How is a CEO shipping 37k lines of code daily?
Naturally, people weren't just going to take his word for it. A developer decided to actually "look under the hood" to see how this workflow functions in practice. It turns out, this isn't just about hitting a "generate" button and hoping for the best. It's about a highly optimized developer workflow using advanced LLMs and AI coding assistants.
The real takeaway here isn't just the sheer volume of code, but the shift in how we perceive software engineering. We are moving away from the era of manual syntax typing and moving toward a role that feels more like a system architect or an editor. When you use AI tools to handle the heavy lifting of boilerplate and repetitive logic, your output capacity scales exponentially.
But it does raise some interesting questions for all of us here. If we are seeing this level of code generation, how does the role of a junior developer change? How do we maintain code quality and prevent technical debt when the velocity is this high? Are we becoming better architects, or are we just becoming curators of machine-generated output?
I'd love to hear your thoughts. Do you think 37k lines a day is a sustainable metric for productivity, or is it just a vanity number? Are you incorporating this kind of high-velocity AI workflow into your own dev stack yet? Let's discuss!