The Sub-7 Experiment

Tag: rowing

  • A New Coach in the Room

    It feels like I have a new coach.
    You might remember that I’ve been asking ChatGPT to prepare workouts and coaching advice to help me row 2,000 metres in under seven minutes. That is the whole point of The Sub-7 Experiment. Can I use AI to help me achieve a fitness goal.

    When I first tried this, the model available to me was GPT 4.0 and it was good. I set up the role, gave it the context, kept the conversation alive, and each day I told it how I was feeling. It responded with the workout for that day. That simple rhythm worked well.

    Then 4.1 came along. The improvements were small but noticeable. It held context better, got confused less often, and could handle my slightly lazy and vague questions more easily. As with most tech, each release pushed things forward.

    Earlier this year GPT 5.0 arrived with a huge amount of hype. It was supposed to push ChatGPT into a whole new league. PhD-level reasoning. Better accuracy. A genuine step up.

    The reality was mixed.
    Yes, it produced better code for a different project I was working on. Yes, it had more “thinking” capacity and could reason more deeply without me having to explicitly tell it to think. That part was a massive improvement.

    But as a conversationalist it was a step backwards.
    It forgot things. It lost context. It got confused about tasks. The backlash was so strong that OpenAI reinstated version 4.1 as a choice because so many people preferred to keep using it. It felt like my coach had left the building.

    I worked around it with careful prompting, but it was frustrating. The Sub-7 Experiment relies on continuity and rhythm, and something was always slipping.

    Which is why it now feels like I have a new coach. GPT 5.1 has arrived and it feels different in a very good way. The tone is consistent. The help it offers is actually useful. It anticipates the next step instead of fumbling it. It feels like an upgrade in the true sense of the word.

    Let me explain why this matters.

    I have a WHOOP device and I’ve used it for almost two years. Before ChatGPT became part of my training, WHOOP was my only guide. It sits on my wrist and picks up all sorts of measurements: heart rate, skin temperature, strain, sleep quality and plenty more.
    Every morning the app shows three dials. Yesterday’s strain, today’s recovery level, and last night’s sleep. When you start a workout you tell WHOOP what you’re doing and it gives you a target strain. When you hit it, the band vibrates and tells you to stop. Simple. Clever. And it worked well.

    But in the last few months I’ve been questioning the value.
    The subscription model has changed. The promise of free device upgrades for active subscribers has been replaced by an “uplift fee”. My renewal is in February and it will cost a lot more to keep going into my third year. And that makes me ask what I actually need it for.

    Most of the data WHOOP collects I don’t really use. I know how well I slept because I was there. What I actually value is recovery guidance and strain targets. And there are other devices out there that do similar things for a simple one-off cost. Polar Loop is one I’m looking at seriously.

    So I turned to ChatGPT 5.1 for help. Reviews. Recommendations. Thoughts based on my training. And one of the threads pointed out something obvious: I have not been using most of WHOOP’s data anyway. Not deeply. And the only thing that truly matters is the workout planning, which comes from CoachGPT.

    I asked if there was any way for ChatGPT to access WHOOP data directly. It said no, the APIs are not available yet. But then it made the suggestion that genuinely impressed me.

    It told me exactly which two screens in the WHOOP app to screenshot each morning. It told me to upload them, and it would analyse everything it needed: recovery, sleep, strain, HRV, and readiness. It would then produce a fully tailored workout for that day. And if it thinks I need a rest day, it will tell me that too.

    I have used this new process for the last few days and it is genuinely brilliant.
    Two screenshots. Upload. Instant plan. Clear reasoning. Exactly what it expects from me. Exactly what to avoid. Exactly how hard to push.

    And it works.
    The coaching is better.
    The structure is better.
    The whole system feels like something new.

    Well done, ChatGPT 5.1.
    This is The Sub-7 Experiment.
    Recovering using structured data.

  • Moving Again

    Second time back in the gym since the surgery, and it felt good just to move. I sat on the rowing machine for 30 minutes, kept the resistance low, and rowed an easy 6,000 metres. No pressure, no chasing numbers, just movement.

    Normally I’d be pulling harder, aiming for pace and power, but not today. Today was about giving myself permission to ease back in. About listening to my body instead of trying to prove something.

    I did a 5k walk yesterday, so this was the next step, gentle, deliberate, and calm. I’ll see how the leg reacts later, but right now my head’s in a good place.

    It’s funny how something as simple as half an hour on the rower can feel like a small victory. But that’s what this part of the journey is, not big leaps, just steady steps.

    This is The Sub-7 Experiment. Currently in the slow lane.

  • Old Limits, New Baselines

    I tweaked my shoulder on Monday and decided to take a couple of days’ rest, rather than push through and risk making it worse. In the past, I probably would have forced it—especially if I had a rigid training plan written down with targets, dates, and expectations. If the plan’s written down, you have to follow it, right?

    Well… no. And that’s the beauty of this experiment—I can pivot.

    The conversation with ChatGPT went like this:

    Me:
    “Hey good morning. I’m in the gym, shoulder’s still a bit twingy, but I want to row. What do you recommend—and a warm-up too, please?”

    ChatGPT:
    Warm-Up (10–12 min total)

    1. Assault bike or light row – 5 minutes easy
    2. Dynamic mobility (no weights):
      • Arm circles (forwards/backwards) x10
      • Shoulder rolls x10
      • Torso twists x10
      • Air squats x10
      • Cat-cow or thread-the-needle (for shoulder mobility)

    Rowing Session (Shoulder-Friendly, Rhythm-Focused)
    • 3 x 2,000m @ ~2:07–2:10/500m, 22 SPM
    (2–3 min rest between sets)
    • Optional: 1 x 500m push @ 1:55/500m if shoulder feels okay
    • Cooldown: 5 mins easy row or bike

    “Keep your stroke smooth—no need to muscle through the finish. Let the legs drive, keep the core engaged, and guide the handle in.”

    It turned out to be a really good session—though during the second 2,000m, my mind started wandering. I found myself questioning all of it:
    What’s the point? Where is this going? Is a sub-7 even possible for someone like me? Am I getting bored?

    It came out of nowhere. It was like my old mindset trying to sneak back in and talk me out of it. Talk me into giving up.

    And give it up for what?
    Go back to how I was?
    No thanks.

    That second 2,000m came and went. Then the third. Then a 500m push—1:42.
    And that’s when it hit me: real progress is showing up.

    Three sets of 2,000 meters at a cruisy 2:05/500m pace and 21 SPM. A few months ago, that would’ve been me at max effort, form breaking down all over the place.
    That final 500m at 1:42? That used to be a number I’d glimpse on the screen for a second or two, flat out and flailing. Today, it was measured. Solid.

    The physical progress is great. But the mental shift is the bigger win.

    Old thinking tried to creep in—but the new mindset held strong.

    It’s not about hitting the perfect session.
    It’s about making the average ones stronger, more consistent.
    That’s how I know this is working.

    This is the Sub-7 Experiment.