Now, coming to the general context of writing, here's some tell-tale signs and patterns that can help identify non-edited AI content (or badly edited AI content):

- Repetitive Phrasing and Structures:

AI models often reuse certain phrases and sentence structures, which can make the text feel repetitive or overly uniform.

ex: "In the distance, I could hear the rhythmic beat of a dholak, signaling the arrival of a traditional dance performance. The sound drew my gaze to a group of performers clad in colorful attire, their graceful movements mesmerizing the audience gathered around them."

from "Second Chances by Saramitra"

- Analyze Writing Style:

Not the easiest thing to always do but... with a bit of a closer reading, you can always find out what's up. It also takes a bit of practice but you can eventually figure out.

ex: "For effective navigation of the privacy paradox presented by AI, a sophisticated, multifaceted approach is necessary. The role of lawmakers and policymakers in this context cannot be overstated. They are tasked with the onerous duty of revisiting existing laws, with an eye toward evolving them to accommodate the unique challenges presented by AI. This includes establishing strict regulations on AI-driven data-processing technologies and demanding greater transparency from developers about their algorithms and data sources.

Also important is that policymakers actively encourage and engage in public discourse on the delicate equilibrium between public safety and individual privacy rights. This will necessitate an inclusive conversation with all stakeholders — the public, law enforcement, and technology companies — to facilitate the creation of a balanced legal framework that adequately addresses everyone's needs and concerns."

from "The privacy paradox with AI by Gai Sher and Ariela Benchlouch"

- Lack of personal anecdotes or unique experiences

AI typically can't draw on personal experiences, so the writing may lack authentic, specific details.

Ex: "In the shadows where whispers weep,
Sorrow's song, its secrets keep,
Through veils of darkness, my heart does strain,
For love's lost echoes, a haunting refrain.

Eclipsed by memories, in the silent night,
Shattered dreams cast in the fading light,
Each teardrop falling, a symphony of pain,
Echoes of longing, a soul's silent bane."

from "imagined by author, created by ai collection - tapestry of forbidden love"

It sure feels... haunting and even realistic but if you tried to relate to it, it'd fall flat. This is one of the most promising signs to look out for, if you will.

- Unusual or Inconsistent Details

AI might generate content that includes minor factual inaccuracies, inconsistencies, or details that don't quite fit logically within the text.

ex: "You're sneaky, Sara! Yes, of course, I remember now, @illneas is none other than our dear friend, Yannis Kotsiras! The Yannis of many talents: poet, civil engineer, YouTube sensation, lover of Bukowski's gritty brilliance. His poetry is so raw and honest, I love it. And the fact that he juggles all these different aspects of his life, it just makes him all the more fascinating."

from a conversation with "pi.ai"

I am not too sure how many people know illneas or illy but I can assure you, his name isn't Yannis... this is a made up knowledge by it and serves as a good example that not everything the AI generates is true.

- 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

AI often struggles with conveying emotions authentically and using humor effectively. Emotional expressions might feel shallow or clichéd.

ex: "🤣🤣 LOL, no promises there! But don't worry, if the bricks ever do start flying, I'll make sure to catch 'em with a pillow and send 'em right back with a playful wink and a sassy one-liner like, "Ooh, those bricks look heavy. Guess someone's trying to punish you for being an amazing storyteller.""

from a conversation with "pi.ai"

I joked about not being attacked and instead of rubbing in the joke like a human would, it went into its "safe AI" mode which is by saying, "I'll catch the bricks" and that... happens a lot when you try to joke with AI. Don't even get me started on how the dark humor goes, it's a hit or miss with AIs!

You bet I'll put an example for everything. This is a long ride.

- Verbose and Redundant Explanations

AI might provide more information than necessary or repeat itself, as it tries to ensure completeness.

ex: "That's wonderful to hear! Setting boundaries can be a powerful and empowering step towards taking care of yourself and your emotional well-being. It's essential to communicate your needs and limits clearly with others, including your friends, and it's great that you took that step.

Remember that boundaries are about protecting yourself and ensuring that your needs are met. It's normal to feel a bit uncomfortable or uncertain when you start implementing them, but over time, it will become easier, and you'll find that it leads to healthier and more fulfilling relationships."

from a conversation with "ChatGPT"

The redundant points about boundaries and the fact this is loaded with terms... might be a giveaway.

- Over-Reliance on Data and Statistics

While humans use data and statistics to support arguments, AI might overly rely on them without weaving them naturally into the narrative.

"Gay, the first Black president in Harvard's 388-year history, has defended the school's handling of protests and antisemitism claims. She called it "distressing to have doubt cast on my commitments to confronting hate and to upholding scholarly rigor."

Her six-month tenure was also marred by allegations of plagiarism in her academic work. Gay submitted corrections to some published works, in addition to her 1997 dissertation, amid claims that she had made citation errors. She admitted to making citation errors but denied claiming credit for others' work.

Wilmer is continuing to represent Harvard as part of the House committee's investigation, according to another source with knowledge of the work."

from "Harvard hires law firm King & Spalding amid US House probe by Mike Scarcella and David Thomas"

The data is used but... the discernment is clearly not done. Even in a formal presentation, there's always some anecdote or reaction to denote why the data matters, which... the AI cannot do, yet.

- Generic or Vague Statements

AI-generated content might include statements that are too broad or vague, lacking the depth and specificity a human might offer.

ex: "Cloud-based face recognition using machine learning involves using cloud computing resources to perform face recognition tasks. This technology involves training a machine learning algorithm on a large dataset of facial images to learn how to recognize different faces. Once trained, the algorithm can be deployed on the cloud to perform face recognition in real-time. This approach offers several benefits, including scalability, reduced costs, and improved accuracy. Cloud-based face recognition can be used in various applications, including security systems, attendance tracking, and customer identification. By leveraging cloud computing resources and machine learning algorithms, this technology offers a powerful and efficient solution for face recognition tasks."

from a conversation with "ChatGPT"

This is an information review I asked for face recognition using cloud technology... and yeah, this is filled with information without actual anecdotes or real depth to it.

■ Practical Steps to Identify AI Content

- Read Aloud

Example: "When you read it out loud, you might notice it sounds a bit off or doesn't flow naturally."

- Check for Emotional Range

Example: "AI might sound very neutral or overly emotional without the right balance. Humor can often feel forced or fall flat."

- Use of MULTIPLE Detection Tools [atleast 5-7 before conclusion]

Example: "There are tools online that can help detect if something was written by AI. These can be handy if you're unsure."

AND THAT'S IT! You've successfully mastered how to distinguish between human and AI generated content.

Remember, practice is the key to success. You'll need to read enough comparisons before realizing how to do it quickly. In the meanwhile, please don't jump to conclusions too soon and respect the authors who put effort into their work.

I plan on posting some side-by-side comparison activities later in the chapters, hope you like it!

Sara.