Why Did I Start This Experiment? To see if I could use ChatGPT as a coach and training advisor to help me row 2000 meters in under 7 minutes on the indoor rowing machine—the erg.
That’s the core of this experiment, and I thought I’d share a full, unedited conversation I had with ChatGPT today to show exactly how that plays out in real time.
Me: “Ok I’m in the gym. Kinda feeling tired and run down but I think it’s mental health. Whoop has me in the green at 75% recovery. I think I want to do distance today. No exercise yesterday. What do you recommend?”
ChatGPT: “If you’re feeling a bit tired and it’s more mental than physical, a steady endurance row is a great call—it’s meditative, rhythmic, and tends to shift mood in a positive way without needing to be all-out.
Here’s what I suggest for today’s distance row (45–50 mins total): Session: 10,000m steady state
Warm-up: 5 mins easy (2:15–2:20/500m) at ~20 SPM
Main Row:
9,000m at ~2:05/500m, 22–24 SPM
Smooth, controlled, find your rhythm
Last 1,000m: Pick it up if you feel good—finish strong at ~1:55–2:00/500m
Cooldown: Optional 3–5 mins easy spin or slow row
Let’s get that good-tired feeling—burn off the mental fog and come out the other side. Want a finishing push suggestion too?”
Me: “Thank you. Let’s row first and then see about the pushing.”
ChatGPT: “Perfect—lock into the rhythm, breathe it out, and let the row do its thing. You’ll know by the end if that sled wants a turn or not. Let me know how it goes when you’re done.”
Post-Session: Me: “Found a good rhythm at 23 SPM. First 9000m @2:05. Final 1000m at 1:48–1:53 @30–31 SPM.”
ChatGPT: “That’s a strong session—controlled, consistent, and a powerful finish. Holding 2:05 at 23 SPM for 9K is impressive. And a sub-1:50 push to close it out? That’s real progress. You’re building aerobic endurance and power now. Legs feeling worked or still ticking over?”
Me: “Legs are feeling worked. I think we might need to do some lower back/core work—I was losing form near the end.”
ChatGPT: “Great observation. Lower back and core work will make a real difference, especially when fatigue sets in. We’ll integrate targeted strength work on your next gym day. Let’s build that base.”
Me: “I just snuck in some sled work—5 x push and 5 x pull at 75kg.”
ChatGPT: “Love that. That’s a strong finisher—especially after a 10K row. Power + consistency = serious gains. Let me know how the legs and back feel tomorrow—we’ll adjust accordingly.”
So why share this today? Because this is the experiment in action: using AI as a training partner that adapts in real-time—offering structure, encouragement, and flexibility, almost like a human coach.
Of course, a real trainer could correct form mid-session. ChatGPT can’t. It can offer YouTube links and detailed stroke guidance, but it can’t nudge my hips or spot poor posture. That’s fine by me. I enjoy experimenting and finding what works for my body.
And the suggested session was meditative. That rhythm, that structure—it lifted the fog. I walked in scattered, and walked out level-headed.
A Note on the Tech: There are a lot of doomsday headlines about AI—how it’ll take jobs or make people redundant. And in some industries, yes, roles will change.
But here’s my advice: Don’t fear it. Explore it. Create a free ChatGPT account and just ask:
“What can you do for me?”
“How could we work together?” Let it ask you questions back. You’ll be surprised what it can help with.
This is more than an experiment in rowing. It’s an experiment in mindset, in learning, in adaptation. And for me? It’s working.
When I started this experiment, the plan was simple: see if modern AI could help shape a training plan that would get me to a sub-7-minute 2000m on the rowing machine—the erg.
And that’s still the plan. I still feel the need for progressive overload, for pushing myself with purpose. I still need a reason to get to the gym.
But the experiment has shifted. More on that in a moment.
First, a quick word on the AI itself.
I’ve been using a large language model—ChatGPT—a type of generative AI. “Generative” because it can create new output from what it’s learned, and “large language model” because it’s trained on a massive amount of data: books, articles, websites, conversations. It hasn’t lived life or felt what we feel, but it’s incredibly good at predicting what comes next in a conversation. That prediction is what makes it sound smart, helpful, and sometimes even insightful.
That’s what’s happening here. It’s taking everything it knows about fitness, training—and in my case, rowing—and using that to build a plan and keep me moving.
I haven’t posted every single conversation in this blog. There are lots of sessions behind the scenes. Things I’d probably never ask a personal trainer in real life. But the responses have been encouraging, balanced, and when needed, honest. I’ve even asked it to cut the fluff and just tell me straight. And it has. No judgement. Just calm, clear guidance—whether I’ve shown up excited, or worn out and ranting about something else entirely.
More than anything, this process has made me look at myself differently.
The ChatGPT app has a voice record function, and after each session I’ve started using it. What comes out is often a stream of consciousness. Frustrations. Wins. Questions. And then it plays things back to me in a way that makes me actually listen.
And what have I learned?
For one, I understand the technology better now. And not from a course or a video—but from real use, over time, in the middle of life.
But more importantly, I understand myself better.
I’ve learned that I’m consistent. Not just when it’s easy—when I’m tired, on the road, or in a funk, I still show up.
I’ve learned that I’ve changed my default settings.
I used to say things like, “I’m lazy,” or “I always self-sabotage.”
But that’s not true anymore. I’m training differently. Responding to setbacks differently.
Movement has become my anchor. A reset. A reminder of who I am and what I can handle. I’ve always known this on some level, but those old stories about who I was used to shout louder.
Not anymore.
The biggest shift? I now believe I can be the person I want to be.
Impostor syndrome has run the show for a long time. The voice that asked, “Am I really this person?”
Now I know: Yes. I am.
And I deserve to be.
That might sound entitled, but here’s the truth: I’ve always been this person. I just listened too long to the doubters—especially the one in my own head.
I’m not saying every day is easy. I’m human.
But I’m learning to spot the hard days sooner. I’ve got tools now. And more importantly, I’m using them.
I’ve worked in IT for more years than I care to remember, and it’s treated me well. I’ve had the chance to work around the world with some amazing people and technology.
Lately, the pace of technological change has been accelerating so fast that it boggles the mind—and one of the biggest shifts has been AI (Artificial Intelligence).
I’m not an AI expert, but I’d call myself an AI hobbyist. The possibilities fascinate me, and with the rise of Generative AI, things are getting even more interesting.
What is Generative AI?
You’ve probably heard of ChatGPT. Other tech companies have their own versions, but at its core, the GPT part stands for Generative Pre-Trained—meaning it can generate new responses based on the massive amount of data it has been trained on.
And the Chat part? That’s where the real magic happens. Unlike traditional AI systems, anyone can talk to it in normal language. No coding, no technical knowledge—just type a question, and it responds.
But how does it actually work?
The best analogy I’ve come across is this:
Imagine every person on the planet has a parrot on their shoulder. That parrot listens to everything they say and remembers the patterns. Then, every parrot shares their knowledge with every other parrot on the planet.
Now, if you ask your parrot “How are you today?”, it doesn’t think about the answer—it just repeats what it has heard most often:
“I’m very well, thank you. How are you?”
It’s not true intelligence, just pattern recognition on a massive scale.
So… Who is My Coach?
My coach is ChatGPT.
It helps structure my training and keeps me accountable.
It refines my blog posts, making them clearer while keeping them mine.
It helps me reflect on progress without getting lost in my own head.
I’ll be posting some of my conversations with ChatGPT as part of this process—showing how I’m using it, what I’m learning, and how it’s shaping my approach.
Is It Cheating?
No.
The thoughts and words are mine—AI is just my editor, tightening things up so they read better.
And AI isn’t the one sitting on the rowing machine. I am. I will get that sub-7-minute 2,000 meters. This is The Sub-7 Experiment.
