AI Zealotry

Summary

AI Zealotry I develop with AI today. It's great. There are many articles you can read on why AI is great (or terrible) or how to use it. This is mine. I focus on the experience of a senior engineer (and why we in particular should use AI), on my experience operating within the OSS Python Data world, and on practical suggestions that I've found myself repeating to colleagues. This article contains learned lessons of two types: Big Ideas: Grand(iose) philosophy on why AI is great for experienced programmers Tips: Taken from my workflow using Claude Code We'll interleave these two. I'm hopeful that this approach will make this more fun. Why AI AI development is more fun. I do more of what I like (think, experiment, write) and less of what I don't like (wrestle with computers). I feel both that I can move faster and operate in areas that were previously inaccessible to me (like frontend). Experienced developers should all be doing this. We're good enough to avoid AI Slop, and there's so much we can accomplish today. I like this quote from this blog I get it, you’re too good to vibe code. You’re a senior developer who has been doing this for 20 years and knows the system like the back of your hand. [...] No, you’re not too good to vibe code. In fact, you’re the only person who should be vibe coding. I think that really good engineers, the kind that think hard before writing, can have a tremendous impact and fun while developing with AI. I wouldn't ever go back. Why Not AI That being said, there are some serious costs and reasonable reservations to AI development. Let's start by listing those concerns: LLMs generate junk LLMs generate a lot of junk Writing code ourselves builds understanding Reviewing code for correctness is the slow part, not writing it AI workflows can be dehumanizing when you just press "yes, allow" over and over again These are super-valid concerns. They're also concerns that I suspect came around when we developed compilers and people stopped writing...