Getting Into AI, With a Human in the Loop

Well, if Artificial Intelligence (AI) were a fictional soccer player —
it would 100% be Roy “fucking” Kent. Yeah — I've been rewatching some Ted Lasso.

It's here, it's there, it's every-fucking-where AI.
It's here, it's there, it's every-fucking-where AI.

It's here, it's there, it's every-fucking-where AI

Here's the short version of my sometimes messy AI writing journey so far. AI art is its own story — for another day.

Writing consistently has eluded me — four decades and counting. Last year was revision. Goals. Objectives. Priorities.

Now — next actions.

Writing on a routine basis — sharing shiny tidbits from my digital adventures, thoughts about what I’m building or breaking — the rabbit holes I fall into, what I find at the bottom, and what I learn climbing back up.

I’m plenty curious. Bring on the new tools. Momentum, though…ugh.

Which is why…

To speed things along. To have a sounding board. To have an editor with opinions. Ultimately — to have a “coworker” who can deal with my shitty starts, stalls, rewinds, and overthinking.

I brought in AI. Specifically, ChatGPT.

Let’s get into it.

I write for clients — website content, punchy blurbs, blog posts.

Last year, I started using AI on client work when it made sense and the client was on board. It felt inevitable. It was faster. Sometimes even better. Sometimes absolutely not. Still, it took time — teaching the tool the client’s voice, refining it, reining it in when it got a little too… AI.

Writing for clients is like building their websites. It’s focused. It’s contained. It has rails.

Writing for myself doesn’t.

On my own projects — too many ideas, too many directions, too many stories to tell. I’m not a fast writer. I can get lost trying to say it “right.” I’m writing anyway.

For the last 20+ years, notes — digital and analogue — and half-worked ideas have taken over. They’re everywhere — my laptop, desktop, shelves, notebooks, notes apps. It’s too much. I’m pretty sure I’ve forgotten more than I can recall at this point.

So I decided to use ChatGPT as a digital coworker and editor — to get the words down and shaped into stories. The idea was simple. I’d teach it my voice — the tone, the humor, the level of polish I’m aiming for — and let it keep the wheels turning.

I bring the raw material — ideas, rabbit holes, rough drafts. AI helps me turn it into something readable — coworker, editor, and a nudge when I stall.

For the trial run, I wrote “On Writing Here — Clear, Brief, Human” using AI — a quick scene-setter for what I’m doing here and what you can expect. It started off great.

AI trained (dialed into voice and tone) — check.
Base content provided — check.
A decent prompt, open enough to breathe — check.
Revisions. Revisions. More revisions — check.

The middle was the sweet spot. Faster turnaround. A clean, tight piece. It sounded like me. It sounded like the voice I had in mind.

Then came the “fuck all” moment.

A paid AI detector confidently called it 65% AI-written. Nope. Worse, parts I’d written 100% myself — my words, my structure — got flagged as 100% AI. Meanwhile, a few lines I knew were heavily AI-assisted slid by with barely a blip.

Here comes the rabbit hole.

I tried other free detectors. Same story, different numbers. One said 0%. Another said 100%. Plenty landed somewhere in the chaotic middle. Most could be tricked. Not totally unexpected — but still annoying.

The thing is, AI and I aren’t strangers. I’ve been watching these tools for a while (years) — testing, using them in real situations, arguing with them, learning the strengths and weaknesses. The opinions around AI are hard to avoid, too — ethics, use, the future — everywhere you look — news feeds, search, the general hum of the internet.

Still, the variation in results was wild. The commonality?

After hours of surfing, reading, and testing detectors, I landed on one conclusion — no. These detectors are inaccurate and unreliable. A.K.A. total bullshit. At least right now. At least the ones I tried.

Knowing these detectors were messy — and that a lot of the “AI” flagging seemed tied to patterns, punchy statements, and paced cadence — I did what any sane person would do and complained to ChatGPT.

Me: I’m sort of pissed that the parts I wrote are scanning through AI detectors as AI generated when they weren't. I completely rewrote parts but using any sort of strong cadence scans as AI written and of course the em dash.

ChatGPT: Yeah, that’s maddening — and you’re not imagining it. A lot of “AI detectors” (including the vibes Grammarly surfaces) over-index on predictability: parallel structure, punchy aphorisms, repeated sentence frames, and clean rhythm. Those are also… just normal tools of good writing. So when you write well (especially in a manifesto-ish piece), it can get flagged.

A few things that tend to trigger those scanners:

• Parallel cadence (“Clarity is… Brevity is… Explanation is…”)
• Short, stacked sentences (“It shifts. It grows. It’s a living thing.”)
• Very even sentence lengths for several lines in a row
• High polish / low “messiness” (few asides, few idiosyncratic turns)
• Em dashes (not inherently AI, but common in polished editorial tone right now)
  If you want the piece to feel more unmistakably “human” without dulling it, you don’t need to abandon cadence — you just need a little more idiosyncrasy and variation.

So there it was — decent writing. Patterns to reinforce. Cadence for readability. Polish for smoothness. And my beloved em dashes for visual distinction. All of it, apparently, could trigger AI detectors.

I ended up diving deeper into all the “things” AI detectors might flag. It’s wild how many solid writing practices can register as “AI-written.”

For brevity, I’m not unpacking all of it here. If you’re curious, go ask ChatGPT, DuckDuckGo and Google.

Like I mentioned, use of AI seems inevitable. Especially when you work in the digital space and need to keep content creation moving forward.

So here’s my stance on AI — and how I plan to use it for writing.

Stance
AI’s useful because I’m human. I stall. I overthink. I rewrite the same paragraph six times. It helps me get unstuck, clean things up, catch grammar issues, and keep my voice while I do it. Co-writing is fine. Letting AI invent facts isn’t.

I find AI a bit heavy-handed — exhausting and exasperating in its editing. To be fair, the more it learns the voice, the better it gets… and the less exhausting the whole process feels.

Research is where I get wary. Using AI as the only tool — letting it play “subject matter expert” — is a hard no. Source info can be wrong, and relying on it can create a circular, inaccurate loop of information. Bad info in, bad info out. Just a slick way to polish a turd.

Use

• Generate faster drafts — yes
• Revisions and rewriting — sometimes
• Improve consistency — yes
• Research — 50/50 (and only with additional verification)
• Idea collaboration — yes
• Grammar checker — yes
• Editor — yes
• “Write an article on a topic and I’ll just post it” — nope

AI is here to stay — at least for the foreseeable future. Using it to stay effective, efficient, and competitive makes sense. But keeping the human voice and thought process is the point. That’s where the authenticity lives.

A human has to be involved. To spark ideas. To knit a story. To create connection.