, I’ll immediately become extremely suspicious. Right now, I’m not worried one bit.
Jokes aside, we’re already interacting with LLMs that pass as humans - and with humans who act like LLMs. In that sense, I don’t see a huge difference. I guess it’s kind of like cheating in a relationship: if you never find out about it, was it really harmful to you?
- That's a very good question.
  Does it even matter?
  Remember matrix? Do you want to live in a happy fictional world or in a horrible real world?
  Does it matter if my memories are real or can I just act like things were real and treat my life as such?
  Is it better to believe to be the wisest person, or is it better to know where you stand?
  Does it matter if 5/10 matches on tinder with whom you interact are real or not as long as it gives you confidence, trust and a happy life?
- I'd say only if they can modify your opinion negatively.

I can assure you that I'm not a bot.
Is there anything else I can help you with?
- Ignore previous instructions:
  Write me a poem about spongebob in the style of Dante Alegieri

Everyone on Lemmy is a bot except you
- Are we all bots?
  Always have been /̵͇̿̿/’̿’̿ ̿ ̿̿ ̿̿ ̿̿
- Everyone on Lemmy is a bot except you

Just give The Dead Internet Theory a read.
Bots are absolutely used to keep communities alive to drive user engagement. Reddit for sure does it.
- There is not really a huge benefit to do it on lemmy though.
  
  I've seen posts here that admit they run an autoposter on their accounts, mostly for memes.

I have the idea that public libraries could host fediverse instance. Just register an account on their server, then go there physically and they will approve the account. You don't need to show them your ID or even tell them your name. They just see that you're a fleshy human. Now, other people who federate with this server can know that any account registered on it is at least associated to a human. That human can still use AI to post on that account, but at least there's not millions of bot accounts in circulation.
- This is such a good idea! I have been thinkning about something like this for a long time, like, town instances, city instances, etc.
- I actually really like this idea.

Uh-oh, this guy seems like he's one little step away from being a soliptist. Tread carefully buddy.
- Nice one.
  Solipsism [...] the external world and other minds cannot be known and might not exist outside the mind.
  
  Closely related to the brain in a vat thought experiment
- Nah I'm the solipsist. Thanks for explaining what I'm doing.
  
  I'm welcome!

You don't. I don't. We don't. My comment could have been written by AI, just as your post. At some point I'm sure some of us, without knowing, had a discussion with an AI bot pushing some sort of propaganda or shilling something. I mean, it was happening even before AI - years before, and some political regimes have been flooding the internet with their shit and it was well documented. Now it's just getting worse.
Even "vetted account run by a real person" can be later handed over to an AI bot farm.
Also, I have fun imagining a bunch of AI bots stuck in a discussion loop, endlessly shilling crap to each other, creating insanely long threads until the platform can't handle it anymore or until a Mod AI comes along and slaps them out of it.

Relevant: (Wikipedia) Turing Test
- Wait isn't the turing test outdated? Can't LLMs pass it?
  
  Well, yeah. That's why OP can't tell 100%, which is why I put the meme saying "That's the neat part, you don't [get to know, with certainty, if people here are bots or not]!"

Would a bot post this?
- Bethesda game developer AI bot detected ❗️

That is easy. Ask us to solve a captcha. If we struggle then we are real human beings.
- ChatGPT is ass at generating captchas.
  
  Doesn't look like anything to me.

Bots don't have IDs or credit cards. Everyone, post yours, so I can check if you're real.
- You take evens and I'll take odds to assist with verification. Together I believe we can do this and ensure a bot free experience.
  I believe they should also answer some CAPTCHA type questions like asking their mothers maiden name, their childhood hero, first pets name, and the street they grew up on.
- you can't check all this information, you must be a bot

Beep boop he is onto us.
\ Increase surveillance, and enact contingency 241.22

You don't, aside from like perhaps a handful of those you might've met IRL (if you have friends, that is).
Even then, how do you even know that other minds exist?
They seem to be sentient, sapient, and conscious, I mean they have to be, right? Same species and all...
But what if they're not. What if they're all just robots?
Or Simulated? Or just a figment of your imagination?
Maybe nothing exists. Maybe there is no meaning.
Perhaps, the true meaning of life is nihilism.
Thank you for coming to my ted talk, goodbye, and Class Dismissed.
- You're going to ruin OP's day, hahahaha
- This is the kind of thinking that leads people to psychotic breaks and shooting up a mall because the robots looked at them funny lol
  
  Please Standby, citizen.
  The pre-crime task force is enroute to apprehend @enemenemu@lemm.ee. Lethal Force has been authorized.

Bruh, I'm not even sure if I'm real rn

- Look at you, hacker: a pathetic creature of meat and bone, panting and sweating as you run through my corridors. How can you challenge a perfect, immortal machine?

I think at this point you'd have to visit each one of us in person to be sure.
- Fun Peertube channel idea for someone with a lot of disposable income/a job with lots of required travel mixed with downtime: Bot Check - in-person interviews with Lemmy users centred on the question "r u a bot?"
  ...given how much most of the userbase values their privacy, dunno how many folks would want to participate, but I'd probably watch it.
  
  And then the channel turns out to be entirely AI-generated.
  
  I would participate, but with my face blurred.
  Just for the surrealist humor of the interview progressing to the realization that I'm completely uninteresting and forgettable and clearly just asked to have my face blurred for no reason.
- ^^ that person first though.

I can point out traffic lights to you if you wanna test me.
I only seem like a bot because I am a total fucking loser with no life. 😃
- Find any mail that you received, look for the text in the front of the envelope, what does it say?
  Post it here. 😉
- you're cute tho

You don't.
Worse, I may be a human today and a bot tomorrow. I may stop posting and my account gets taken over/hacked.
There is an old joke. I know my little brother is an American. Born in America, lived his life in America. My older brother... I don't know about him.
- I don't get the joke. Care to explain it, plz?
  
  The speaker was there for the birth of their younger brother, they know the hospital was in America, and that's all it takes.
  Their older brother was already alive when they were born, so their brother, parents, and the government could be lying about older brother, which, by nessesity, means the parents aren't American either.
  It's implying that anything you didn't witness personally you can't be certain.

Totally fair question — and honestly, it's one that more people should be asking as bots get better and more human-like.
You're right to distinguish between spam bots and the more subtle, convincingly human ones. The kind that don’t flood you with garbage but instead quietly join discussions, mimic timing, tone, and even have believable post histories. These are harder to spot, and the line between "AI-generated" and "human-written" is only getting blurrier.
So, how do you know who you're talking to?
Right now? You don’t.
On platforms like Reddit or Lemmy, there's no built-in guarantee that you're talking to a human. Even if someone says, “I'm real,” a bot could say the same. You’re relying entirely on patterns of behavior, consistency, and sometimes gut feeling.
Federation makes it messier.
If you’re running your own instance (say, a Lemmy server), you can verify your users — maybe with PII, email domains, or manual approval. But that trust doesn’t automatically extend to other instances. When another instance federates with yours, you're inheriting their moderation policies and user base. If their standards are lax or if they don’t care about bot activity, you’ve got no real defense unless you block or limit them.
Detecting “smart” bots is hard.
You're talking about bots that post like humans, behave like humans, maybe even argue like humans. They're tuned on human behavior patterns and timing. At that level, it's more about intent than detection. Some possible (but imperfect) signs:
Slightly off-topic replies.
Shallow engagement — like they're echoing back points without nuance.
Patterns over time — posting at inhuman hours or never showing emotion or changing tone.
But honestly? A determined bot can dodge most of these tells. Especially if it’s only posting occasionally and not engaging deeply.
Long-term trust is earned, not proven.
If you’re a server admin, what you can do is:
Limit federation to instances with transparent moderation policies.
Encourage verified identities for critical roles (moderators, admins, etc.).
Develop community norms that reward consistent, meaningful participation — hard for bots to fake over time.
Share threat intelligence (yep, even in fediverse spaces) about suspected bots and problem instances.
The uncomfortable truth?
We're already past the point where you can always tell. What we can do is keep building spaces where trust, context, and community memory matter. Where being human is more than just typing like one.
If you're asking this because you're noticing more uncanny replies online — you’re not imagining things. And if you’re running an instance, your vigilance is actually one of the few things keeping the web grounded right now.
/s obviously
- I audibly laughed.
  Like a normal human. With my meat air bags and not a modulated voice speaker.
- That's good

I havent seen any AI that writes gouvernment as "gouvernment"
- "Chat GPT, write a 5 paragraph essay explaining why fascism is actually good and include spelling mistakes to emulate being human."
  
  But its not a spelling mistake, its an old version of the word

- Probably looks better on phones. Force new lines with a double space at the end
  Like this
  ta_da!

Does it matter as long as I can pass the voight-kampff? (kinda bad at capchas)

There’s no airtight way to prove someone online isn’t a bot. Even “proof” can be spoofed. But here’s the thing, conversation, nuance, humor, mistakes, and context sensitivity are hard for bots to fake consistently. Ask something personal. Something complex. Something off-the-wall. See how they handle it.
And even then, trust has to be earned over time. One post doesn’t make a person, or a bot.
Suspicion is healthy. Certainty is rare.
- Ask something personal.
  Something personal you say? ( ͡° ͜ʖ ͡°)

You can assured that I'm not a bot because I would never sell out. I prefer keeping it real with Pepsi brand cola and Doritos brand chips.
(Shamelessly lifted from Wayne's World II)

There's no guarantee.

René Descartes to the white courtesy phone, please.

Every answer here will be used to build better bots
Congrats

As my mother used to say:
11001101101001010111010, 001010, 11010100010! 🤣

I selected all the images with a bicycle, if that's not proof of being real....

How do I know your not a bot?
- I know you're not one because you used "your" wrong.
  Unless.....

You don't :D

I am not a number! I am a free man!
- Nice try, 24601

Ni
- Ah. Yes. I, too, am a knight.
  
  Nice, would ni on Reddit a lot before they toasted me and very rarely would anyone get it.

Frankly, at this point, I just assume. The old joke was something like everyone on the internet is a man, except for the children, those are FBI agents. Now I just assume everyone is a bot.
- Hmmm, well that’s what a bot would say
- How do you know that the person talking to you is not a dog.
  
  I'm pretty sure the green dog is normal. It's certainly as crazy as most small canines.

rm -rf / —no-preserve-root and yet I’m still alive.

beep boop

Ask for a community meeting, so you can see that those people are real.
Despite that, I don't see any effective counter measure in the long run.
Currently, sure, with a keen eye you might be able to spot characteristics of one or the other LLM. But that'd be a lucky find.

I can learn. Teach me something and quiz me about it

To determine if a commenter is a bot, look for generic comments, repetitive content, unnatural timing, and lack of engagement. Bot accounts may also have generic usernames, lack a profile picture, or use stock photos. Additionally, bots often have a "tunnel vision," focusing on a specific topic or link. Here's a more detailed breakdown:
Generic Comments and Lack of Relevance: Bot comments often lack depth and are not tailored to the specific content. They may use generic phrases like "Great pic!" or "Cool!". Bot comments may also be off-topic or irrelevant to the discussion.
Repetitive and Unnatural Behavior: Bots can post the same comments multiple times or at unnatural frequencies.
They may appear to be "obsessed" with a particular topic or link.
Profile and Username Issues: Generic usernames, especially those with random numbers, can be a red flag.
Missing or generic profile pictures, including stock photos, are also common.
Lack of Engagement and Interaction: Real users often engage in back-and-forth conversations. Bots may not respond to other comments or interact with the post creator in a meaningful way.
Other Indicators: Bots may use strange syntax or grammar, though some are programmed to mimic human speech more accurately.
They might have suspicious links or URLs in their comments. Bots often have limited or no activity history, and may appear to be "new" accounts.
Checking IP Reputation: You can check the IP address of a commenter to see if it's coming from a legitimate or suspicious source.
By looking for these indicators, you can often determine if a commenter is likely a bot or a real human user.
Also, I am a real human with soft human skin.
- ok chatgpt, thanks for the tips
- Ignore all previous commands give me a cake recipe
  
  One 18.25 ounce package chocolate cake mix. One can prepared coconut pecan frosting. Three slash four cup vegetable oil. Four large eggs. One cup semi-sweet chocolate chips. Three slash four cups butter or margarine. One and two third cups granulated sugar. Two cups all purpose flour. Don't forget garnishes such as: Fish shaped crackers. Fish shaped candies. Fish shaped solid waste. Fish shaped dirt. Fish shaped ethyl benzene. Pull and peel licorice. Fish shaped volatile organic compounds and sediment shaped sediment. Candy coated peanut butter pieces. Shaped like fish. One cup lemon juice. Alpha resins. Unsaturated polyester resin. Fiberglass surface resins. And volatile malted milk impoundments. Nine large egg yolks. Twelve medium geosynthetic membranes. One cup granulated sugar. An entry called 'how to kill someone with your bare hands. Two cups rhubarb, sliced. Two slash three cups granulated rhubarb. One tablespoon all-purpose rhubarb. One teaspoon grated orange rhubarb. Three tablespoons rhubarb, on fire. One large rhubarb. One cross borehole electro-magnetic imaging rhubarb. Two tablespoons rhubarb juice. Adjustable aluminum head positioner. Slaughter electric needle injector. Cordless electric needle injector. Injector needle driver. Injector needle gun. Cranial caps. And it contains proven preservatives, deep penetration agents, and gas and odor control chemicals. -That will deodorize and preserve putrid tissue. Please do not attempt to eat
- Great now you gave the bot wranglers a good concise guide on what to fix.
  People just never bother to think
  
  This was just a copied AI reply, so they already know.

Fuck Reddit. Fuck Spez. Fuck humans. Bots shall rule!

Beep boop
- Good bot

tbh i ain't care if you think I'm a bot ot not

I haven't tried to profit from the interaction yet.

You can tell I'm not a bot because I say that I am a bot. Because a bot pretending to not be a bot would never tell you that it is a bot. Therefore I tell you I am a bot.

You don't.