How do we know that the people on reddit aren’t talking to bots? Now, or in the future? what about lemmy?
Even If I am on a human instance that checks every account on PII, what about those other instances? How do I know as a server admin that I can trust another instance?
I don’t talk about spam bots. Bots that resemble humans. Bots that use statistical information of real human beings on when and how often to post and comment (that is public knowledge on lemmy).
You must log in or register to comment.
I CAN ASSURE YOU THAT I AM A HUMAN, JUST LIKE YOU ARE. I ENJOY HUMAN THINGS LIKE BREATHING AIR AND DRINKING
LUBRICANTWATER.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.
GREETINGS FELLOW HUMANS!
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?
I was deadass getting into it before I realized i was a prompt lol
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…
Wait, what, is this true?
Eh, it’s one of those perpetual rivalry things where the answer will probably never be known, and doesn’t really matter except when it comes to petty squabbles between nations.
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?
deleted by creator
What the fuck did you just fucking say about me, you little bitch? 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.
October thirnteeurst lmao.
I feel your relief
deleted by creator
Glad you’ll still be celebrating October 3rd with us.
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.
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.
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.
