Kill your darlings, they keep saying

For a few months now, Iโ€™ve been working with Claude Code on an experimental project. Itโ€™s a system to help me document my days and emotions while I attempt to walk the entire length of New Zealand.

Most people who walk this trail document their journey on social media. Instagram is naturally the best fit, because itโ€™s audiovisual and doesnโ€™t penalise you too much if you donโ€™t post chronically. TikTok is another popular choice. For those who use these two platforms to post shorter videos throughout their journey, YouTube is the endgame. Open it up and youโ€™ll see day by day logs, hour-long documentaries, and detailed series that capture the essence of what itโ€™s like to be on this epic adventure.

I wanted to post on Instagram as well. But I also wanted to document daily notes just for myself. As notes. That I can look back on. Like a journal, in written form.

So I planned it. I knew I might be too tired after walking 8-9 hours to sit down and type into a phone. Even though Iโ€™ve written several long-form pieces on my phone before, part of me doubted that I’d do that on trail.

It was easy enough to build the shell. The interface was decent with an option to record voice notes, that would be transcribed and cleaned up before saving. And because I like to double check my work and double bag my electronics, I also decided to have a text-only log. That way, I could write or talk into my phone, depending on my mood.

I tested it. Neither the record button nor the save text button worked. I sat down to diagnose. After a lot of back and forth and enabling and disabling the developer menu on Safari, I learnt how to verify the error. A bit more back and forth with Claude Chat and we finally fixed the save text button. By then, it was 2am and we still needed to figure out what was wrong with the audio record button.

So I fell asleep and forgot about the project for two weeks. That was my reality throughout this processโ€”I didnโ€™t magically build a fabulous thing over a weekend. It took me months. Work and life happened. No matter how much I wanted to ignore the world and play with Claude, I had other commitments to honour, a father recovering from surgery, and a family that loves to be dramatic.

When I eventually returned to Claude, we went through several attempts to fix the issue before realising I needed to sign up to a voice transcription service, connect its API to Claude, and only then would my record button work.

Obviously, thatโ€™s common sense. However, I was under the impression that Claude Chat, with all its mightiness, could transcribe audio. In the planning stage, I didnโ€™t ask the question specifically so Claude didnโ€™t tell me.

Now I know Claude canโ€™t transcribe audio. Neither can ChatGPT. But Perplexity does a pretty good jobโ€”it even transcribed Tamil, my first language.

Then I had to contend with two options: Sign up to a transcription tool and connect that to my Claude app. Or ditch the voice recording feature entirely.

The purpose of this project was to be able to talk into my phone. I didn’t want to get rid of it.

I took several days to think it over and kept coming back to the same idea: What if the transcription connection failed mid-way?

Iโ€™ve worked in tech long enough to know that every piece of tech you plug into another piece of techโ€”like adding more weight to your bicycle rackโ€”is a potential point of failure. This is how software works. When somethingโ€™s off, you check the plumbing, where things connect with each other, because thatโ€™s almost always the cause for a leak.

I went down that thought process rabbit hole. If transcription does fail for whatever reason, I would know fairly quickly. But thereโ€™d be no way to fix it while Iโ€™m on a 3000-km tramp. I mean, strictly speaking I could, but itโ€™d be tedious and not what Iโ€™d want to do on trail anyway.

Then thereโ€™s the issue of backup. I wanted all my entries (text and voice) to be backed up to my Zoho WorkDrive account. In case I dropped my phone in the Whanganui river, everything I’d done until that point would still be safe. If transcription fails and I fix it, then Iโ€™d also have to re-check the backup status. All of this is super simple when I have a laptop connected to a stable internet connection, sat in my home with a hot coffee by my side. Itโ€™s torture to work all of that out on my iPhone, with spotty internet, in the backcountry, sitting on an uncomfortable rock, hungry and sore from walking all day.

If transcription fails and I don’t fix it, I won’t have an alternative voice recording system thatโ€™s as efficient and battery-conscious as the one I was trying to build. My phoneโ€™s voice notes would be fine, but theyโ€™d become messy. They wonโ€™t be automatically location-tagged or categorised by emotions and regionsโ€”a feature I definitely wanted.

Eventually, I decided to remove the voice option altogether. Going the extra mile to build it didnโ€™t guarantee reliability. The extra work and admin didnโ€™t justify the risk.

This was my biggest disappointment in the whole process: Having to kill the thing that got me started.

Even without the voice recording feature, I still have other potential points of failure in my app. Iโ€™ve done what I can to minimise niggly issues, but the real test would be on trail. One way to find out.


โ€”
This is post 3 of 5.

Who will I be on trail?

A little while ago, I decided to create something with Claude Code to help me document my upcoming hike along Te Araroaโ€”or TA. It’s a 3000 kilometre walk from one end of New Zealand to the other. Iโ€™m going southboundโ€”so from Cape Reinga at the top to Bluff at the bottom of the South Island.

Map of Aotearoa New Zealand with the Te Araroa trail running through it
Source: https://www.teararoa.org.nz/map/

I’ve never done a multi-day hike before. I’ve done lots of day hikes of varying complexities but I’ve never had to worry about not having phone signal for long stretches or being out in the wild having to fend for myself. So I don’t know what that would do to me physically and psychologically. Which is fine, and is kind of the whole point of doing the hikeโ€”to challenge myself in ways I never have before and to hopefully find the courage and resilience within me to keep going.

I don’t know the person I’d become on trail, so building any piece of technology for this person is a bit tricky. I mean, would I want to sit down and write long drawn essays at camp after walking 25 kilometres a day? What would my tolerance be like after 20 river crossings and a big gash on my foot, surrounded by sandflies? Would I even care about writing the story then as I care about it now? Maybe, but also maybe not.

And that’s a problem. Because good technology understands the user’s mindset and behaviours. For instance, if you’re sat in an office with access to unwavering internet, you take it for granted that Safari will load your website without glitches. But when youโ€™re going in and out of network areas all day, would you prioritise sending a message to your now-single and post-heart-surgery dad or would you try and open a website?

So many questions and so few answers. Thatโ€™s what I was dealing with when I first went back and forth with Claude to see what we could build together.

As nerve wracking as that was, it was also one of the best lessons from this process: I had to do my best without assuming anything about my future self.

So I started making a list of things I need to factor in, while still allowing room for failure.

My solution needed to be as light weight as possible. It needed a daily journal log, and tags and categories to filter entries by. It needed to work offline, sync online. Mobile first, basic interface, less scrolling, big font, dark text, automatic location tagging that matches the TA route map, periodic data back-up, built-in language checkerโ€ฆ all the things I needed to figure out how to do.


This is post 2 of 5.

The notebook guy started it

For a few months now, I’ve been actively thinking about and planning for the biggest trip of my life so far: Te Araroaโ€”or TA. Basically, a long walk from the top of the North Island of New Zealand to the bottom of the South Island.

An essential part of the research is watching YouTube videos of other hikers that have gone before me, to learn from their experiences, to observe their gear, and methodologies and incorporate the lessons in my own planning and preparation. In one such video, I saw a brief scene where a hiker walks into a hut and greets the rest of the hikers who return the gestureโ€”clearly they all know each other. And one of the hikers in the hut looked up from his notebook in which he’d been scribbling something.

It was the first time I saw a video of someone writing in a notebook on TA. Most people use technologyโ€”cameras, voice recorders, phones, drones. It’s not a big deal, if you think about it. Journaling is such a common habit and a lot of hikers do it. I just hadn’t seen anyone do it on a five-month endurance hike like TA.

That got me thinking about my own trip and how I’d document my journey. I hadn’t thought about that particular thing before. I loved the idea of writing on a notebookโ€”in fact, I think I’ll still have a notebook. I’d appreciate the sheer analogue-ness of it after a hard day of walking.

But I also knew, within five seconds of watching that video, that I couldn’t rely only on handwritten notebooks to document my trip. One accident on the Whanganui river canoe section and all my notes would be dripping, dead weight.

I could use the Notes app on my phone, I considered. But they’d be so scattered. I didn’t know if I could trust myself to have the discipline to date and location-tag every entry, especially when I might be going through rainy, windy, sleety, scree slopey environments every day.

So I decided to find an alternative option that’d work a bit more… the way I want it to.

As a marketing copywriter who once obsessed with being found online, I’m ashamed to admit this: I didn’t even research what other options might be out there. Instead, like so many people of my generation and industry, I figured I’d just ask Claude.

For months I’d watched people on LinkedIn rave about Claude Code and brag about how they kept hitting their limits. There were proud posts about being on the highest paid plan of Claude Code because they were just building so much cool shit that the peasant version wasn’t enough anymore.

I hadn’t tried Claude Code yet because I didn’t know what I’d build. It seemed rather frivolous to pay for it for the sake of poking it and seeing if it’d poke back.

That clip of a guy writing on his notebook was the impetus I needed. I sat down with Claude Chat to talk it through. What could I build with Claude that could be useful for me on trail, and help me learn the basics of Claude Code and building a solution on it?

So I started experimenting with Claude Code. I’m building something to help me document my trip, and structure it in a way I can look back on and appreciate in the future. But as with any experiment, although the excitement and novelty of it buoys me, I also wonder if what I’m building will truly withstand the trail. I guess there’s only one way to find out.


This is post 1 of 5.

Taking a walk

About a year and a half ago, I moved to New Zealand. The company I work for had been looking to expand into the country, and I asked if there’s an opportunity for me to move and build up the business here. They said yes.

I had no idea what I was getting into. Turns out, they didn’t either.

Because even though I arrived as a marketing person, we needed more than a marketer. We needed someone who people can go to for… anything. It started a “here’s your local point of contact” that soon ballooned into a constant barrage of emails and calls from partners and customers and prospects asking questions, escalating issues, validating ideas, pitching events, and so much more. Plus, I was actively building my networkโ€”attending events, talking to people, trying to build partnerships, understanding how businesses operate… it’s fair to say I had a lot going on.

More than once, I’d be typing away in my home office at 3:45pm and remember I’d run out of food or toothpaste or shampoo or toilet paper. Or I’d walk into my living room and realise I hadn’t vacuumed or taken the recycling out for weeks. I’d laugh about it with colleagues after, while secretly wondering why I was so active, energetic, focussed on work but so careless and lazy about my home.

I enjoy 70 percent of my work. It involves meeting lots of new people, learning about their life and work, and trying to identify how we might work together.

The other 30 percent is gruelling. That involves working closely with my colleagues overseas. So lots of late nights, trying to get my brain to think straight even after it’d been running on work mode for 12 hours straight. Then I’d go to bed with my mind racing and refusing to shut down for another two hours. I never really stopped to think how crazy it was that that was week after week and month after month, rather than just a one-time thing.

Plenty of times I told myself it was just for this one project or one event, and things would become a lot less hectic after that. But after a year of it, I had to admit it wasn’t going to slow down. Don’t get me wrong, I had lots of “slow” days that I cherished. But those slow days were about 8-9 hours of work without any late meetings, events, or otherwise large stressors. In reality, that’s not a “slow” day, that’s the definition of a normal day.

I have a fairly high tolerance for stress. However, I’m also aware of what chronic stress can do to the body, inside and out, even if it doesn’t show straightaway. Sidenoteโ€”if you haven’t yet, I highly recommend reading Why Zebras Don’t get Ulcers by Robert Sapolsky.

So even though I knew I could keep pushing, I also knew that I shouldn’t. When you do weight training, they say you should do as many reps as you can until the point of failure. That’s how I’ve always thought about work stress as wellโ€”keep pushing until you can’t. One of my good friends once said that she’ll quit her job when she has her first heart attack. Not if but when. She’d been in that job for about 18 years, and she knew the stress would probably cause her to break. Work isn’t weight training. Yes, I want to get better and stronger and more accomplished in my work, but I don’t want to do that at the cost of getting sick.

So I decided to take a walk to clear my head.

I’d been wanting to walk Te Araroa for years now. It’s a tramping trail that runs the entire length of New Zealand. It’s always been one of those, “Oh, I’ll do it someday” kind of things. So in December last year, I sat down to think through what it’d really take to do this walk. There’s a lotโ€”food, accomodation, trail logistics, gear, safety, hygiene, loneliness, weather, and so many things that we take for granted on a daily basis.

So I started planning. I watched a lot of videos on YouTube, followed all the Facebook groups, looked through the trail inch by inch (got tired mid-way through the North Island), started collecting hundreds of links of potential gear, and created high-density, high calorie food recipes.

It was a glorious three weeks of intense work. Then the Christmas/New Year break ended and we went back to work. The full force of my daily routine returned, and this time it hit harder. We’d built momentum the previous year so now it was about acceleratingโ€”about doing more things, bigger things, and doing them faster. I love this stuff, remember. So I dove headfirst. I said yes to all the things, forgettingโ€”every timeโ€”that I was also saying yes to more late night meetings. As much fun as it was, it was also utterly exhausting. Every chance I got, I went back to my Te Araroa Trello board and looked through my research, adding a few more links. As March and May rolled around, I was in the thick of work with no brain power left even to write my daily haiku. For the first time in over five years, I stopped writing haiku every day. I had no energy left to give to my creativity. But I knew I still wanted to walk TA this year.

So in June this year, I rolled up my metaphorical sleeves and started narrowing down my gear options. By July I had most of my gear, and a lot of uncertainty about how many layers I’d need. I also spoke to my boss about taking time off. He took a couple of days to think it over and told me he couldn’t let me take time off. It was too much disruption for the business to lose the only marketing person in the country.

So I spent the next three weeks trying to convince myself to do the walk next year, instead. To keep pushing for another year because I know it’ll be fine.

But I couldn’t do it. The idea of doing it all for another year without a break scared me. Even if others don’t see it that way, I saw it as a health and safety issue. I didn’t want to end up in hospital for me to wake up and give myself a break.

I went back to boss and explained that I’m totally spent, and I need this time off. He understood, of course. He always did. But when you work for a big company, things like this need to be run up the food chain to be formally approved.

Now we wait.

I also just ordered a couple of water bladders and a backcountry bidet for the trip.

The land owns us

I’m walking Te Araroa (TA) later this year. There, I’ve said it. For the first time since I fell in love with the idea seven years ago and seriously started planning for it last December.

Loosely transliterated to “The Long Pathway,” Te Araroa is a 3000 kilometre (1800 miles, if you’re that way inclined) tramping/running trail that goes through the entire length of New Zealand. From the top of the North Island, Cape Reinga, to the bottom of the South Island, Bluff, the trail snakes through iconic forests, mountains, lakes, rivers, and volcanic craters. It’s one hell of a way to travel through the country.

What I love most about the trail is not its length or its majesty. It’s the fact that this trail only exists because of the kindness and generosity of humans that owe nothing to the people who walk the trail every year.

1800 kilometres of the 3000-km trail is on public land monitored, managed, and cared for by the Department of Conservationโ€”colloquially known as DOC, a little nod to the inimitable healing power the Department and its humans seem to have on the land.

The remaining 1200 kilometres are on private land. The Te Araroa Trust and DOC work closely with these private landowners to make sure the trail continues to live on for people who come from thousands of miles away to experience it. It’s a lot of work, negotiating with and reassuring these owners that hikers aren’t always a scourge on their land, and that the world deserves to see and appreciate Aotearoa in its entirety.

When I lived in India and Australia, I’d often see swathes of private property fenced off with stern signs that trespassers will be frowned upon and prosecuted. I hated that. I yearned for a world where roaming is a basic right and passing through is welcomeโ€”as long as you behave responsibly.

It’s a naive thought. There’s no country in the world that will allow random humans to walk onto and through other people’s property without explicit invitation.

Which is why Te Araroa is special. Anyone is allowed to walk through 1200 kilometres of private property without the fear of retribution.

However, that doesn’t mean that you can do whatever you want on that property. There are rules, written and unwritten. There are protocols, best practices, and basic human decency principles that every walker is expected to follow.

My past self would’ve raised eyebrows at this. I would’ve vehemently argued that land should not be “owned” by private individuals because it’s for everyone to appreciate and enjoy. The land-owning few enforcing rules on the rest of us seemed like a moral wrong to meโ€”especially when the land has been around for far longer than humans.

In the last few years, however, my perspective has shifted.

I still strongly believe that we don’t own the land; the land owns us. I believe that humanity has wasted itself by conjuring rules and regulations around who owns which part of land and for how long.

But now, I also believe that people who’ve invested their life in serving and conserving the land have the right to protect it against pests, humans and otherwise.

I will never let a horse, however sweet and charismatic, into my garden patch of broad beans. It’ll destroy the integrity of the land. I have a responsibility to my broadies and that means keeping out anything that might harm the life of the land.

Everyone who cares for land in the same way has the same responsibility. As soon as I realised that, I understood that this what native land titles were all aboutโ€”not to carve up land for use and abuse but to treat the land with the respect and grace it deserves. First Nations people embody this. I’ve never heard an Indigenous person talk about land ownership as an entitlement. They talk about it as a responsibility and an honour to stand guard.

Australians have a habit of starting every event and gathering with an acknowledgement to Country. It goes something like this: “We acknowledge the [name of native tribe] people, the original custodians of the lands that we’re meeting on today.” Australia didn’t respect the Original Custodians or the Country in its long, brutal, and bloody Colonial history. Even today, native land title is a heated topic in parliaments and dinner tables across the country. Despite that irony, the script reflects something meaningful. We so often unthinkingly utter those words, like a chore almostโ€”but they show the true depth of native land rights.

The land always owns usโ€”not the other way round. But there has also always existed a group of custodians who take on the heavy burden of nurturing the land, and living on the land long after the passers by are gone. So they should have a say in whether and how rest of us can walk through the land.

So when I say Te Araroa is special, it’s because these peopleโ€”both native title holders and those who bought property under the modern ways of lifeโ€”have come to agree to share their homes and back yards with the rest of the world. With no expectation other than we leave it as we find it.


Photos of The Escarpment Track, a 10km trail in Wellington, NZ. This trail forms a part of Te Araroa.