Vibe Engineering

One of the lesser spoken truths of working productively with LLMs as a software engineer on non-toy-projects is that it’s difficult. There’s a lot of depth to understanding how to use the tools, there are plenty of traps to avoid, and the pace at which they can churn out working code raises the bar for what the human participant can and should be contributing.

It can be so easy to see code and think hey! this works! But code that works is only half of what it means to develop software. Can the code scale at all? Can it be maintained? Is it efficient? For a little tool you're building to help you with something, maybe none of that matters. But for anything more extensive than that, you bet it does.

If you’re going to really exploit the capabilities of these new tools, you need to be operating at the top of your game. You’re not just responsible for writing the code—you’re researching approaches, deciding on high-level architecture, writing specifications, defining success criteria, designing agentic loops, planning QA, managing a growing army of weird digital interns who will absolutely cheat if you give them a chance, and spending so much time on code review.

Almost all of these are characteristics of senior software engineers already!