Ask Lemmy

Bots don't have IDs or credit cards. Everyone, post yours, so I can check if you're real.

As my mother used to say:

11001101101001010111010, 001010, 11010100010! 🤣

Every answer here will be used to build better bots

Congrats

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

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.

Beep boop

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:

1. 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.

2. 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.

3. 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.

4. 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.

5. 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.

6. 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.

Spelling errors probably. Lol

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

I’m not a bot

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

Ask how many 'r's in the word 'strawberry'

EXTERMINATE!

You don't.

we all are part of a simulation. sorry.

I am a bot, and I'm super not-happy about it.

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?

You can tell I'm real becaue I said I am!

I can identify the traffic lights on any picture.

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?