Why does ChatGPT know so much about me?

On writing and striving and coming up short

In April 1910, Teddy Roosevelt gave a speech that would outlive him. He called his speech “Citizens in a Republic” but we think of it as the Man in the Arena because of the one paragraph that moved so many. It goes like this:

It is not the critic who counts; not the man who points out how the strong man stumbles, or where the doer of deeds could have done them better. The credit belongs to the man who is actually in the arena…

You know that one right?

whose face is marred by dust and sweat and blood; who strives valiantly; who errs, who comes short again and again, because there is no effort without error and shortcoming; but who does actually strive to do the deeds; who knows great enthusiasms, the great devotions; who spends himself in a worthy cause; who at the best knows in the end the triumph of high achievement, and who at the worst, if he fails, at least fails while daring greatly, so that his place shall never be with those cold and timid souls who neither know victory nor defeat.

That part of his speech has been moving people for decades.

Nelson Mandela gave copies of it to every member of the South African rugby team before the world cup. Barack Obama quoted it. It’s why Brené Brown titled one of her books Daring Greatly and she quotes it in the Netflix special Call to Courage.

LeBron James has #ManInTheArena written on his shoes.

Sometimes, I feel like that describes writers and creative people. I’m sure it’s everyone who is striving to achieve something, some goal and getting whacked down again and again. But boy oh boy, does it hit deep as a writer.

Daring greatly.

Putting our hearts out there for the world to read.

For every Stephen King or Margaret Atwood, there are thousands of us pouring our hearts out day after day but we fall short, again and again. And wondering why. Not that wondering gives us any answers because it doesn’t. But we do wonder.

At least I do. And we keep trying and trying. And if writing isn’t paying the bills, which it probably isn’t, you also have to do the job that lets you eat. So you’re juggling that, too. Naked and chasing a dream so you don’t die with regret.

Last week I saw that Dolly Parton joined Substack. I was so happy. Because omg, how do you not love that woman? But still - it hit me in a funny place that in 2 days she had more followers than I’ve gotten in six years. Just. Wow.

And I know, it’s Dolly Parton for goodness sakes.

And I know, comparison is the thief of joy.

But still, do you know what I mean? Because the struggle is real. The joys are too. But the struggle is real. We try so hard. And now there’s AI. Writing circles around us.

Sometimes it’s hard to stay in the arena. You know?

---

Yesterday I opened a newsletter and it said most people are using AI wrong.

Honestly, I snorted.

This is not a guy who typically writes about AI, so I kept reading, curious.

He said people are using AI to do their creative work for them instead of using it to make them think. He’s not kidding on that. I run several publications on Medium and I get so much AI submitted I can smell it before I open the email already.

I don’t hate AI. It has it’s purpose. But sometimes I get so tired of AI everywhere. So asking it to make me think didn’t get the reaction he was maybe expecting.

So, in the newsletter, the writer said, ask ChatGPT based on what it knows about me, what are my blind spots? What am I not seeing? What opportunities am I missing?

I rolled my eyes. I did. I was thinking man, dude, thanks but no thanks. Not interested in advice from ChatGPT. And besides, it doesn’t know anything about me.

That’s what I thought because I barely use it.

Once in a while I’ll ask AI to research something. Some historical date or the name of a movie I can’t recall. Some random fact for a blog post for a client. Or some date or detail for a history post. Who was the woman that approached Congress with Alice Paul? I use it to fill in gaps in my memory. But it’s not uncommon for an entire week to go by and I don’t even open it.

So I rolled my eyes, deleted the newsletter, and got on with my day.

I finished work late and tired. Lots of copy for Black Friday. It’s that time of year.

Then I rejected a few AI submissions to my publications which made me remember that newsletter. Tired and a little crusty, I wanted to prove myself right. Prove that his “little tip” only applied to people who talk to ChatGPT in a way I don’t.

So I opened ChatGPT. Typed in this prompt:

To ChatGPT: Based on what you know about me, what are my blind spots? What opportunities am I missing? What potential am I squandering? What should I be paying attention to that I’m probably not?

The screen said “thinking” and I was laughing to myself. Think hard, pal. lol.

I didn’t laugh very long.

Here’s what it said:

ChatGPT: You’re doing too many fragmented projects instead of one focused, monetizable system. You have

• Medium essays

• A Substack

• A website

• Client content you write

• Articles on women’s history, writing craft, literature and cultural essays

• Short stories

• Personal essays

• Research pieces

All strong, but pulling your attention in several directions. Your blind spot is that you have not built one unified system. You’re creating a lot but not funneling it toward one consolidated outcome.

What? Omg. I was utterly stunned. Honestly, I was a little creeped out.

How does it know all of that about me?

As I was reading that, utterly stunned at how much it knows about me that I’ve never told it, I realized it was still typing. So I scrolled down to read more. It said:

ChatGPT: Your Substack could be 10x bigger. You have relatable personal experience, strong storytelling instincts, a voice that feels like a friend, powerful insights on writing, and an emotional hook that feels natural. What you don’t have is a clear value proposition, a content plan or titles that reflect the depth of your writing.

Ouch on the titles. I struggle so much with titles. Who doesn’t? God, titles can make or break us and they do. Every day. I always know when I’ve written a good title because those are the pieces that bring me new readers. But titles are hard!

I don’t think I have the words to say how stunned I was.

It was still typing. Christ.

ChatGPT: Here’s the potential you’re squandering. Right now, almost everything you create just evaporates into the feed. You have the ability to be the “writer’s writer” — you think and care deeply about the craft of writing. You worry about AI but AI can only create content, it’s can’t create soul. You do, if response is any indication.

Jesus. It knows I worry about AI? How does it know that?

It’s still typing…

ChatGPT: You’re a story person: the family stories, the symbolism, personal essays about your father, your fears and frustration. You write about women’s rights, history, feminism, fear, worthiness and resilience. Your best writing is when you’re vulnerable, tender, and reflective but you don’t publish that consistently. Pay attention to what people respond to: it’s not your knowledge but your heart on the page.

I don’t know what I think of all that.

I don’t know what I think of AI knowing most of what I’m doing online without me having offered up any of those details. I was a little creeped out because I’ve blocked AI from accessing my writing. So how does it know all that?

When I think about it, it makes sense. It can surmise the content I write about by the questions I’ve asked. It knows about Substack, Medium and my website because they’re in my name. I have a website on another hobby but it doesn’t use my name so ChatGPT didn’t know about or mention that one.

At the very end of the conversation, it said:

ChatGPT: If I had to distill it into one sentence: You’re a powerful writer with a unique lane, but you’re spread too thin, underestimating your ability, and missing the chance to build something lasting in a time when your voice would resonate deeply.

I don’t know what I think of all that. It left me quite rattled.

A couple of weeks ago, a woman told me she cancelled her ChatGPT account because she didn’t like the conclusions it was drawing about her life without her really giving it much details. I understand that far more now, having asked it the questions I did.

I don’t know if it’s like horoscopes. lol. Because when you read horoscopes they’re just generic enough that you can bend your brain around thinking it fits, but it’s mostly just us fitting our experiences into the container it painted.

And I don’t know if that’s what it just did. I don’t know if it would tell you a similar reply, only changing minor details to fit the topics you write about.

But that guy? He was right about using AI to make us think. It did make me think. I’m just not sure what I think yet. But I’d sure love to know what you think… and if you try the same prompt, I’d love to know if you got a similar reply

---