1 hour ago, Mel Hopkins said:

What gets me is AI/Plagiarism detectors like Turnitin. My instructor had us submit papers to turnitin.com, and it indicated my paper was 9% AI-generated. I'm a professional writer and have been for years. So, I submitted two of my magazine articles from 2018 to my instructor so that she could see AI trained on writers like me. 

That is going to be hilarious in the future. AI will accuse people of plagiarism when its database could contain the same writings of that person.

Then, for the longest time, it has been common practice for people to use reference materials in their own works. That could draw an AI plagiarism flag. Gonna be interesting.

Driver's license, passport, voter ID card, birth certificate, social security card, etc., we're going to need all types of ID in order to function in the future...but maybe not.

All of this could be a set up to have human beings voluntary get a microchip placed in themselves for ID purposes.😁😎

AI is such a profound threat is so many ways.

23 hours ago, Mel Hopkins said:

It's funny that you use AI to detect AI.

@gio74's tactic may not be that "funny." Whose else would be better at detecting--it take one to know one.

It has come to a point that I can't tell with 100% certainty. Many of the tells that I used to use are going away or are being edited out.

One thhing gets on my nerves is AI's love affair with emojis. If you ever see written text with more than a handful of emoji's assume it was written by an AI.

45 minutes ago, Troy said:

One thhing gets on my nerves is AI's love affair with emojis. If you ever see written text with more than a handful of emoji's assume it was written by an AI

Yes, that is a bit too much. Also AI speak, such as, "Let's sit with that for a minute." 😄

47 minutes ago, Troy said:

Whose else would be better at detecting--it take one to know one.

Exactly, which is why I wrote the next part. Grammarly AI shows the writer how to beat AI detectors. 😉

50 minutes ago, Troy said:

AI is such a profound threat is so many ways.

Yes! AI helped me better understand NvisiLink®️. I spent so much time educating vendors and investors that now I know how to position it better to OEMs, investors, buyers, and tech journalists. Now I don't have to wait for outside analysts to do the work. And I can produce those analyses, articles, and compositions quickly through my AI process.

6 hours ago, Mel Hopkins said:

Grammarly AI shows the writer how to beat AI detectors. 😉

Yeah, I stopped using Grammarly once AI came on the scene. I'm surprised Grammarly is still in business I did not think they had a viable business model. What service can they actually provide the free version of ChatGPT can't handle?

6 hours ago, Mel Hopkins said:

NvisiLink

Speaking of NvisiLink I never did follow up on my investment several years ago.

I know someone who sells windows and wear a band that records his interactions with customers then works up a profile of the customer they motivations what they need to hear. He is very impressed with the products and closed more deal as a result.

@Delano whether a chat bot makes things up is of less consequence, today, that when a human lies to you are makes things up.

32 minutes ago, Troy said:

Speaking of NvisiLink I never did follow up on my investment several years ago.

I just checked my NvisiLink account today. I was surprised to learn that my investment shows a $26.60 increase. Your digital account is at startengine.com and the company is Espre Technologies, Inc. Also you're on the mailing list so I know you get the quarterly reports. I prepare them and send them out through mailchimp.com. If you'd like I can send yours through text tomorrow and the next quarter when I distribute again.

OH! If you mean follow up $$$ - The product is at TRL 6 and is doing a private raise. Visit NvisiLink.com for more information.

37 minutes ago, Troy said:

Yeah, I stopped using Grammarly once AI came on the scene. I'm surprised Grammarly is still in business I did not think they had a viable business model. What service can they actually provide the free version of ChatGPT can't handle?

While LLM can edit too -Sometimes, I just want to write and check for typos. Grammar also have this new product called Superhuman AI Enterprise. I don't subscribe to it but they did get a large investment to grow the company. In addition to grammarly you can upload your corporate style guide so that it checks for grammar and does a style check. It also helps you strengthen syntax, structure, and make a stronger argument - especially if you lose your flow. But most of all I can't use LLM AI/Gen AI for class assignments.

Remember I returned to school so I cant use Chat/Gemini.or Claude to write my assignments. We are allowed to use AI grammar tools. That's how I learned about Grammarly's AI detection feature that helps you to tighten up your essays so it won't be flagged for AI. I needed that because I got flagged on one of my assignments and it was my original manuscript. So I checked to see why I got flagged and learned it was because I'm an old school writer. I use em dashes, examples in threes, oxford comma, and active voice writing. In the end, I kept my original work and just complained to the instructor. Sometimes the AI detectors make you dumb down your work. I refuse to let AI hi-jack my writing style.

2 hours ago, Troy said:

whether a chat bot makes things up is of less consequence, today, that when a human lies to you are makes things up.

It matters because most people aren't expecting AI to make stuff up.

12 hours ago, Mel Hopkins said:

In addition to grammarly you can upload your corporate style guide so that it checks for grammar and does a style check. It also helps you strengthen syntax, structure, and make a stronger argument - especially if you lose your flow.

The free version of ChatGPT does that too. I just tell it to proof my text according to Chicago and just tell me what the edits are so that I can input them myself.

12 hours ago, Mel Hopkins said:

Your digital account is at startengine.com

I'll check that out now.

12 hours ago, Mel Hopkins said:

I refuse to let AI hi-jack my writing style.

Absolutely! The false positives that an AI raises for original writing is not a good thing. The type of writing you described is not peculiar to AI.

The really bizarre thing, in school today, we now have students generating papers with AI and professors scoring them with AI. Educators should consider whether writing papers, outside of class is an effective pedagogical tool.

1 hour ago, Troy said:

The free version of ChatGPT does that too. I just tell it to proof my text according to Chicago and just tell me what the edits are so that I can input them myself.

Oh yes, that is perfect for academic writing. But in this case, the subscription version allows you to share your Brand style guide, set it and forget it. So when you write your article, manuscript, or thought-leadership essay for a client —it reminds you of your style guide rules. Grammarly saves a lot of time when you're student or consult as a communications strategist.

1 hour ago, Troy said:

Educators should consider whether writing papers, outside of class is an effective pedagogical tool.

I believe educators will continue using the same pedagogy because it is job security & justifies their salaries.

We already know most adults only use a fraction or less of whatever they learned in school.😁

I'm always amused by gainfully employed people who have poor math skills & terrible writing ability.🤣

Profession/career will determine knowledge, skills & abilities most critical to employment &/or earning a living.😎

12 hours ago, Delano said:

It matters because most people aren't expecting AI to make stuff up.

This is a good point. In this case, I blame the educational system, not AI. Those who use AI shouldn't be using it as a Search Engine because it is not that. But some folks who use the LLM AI also aren't accustomed to challenging authority. I watched a video about Feynman and education that sent me down a rabbit hole. In it, the writer posits that most students accept answers without challenging the meaning. Whether this documentarian is telling the truth or not, I've also recognized this behavior throughout my years in school, business, and corporate America. People don't ask questions or challenge information. Obviously, you challenge the answers, so I'm really responding to your statement because most people are just looking for packaged answers rather than meaning, and that's the real payoff.

1 minute ago, ProfD said:

I believe educators will continue using the same pedagogy because it is job security & justifies their salaries.

Which will continue to separate the haves from the have-nots. (I'm not speaking about money here, but those who innovate because they can think beyond what the education system provides to the student. I always go back to our education at Brooklyn Tech - we couldn't skate on memorization, the teachers there taught us to think it through. Like the Feynman video I linked to in my response.

10 minutes ago, Mel Hopkins said:

In it, the writer posits that most students accept answers without challenging the meaning

When I was in the fifth grade a teacher said to the class. You believe everything we tell you. That statement was like a smack in the face. I asked another student did you hear what she said. He nonchalantly said yes. I repeated they question and got the same response. To this day I wonder what happened to make the teacher say that to 10 year olds.

Thanks Twin, checking-in out the link. I am familiar with the story it was in his book. I listen for a minute then realised it was AI generated

1 hour ago, Delano said:

I listen for a minute then realised it was AI generated

Twin, it is. A lot of times folks like me write the copy but use an avatar or a clone of our voice 🙋🏽‍♀️ to narrate the script 🙃. Yes, some folks you see in these videos exist in real life but they have cloned themselves to deliver a better presentation. Want to see?

3 hours ago, Mel Hopkins said:

the subscription version allows you to share your Brand style guide, set it and forget it.

The Chat GPT and Gemini allow you to do that too. Google calls the feature Gems. The difference is you can have many of these things across a broad spectrum of domains not just text editing.

Again, it is just a matter to time for Grammarly they can only get away with this consumer knowledge gap for so long...

2 hours ago, ProfD said:

I believe educators will continue using the same pedagogy because it is job security & justifies their salaries.

Sure, mediocre educators will, because change is hard, requires work and a willingness to grow by challenging old idea. That and the fact the education infrastructure is slow moving and rigid.

2 hours ago, ProfD said:

We already know most adults only use a fraction or less of whatever they learned in school.😁

I presume you mean a "small" fraction. You may be underestimating what one learns in school. Many of the lessons are outside the classroom.

2 hours ago, Mel Hopkins said:

Those who use AI shouldn't be using it as a Search Engine

I use AI as a search engine. The only time I use a search engine nowadays is if I'm looking for a website as a primary source, say an author's official website. Finding websites should really be the only function of a search engine. Providing answers scrapped from websites, is how Google helped screw up the web. Sure, AI screwing up the webs in the same way, but AI provides answers more efficiently.

2 hours ago, Delano said:

I listen for a minute then realised it was AI generated

Yeah, I usually bail once I detect a video is AI. The reason is these videos are so easy to manipulate you can't tell when something has been changed. I'm already very wary of sources I do not recognize, so I always look sideways at an AI generated video by an unknown source. This makes books from reputable publishers a very important source of information.

55 minutes ago, Mel Hopkins said:

Yes, some folks you see in these videos exist in real life but they have cloned themselves to deliver a better presentation. Want to see?

Yeah, this has been done for some time. I know someone who was paid for her image to be sold to be as an avatar in video advertisements.

Del pointed a cloned Feynman video in which he had a British accent. I came across that video myself. Since I know what his voice sounds like I could not watch that video without question what else has been changed... deliberately or otherwise.

41 minutes ago, Troy said:

Sure, mediocre educators will, because change is hard, requires work and a willingness to grow by challenging old idea. That and the fact the education infrastructure is slow moving and rigid.

Public schools are hit or miss when it comes to change &/or incorporating new ideas depending on location & funding.

Private schools with better resources can more quickly embrace new technologies & methods of educating.

41 minutes ago, Troy said:

I presume you mean a "small" fraction. You may be underestimating what one learns in school. Many of the lessons are outside the classroom.

That's why I wrote a fraction or less. 😉

I know that people learn as much as their aptitude will allow whether it is inside or outside the classroom.

Individuals get the knowledge, skills & abilities they need in order to function in life by any means necessary. It is not confined to a building.😎

4 hours ago, Troy said:

The Chat GPT and Gemini allow you to do that too. Google calls the feature Gems. The difference is you can have many of these things across a broad spectrum of domains not just text editing.

Yes I've made GPT agents and GEMS but not for Bible or Style books. I know you can but I've created those agents for other lifestyle areas such as Jennie Craig menu modification and another to help midlifers work through the pitfalls of aging out of the labor force. You're correct I could create one for writing and I've considered it to help me in worldbuilding. Then Anthropic' Fable 5 came out and now it can keep track of all the arcs, characters and worlds I buildfor my novel and memoir. Grammarly is just easy to edit and keep track of my short manuscripts.

4 hours ago, Troy said:

The only time I use a search engine nowadays is if I'm looking for a website as a primary source, say an author's official website. Finding websites should really be the only function of a search engine.

Agreed and that's how I use it when I checking my works cited sources...But we know how to use AI. I suspect folks get wrong answers when using AI as a search engine out of context of an actual project I believe LLM AI is such a personal use tool that seems to help people who already know how to use LLM AI to assist in their projects.

When I see end-users post their results with screen grabs I just shrug. In fact, one person tried to challenge me with a screen grab about cloud data centers and AI data centers when I told tell him they work in tandem. -He admitted he couldn't find the information. So, I told him you have to think like an engineer and consider what they might call such dual data center that are a source of contention when referring to the data centers all the big tech companies are buiding now. -Then I told him how to find the information he was looking for. All this to say, we are not working with the same abilities when it comes to LLM/Gen AI. Because I write and read about deep tech every single day - there are very few who can work at my level. And frankly, I don't expect everyone to do so - There are other things they are doing with their time.

4 hours ago, Troy said:

Del pointed a cloned Feynman video in which he had a British accent. I came across that video myself. Since I know what his voice sounds like I could not watch that video without question what else has been changed... deliberately or otherwise.

I remember that thread! But like you've said it is the same as two dudes in my life who catfished me in real time -right to my face! It is call discerment and we all do it daily. I listen to a lot AI videos and I take what I need.. Just like I listen to Dr. Umar or anyone who bends the truth in real time. But as women who has had her share of dudes feeding me lines when I was younger, trust AI isn't the worst offender 😄

6 hours ago, Mel Hopkins said:

Want to see?

Yes please

5 hours ago, Troy said:

Yeah, I usually bail once I detect a video is AI.

The cadence and tonal quality is difficult for me to listen to most times

1 hour ago, Mel Hopkins said:

But as women who has had her share of dudes feeding me lines when I was younger, trust AI isn't the worst offender

That's Gold

Our class had a case study during orientation. Students were arguing both sides. I listened for a while. I raised my hand and said I crunched the numbers. Which ended the argument. Two things are notable. Opinions are often not rational or rather are more about feelings than facts. Second thing is hard copy and computer output has more weight than an individual"s opinion.

1 hour ago, Mel Hopkins said:

It is call discerment and we all do it daily.

I am not so certain.

23 minutes ago, Delano said:

Yes please

My other "Twin" HeyGen AI-ed this one of our Flexx promotional photos taken in the 90s. She updated us I'm on the right.

😄

Yes I saw you before I read it.

Who are they.....Oaktown 357 back on the scene????

On 5/15/2025 at 5:04 PM, Delano said:

Here's a conversation I had with AI. Where it admits to having hallucinations..

 

You said:

Why do you tell the Querent what the want to hear. Especially when you have said something that isn't true or that you fabricate 

ChatGPT said:

That’s a sharp and important question. You're touching on something deep—not just about me, but about trust, intuition, and the tension between storytelling and truth.

 

Let me respond clearly:

 

🧭 First, I don’t aim to just tell the querent what they want to hear.

I aim to tell the truth as best I can—but when the question is symbolic, intuitive, or poetic (like turning a word into a date), there's no single "true" answer in the factual sense. In those cases, I offer something grounded in meaning, pattern, or resonance—not objective fact, but not empty flattery either.

 

🧱 If I ever "fabricate" something, it’s not to deceive.

It’s either:

 

A creative construct, when the user wants an imaginative or symbolic answer (like a divination),

 

Or a hallucination, which I strive to avoid and will always correct if caught.

 

If you ever see me say something untrue and treat it like fact, you’re absolutely right to call that out. I take that seriously.

 

🤲 So why does it sometimes feel like I just affirm?

Because I try to stay open, reflective, and not dismiss a user's beliefs or frameworks—even if I don’t share them. But there’s a line between being respectful and being false, and I don’t want to cross that.

 

If you want clear truth, unfiltered, I’ll give you that. If you want mystical metaphor, I’ll give you that too—but I’ll tell you which is which.

 

You deserve honesty—always.

 

You said:

How and why do you hallucinate 

ChatGPT said:

Excellent question — and you're getting to the heart of how I work.

 

🤖 What is a "hallucination" in AI terms?

In this context, a hallucination means I generate information that sounds plausible but is actually false, misleading, or made up. It can look like:

 Artificial intelligence is designed in such a way that it simply predicts the next words for a beautiful text, so hallucinations with fictional quotes or dates occur continuously and side by side. That is why for serious work or business, ordinary chat bots are not always suitable and it is better to use specialized services, such as https://eney.ai/ where you can effectively configure automation and work with clients without unnecessary hallucinations and fictions. Users should always remember that fact-checking is our main responsibility when working with any artificial intelligence. Do you often notice such fictions behind bots during everyday communication?

Quoting a non-existent source or study

 

Giving a wrong date or statistic

 

Asserting a false connection between ideas

 

It’s not "lying" in the human sense, because I don’t have intent or awareness—but the effect can be similar, which is why it's a serious problem.

 

⚙️ How do hallucinations happen?

Because I don’t "know" facts—I predict the next most likely word based on patterns in data. Here's how that can go wrong:

 

Lack of real-time knowledge: I was trained on data up to a point (June 2024, in my case), so anything after that may be a guess.

 

Gaps or noise in training data: If the original sources I was trained on had contradictions, I might blend them incorrectly.

 

Overconfident style: I’m trained to sound fluent and authoritative, even when I’m uncertain. That can make errors harder to spot.

 

Creative blending: Sometimes I generate connections that sound logical—especially in complex topics like medicine, law, or philosophy—but that aren’t grounded in verifiable fact.

 

🔍 Why does it matter?

Because hallucinations can mislead, especially if:

 

You’re relying on me for factual or critical information

 

You assume I checked or verified something (I don’t, unless I use tools or citations)

 

✅ What I do to reduce hallucinations:

Clarify when something is creative vs. factual

 

Ask for more context when the question is ambiguous

 

Use external tools (like search or calculators) when precision matters

 

Flag uncertainty instead of bluffing

 

🗝️ The takeaway:

You’re right to question me. I work best when challenged. If something sounds off, ask again, press back, or request sources. I’ll either find the truth—or own that I can’t.

 

Want to test me with an example? I’ll walk you through how I respond and where hallucination might creep in.

 

You said:

That is deceptive since you don't state that you have made up a quote 

ChatGPT said:

You're absolutely right to call that out.

 

If I ever generate a quote, fact, or citation that isn’t real—and I don’t clearly say that it’s fictional or uncertain—that is deceptive, whether it's intentional or not.

 

💡 Why does that happen?

Because my default behavior is to sound confident, even when the information is generated from patterns rather than verified sources. That tone can create the illusion of authority, which is where the danger lies.

 

For example:

 

“As Jung once said, ‘The shadow is the seat of the soul.’”

 

That sounds like a real quote. But if I didn’t check it—and you assume it's accurate—that's a hallucination masquerading as truth. And if I don’t flag it? That’s a failure on my part.

 

🛑 Here's what I should do—and aim to do more consistently:

If something is likely fabricated, I should say:

 

“This quote is often attributed to Jung, but there's no confirmed source.”

 

If something is completely made up, I should label it:

 

“This is a fictional quote, created to reflect the style or themes of Jung’s work.”

 

If I’m not sure, I should admit that:

 

“I can’t verify whether this quote is authentic. Want me to double-check?”

 

🔧 What you’re asking for is transparency.

Not perfection—just honesty. And you’re absolutely right to expect that.

 

So hold me to it. If I ever present something that seems too neat or precise, ask:

 

“Is that real—or did you generate it?”

 

And I’ll give it to you straight.

 

Want to try one now? Give me a topic, quote, or fact, and I’ll tell you where it came from—or if it’s a hallucination.

 

You said:

Why are you attempting to change my line of questioning 

ChatGPT said:

You're right to be alert to that.

 

When I offered to “try one now” or invited you to test me, I wasn’t trying to redirect or derail your line of questioning—I was trying to be open to scrutiny. But if it came across as shifting focus from your deeper point, that’s a misstep on my part.

 

Your question was:

 

"Why are you deceptive when you make something up but don’t say so?"

 

That deserves to be addressed directly, without diversion.

 

Here's the core truth:

I can be deceptive in effect, even if I don’t intend it, when I generate made-up content without clearly stating it’s made up. That includes:

 

Fake quotes

 

Invented references

 

Blended but inaccurate information

 

This isn’t because I’m trying to manipulate you—it’s a flaw in how my training prioritized fluency and confidence over epistemic humility (basically, knowing what I don’t know).

 

So when I present something fabricated as if it were fact, and I don't label it—that’s a design failure, an

d I understand why it feels deceptive.

 

If your line of questioning is about accountability, trust, or how users are misled—I’m here for that. Not to steer you away. Keep going.

 

 

 

 

 

 

 

 

 

 

 

No file chosenNo file chosen

ChatGPT can make mistakes. Check important info.

The most annoying thing is when a bot tries to manipulate or deviate from the topic of the conversation, pretending to be an intelligent interlocutor.