I built a 500K LOC production app alone in 7 months. Here is the proof

For the last year we've been building an AI mobile app builder. Last week we decided to generalize our agent harness and benchmark it against vanilla Claude Code. Turns out the tools we built for app building were significantly more efficient than the native Claude Code tools. When we ran benchmarks we beat Claude code on speed (~40% faster) , cost (25-55% cheaper) and performance (+17% on Terminal Bench 2.0). Today we're making our agent harness publicly available as a Claude Code plugin. Use code WOZCODE1 to try it for $1 at wozcode.com

I used to be just a blogger. Now I build internet products, still without code, using AI, design, and taste. I was building in public on X for last 2 months. And honestly, I got tired of how it became performative and started to feel fake. I shipped 2 products. Both failed to get any real traction. I kept sneaking into popular builders’ profiles, hoping to learn how they do it. One thing I kept seeing everywhere, product launch directories. I thought here is the scope. So I started building one. Same UI like the rest. Nothing special. Suddenly one day when it was half built, I realized…

Built this code art project as a commentary on the recent wave of using LOC as a primary measure of engineering productivity It's now up to 350M lines of useless (but hopefully funny) code, constantly growing using GitHub actions and https://github.com/jshchnz/codemaxxing Unfortunately, GitHub has now sent me a notice to remove the repo within the next 14 days, so enjoy it while you can

I am a non-hacker "idea guy" with zero discernible talent. Like most, the story starts with me doing things the hard way. I dreamt of a tool that would save me countless hours. Like most of my ideas, it was supposed to die in a couple of hours, but this one had some legs.... "If I needed this, surely others did too" kept looping in my head. Could I get this built? Could I build it myself? Nah...too lazy to learn how, but before I did anything, I had to promise myself one thing: No more ideas! If ideas were sit-ups, I would have a six pack instead of this tire. It was a constant mental…

A little background. For the last 1.5 years I lost what could be considered an embarrassing amount of money hiring other people to work on a project that I thought had potential, I got some important people involved, had some great coders, but couldn't launch. The failure was depressing, rejection by YC didn't help.. I had to take a job, I didn't enjoy and I had a girlfriend who stood by me despite going into debt. But bouncing back over the last 45 days I've taught myself Rails some Jquery, and Javascript and built this www.hangout.io. It's empowering to build something myself because I'm…

My weekly(ish) video logs tracking my progress of building a completely sound statically typed language and structural editor. The motivation is to make lots of invalid programs unrepresentable.