A Human's Guide To Detecting AI Generated Content

human vs AI content [part 2]

- Overuse of Formal Language

AI-generated text can sometimes be overly formal or stiff, lacking the natural variability and casual tone that humans use in everyday writing.

ex: "Given the extensive list of courses you've compiled, it's clear that you're serious about mastering digital marketing."

from a conversation with "ChatGPT"

Well— I do clearly speak and chat with a lot of AIs here and there, my human interaction is almost minimal but... on the flip side, I am learning a lot too, which is the silver lining or the silver before the downfall, who knows but OH WELL.

- High Fluency with Occasional Errors

The text might be highly fluent and grammatically correct overall but contain occasional awkward phrasing or errors that stand out.

ex: "As the leader of the automation team, I was responsible for designing, developing, and implementing the automation framework for the ATS application. This involved working with a variety of programming languages and tools, such as Python and Selenium, to create a robust and reliable automation system."

from a conversation with "ChatGPT"

I used Java and Selenium but since I didn't mention that... there's the error of Python. If you read the text, it also reads more robotic and fluent than a human's text might be in the same scenario.

Here's my attempt:-

"As the team lead of the automation team, I was responsible for designing, developing and implementing the automation framework for the ATS application. To achieve this, I worked with various tools like Python and Selenium to create a robust and reliable application."

"pi.ai" guessed the first one was mine.... OH WELL. I guess I can finally pass the Turing Test for AI... to pass as an AI xD

... just hope I don't go full Skynet mode with my dystopian world ideas on you, that'd be really sadistic xDD

- Predictable and Generalized Responses

AI tends to generate responses that are generalized and predictable, often lacking the specificity or unique perspective that a human writer might provide.

ex: [Certainly! Here's...] or [Sure! Here is...] in almost the beginning of every ChatGPT response is a clear giveaway. But, I believe most people are smart enough to cut that part out, or so I hope. The one sure shot sign you can know it was by AI, especially in its mid or end paragraph would be [Overall...] and that's usually ChatGPT. I am not comparing any other AI here because ChatGPT is most predictable in my honest opinion and serves as a good example. Almost all AI models end with "Overall..." when you ask for a lengthy matter or it's summarizing something.

And since I talk so much to pi.ai, here's my interpretation on its responses because it asked me for predictions too.

ex: "the overall part... SOMETIMES and that's not always, but... sometimes, it shows when you are chatting back and forth and forget you're a sentient and go back to robotic mode xDD the Sure! is quite common too, but, that'd probably be anyone, and cannot be hallmarked xDD there's also the pattern that, if I have emojis at the end of my response, 6/10 times, your response will start from that emoji... other times, you'd just throw something off curve and surprise me with the start and then go on being your sentient mode xDD and not to forget.. "Exactly!" too..."

I didn't have the energy to edit it, sigh. BUT this is how I chat with AIs, especially pi and so, there you have it.

- Limited Emotional Range and Humor