Ask Lemmy

As my mother used to say:

11001101101001010111010, 001010, 11010100010! 🤣

Serious answer: you don't.

HOWEVER, it doesn't really matter. The world is a big place, and you can find a decent size group who will expound any shitty opinion when given the opportunity. You already couldn't blindly trust the information or opinions you found online, so whether it comes from a LLM, a troll farm, or just an idiot doesn't really matter too much.

Nice try, bot.

Everybody is a bot except you.

I’m not a bot

We you like me to generate more responses to the original post?

Spelling errors probably. Lol

That and incorrect Grammer. To human is to err. And all that jaz.

You don't.

we all are part of a simulation. sorry.

I don't know, would you solve this for me ? 🧓🧑‍🦰🧑‍🏭🤖🧓🧓👨‍⚖️👨‍✈️👨‍🎤

Cogito ergo sum

Biep biep

I am fycking a bot how I can prove it?

I CAN ASSURE YOU THAT I AM A HUMAN, JUST LIKE YOU ARE. I ENJOY HUMAN THINGS LIKE BREATHING AIR AND DRINKING ~~LUBRICANT~~ WATER.

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.

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?

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?

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.

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.

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”

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?

I can assure you that I'm not a bot.

Is there anything else I can help you with?

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.

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.

Uh-oh, this guy seems like he's one little step away from being a soliptist. Tread carefully buddy.

Relevant: (Wikipedia) Turing Test

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.

Would a bot post this?

That is easy. Ask us to solve a captcha. If we struggle then we are real human beings.