LLMs Killed My Favorite Procrastination Excuse (and I’m Grateful)
In Overcome the Monday Morning Hurdle I wrote about my technique to easily get into flow in the morning. I thought about adding something similar to TODO comment, something like TMRW-FIX .
It would be something like: TMRW_FIX before save show modal with related streams
That way, I’d add TMRW-FIX label when I finish my day & next morning I’ll be immediately in the context. My idea was to create CLI tool + Git hook to disable committing.
I started thinking about all the stuff that I need to learn. At that time, I was diving into Go, so that would give me opportunity to learn along. I’ll learn about building CLI tools, integrating with Git, and so much more. I was so excited about things I’ll learn. I was looking at future and anticipating what amazing stuff I’ll be building.
But that will be someday.
Now, I don’t have time. That’s a big project. A lot of things to learn. But it will be awesome, someday. It’s so much simpler to think about work than doing it. I can often see myself tangled in my mind thinking, and thinking, and thinking. Planning everything in details, but finally doing nothing.
Procrastination. What a beast.
And then one day I sat down to start building TRMW_FIX CLI. I decided I’ll learn about all stuff along the way (which is totally not my way of learning). I’ll learn while building. I start ChatGPT, I run Cursor & start coding.
Let’s not fool ourselves. TMRW_FIX CLI doesn’t sound hard. The problem itself is trivial. Go, CLI, integrations adds a bit of complexity. Still, if you stick to learning just enough to complete project, it’s not a lot.
After 2 hours of coding, I had working version.
After another 2 hours, I’ve added pre-commit & Homebrew integrations.
And all that planning?
Pre & Post-LLM Reality
Pre-LLM era, building working demo took a lot of time. Of course, it depends on the project itself, but it was rather weeks/months than days/hours. You could live in peacefully, thinking that if only you had time to build product…
And then we’re in LLM-driven development world…
It changes a lot. Now it takes days to build working demo. DAYS. (Some say hours but let’s be honest…)
Coding Is The Easy Part
If you have ever build a project on your own, then you probably know that building (or rather coding) is the EASY part. Talking with customers, marketing, selling, those are HARD things. As developers, we like to think that coding is critical part of building a product (and it’s very important), but the thing is that … yeah… there’s a lot more to make money on product.
I’m building my products as side-gig. That’s more like a learning project, validation that I can ship, play with new technologies. And only if, only if, only if everything goes well to make some money. That’s also why I don’t invest into extensive market/user research. If it solves my problem, it’s often enough to start building.
Dear Developer, It’s Time To Sell
It’s so much faster building walking skeleton (I won’t say it’s anything more after spending few hours on project). It’s going to be even more critical to think about sales. And that’s the most terrifying thing a developer needs to face.
Software is seldom an asset. Software is a way to solve problem. And it only helps if it’s solving a problem better than other method.
Now, it’s even more important to conduct market research, validate, market, sell, look for product-market fit. LLMs push coding into commodity basket.
The thing is you can’t escape marketing & selling (but only if you want to make money).
Procrastinating because you need to learn a lot is no longer an option. You need to find another excuse.
PS: I’m avid fan of Lean Startup, preparing working skeleton, talking with customers & validating ideas BEFORE building. But I also know that world is a bit more complex. There’s no one size fits all. There’s not always a way to validate idea before building. There are many stories when building real MVP was the proper way to check idea.