Memory Lane

It seems somewhat fitting that now, March 11, 2026, almost two years ago to the day that ChatGPT 4 was released (and almost two years after I asked GPT4 my first recorded questionI distinctly remember asking GPT3.5 to create a song about something in the style of Nine Inch Nails, but my ChatGPT.com history only goes back to March 27, 2023.

Compare March 2023 with March 2026. (I have no idea why I was interested in this.) ), I’m writing my first thoughts on it.

There’s a lot of churn in the AI/LLM/Agent space, but I’ve landed on an approach that reliably produces production-quality code for non-trivial work. The core insight is simple: use multiple LLMs to develop a solid architecture, then implement it through a phased crawl/walk/run approach.

Getting the plan right before writing code is where most of the value is. Here’s how that plays out in practice.

Process Overview

1. Set up your environment
2. Arrive at an architecture thru multiple LLMs
3. Adversarially review the result
4. Generate a crawl/walk/run implementation plan
5. Implement phase by phase, reviewing as I/you go

Environment Prep

Dev Containers

The agent needs to run your tests, catch its own errors, and iterate without you babysitting it. Without that feedback loop, you’re stuck manually pasting error messages back in or clicking “yes, run bin/rails test” after every step.

Oops

It has been a long, long, loooooong time since I last wrote here (not that anyone is reading, but hi there AI scrapers!).

Lots of things have happened since late 2018 - the COVID pandemic, a few startups and jobs, and the astonishing rise of AI (nothing in this article or my archives were written by AI).

I do have some takes on those things, but I thought before I did it was worth revisiting my older content with an ideally older, wiser eye ⚡Oops (or in my case, eyes that now wear corrective lenses!)

You may notice sidenotes like these in the archives. This is to call out specific things I thought were worth noticing.