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).
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?
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 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.
The term hallucination bothers me more than it should because fabulation better describes what bots do.
Then let’s start using it!
Needs some em dashes!
And semicolons!