No Going Back

I'm dictating this post through a Swift app I built over the last couple of weeks. Push a key, talk, post appears. I didn't write the code character by character. I described what I wanted and an AI wrote it.

I don't think we're coming back from this.

The credentials

I'm 41. I've been building websites and apps since I was 13. My first paid computer job was at 16. £2.50 an hour to run 'remove' commands that deleted leftover files from a typesetting system. Looking back, that job should have been a cron job. I was literally paid to type commands that could have been automated in five minutes.

One Saturday morning, slightly hungover, I typed rm and got distracted. Came back, typed rm again, then the filename. Hit enter. The first rm had deleted rm. Command not found. I had to go tell my boss I'd removed his custom 'remove' command. That was a fun conversation.

Since then: freelance web design at 19. music technology at uni. Startups, agencies, banks. I built Java apps for Google Glass in 2013. I worked on a podcasting platform for six years. I wrote a 12-week bootcamp curriculum that's now trained thousands of developers. I've been doing this a while.

The wall

For the last few years, AI has been useful but limited. Copilot changed the game for writing tutorials. I could explain a concept and it would write the example code. 95% accurate, maybe higher. That was impressive.

But there was always a wall. Eventually you'd hit a loop where fixing one bug creates another, and fixing that one recreates the first. You'd bounce back and forth, never quite solving the whole problem. That was the ceiling.

Opus 4.5 broke through it.

The cost

I started at $20 a month. Then I was bouncing between Claude and GPT. Then Claude Code arrived. Now I pay $200 a month and I'm creating more software than I've ever been able to create in my life.

It sounds expensive until you see the output. 30 days to build something that would have taken a team of developers months. And not a rough prototype. Production-quality software with more polish than I could have added manually, because I have time to add finesse I never would have had before.

What the job becomes

Nobody is going to pay me to type slowly on a keyboard when they can generate thousands of lines of code in minutes. That's just the reality. It doesn't matter how I feel about it.

So what's left? Ideas. Business. Marketing. Knowing when to nudge the AI in the right direction and when to let it run. There's technique here. New territory to explore, new ways of working with something that didn't exist two years ago.

I don't necessarily like this fact. I've spent 25 years knowing which code to type. But liking it isn't the point. It's still true.

The revelation

The code itself isn't the surprising part. The surprising part is the documentation.

The process I've been using generates requirements documents, planning documents, deviation logs, verification reports. Every problem encountered, every solution found, every decision made and why. It's all captured.

If you put this corpus into a semantic search, you'd have the entire meaning of the project searchable. Every issue, every fix, every reasoning chain. That level of documentation would have been impossible even with the most diligent team I've ever worked with. The overhead would have been too high. Now it's nearly free.

That's more valuable than the code.

The future

The models that can produce quality are slow. The models that are fast can't quite match the quality yet. But both sides are improving. We're watching the gap close in real time.

I don't know exactly what software development looks like in five years. But I know it doesn't look like me typing on a keyboard character by character.

We're not coming back from this.