For decades I’ve chiselled through the thick accretion of features encrusting mass-market commercial writing software. I’ve foisted intricate templates upon Pages, saddled Docs with third-party browser extensions and mostly avoided Word. I’d also tried a string of boutique editors that were appealing in some ways and lacking or gimmicky in others.

Over a single weekend, entirely from scratch and heavily “vibe coded”, I created by some distance the best word processor I have ever used. I’ve named it vibedit. I’m writing in it right now. If there is an actually productive task for generative AI, it is as a creator of bespoke tools like this. Given this new, relative ease of app development, it is easy to imagine the atomisation of software into a mist of customised personal projects, droplets as numerous as users.

Aside from the software product, the experience had other benefits. I felt at liberty from corporate design, and could easily amend my own app as I thought of additions and deletions. And far from removing me from my work, this AI experience forced me to think carefully about how I work, and how to craft a fitting tool. I was also confronted as any craftsperson should be by the minutiae of my tools — technicalities like stream parsing, dirty state tracking, debouncing and atomicity. I have since built a second app devoted to task management, another erstwhile source of daily frustration.

Financial Times: Content 071b2770 5106 4530 a290 2a5eba06c8b2 (subscription required.)

If a non software engineer could create a personal word processor and task management app so easily, I believe software giants like Microsoft, Adobe, CRM et al are in serious trouble.