My Code, My Test, and My Prompt All Agreed. All Three Were Wrong.
I tried to replace my receipt model with one 18× cheaper. The bug turned out to be in my own check, and the real lesson was about trusting AI to verify itself.
Jul 8, 202613 min read
Command Palette
Search for a command to run...
Latest articles
The Job Isn't Writing Code. It's Knowing When the AI Is Wrong.
Three examples from my AI-powered job board pipeline where the output looked right but wasn't.
Feb 19, 20264 min readI Benchmarked 6 LLMs to Automate My Job Board for $0.35/Month
Not all models are good at the same thing. Here's the data.
Feb 10, 20269 min read
I Built 2 Job Scrapers in One Weekend to Avoid Paying for Data
How AI helped me stay on Apify's free tier
Feb 2, 20265 min readWhat If We Could Fix Barbados Traffic With Data?
A Look at the Barbados Traffic Analysis Challenge: Using ML to Improve Traffic Flow
Nov 23, 20254 min read
I Built a Job Board for Transparency. But Is Applying Even the Right Strategy?
Five weeks ago, I launched GlobalRemote — a curated job board focused on interview transparency for remote developers. The feedback was encouraging: developers loved knowing what to expect before applying. I expanded from 7 manually verified jobs to ...
Oct 10, 20259 min readFrom Interview Surprise to MVP: Testing Developer Job Transparency
A few weeks ago, I applied for a Backend Engineering role, expecting a technical interview similar to what I had experienced before—like the collaborative pair programming session I had when joining Automattic, where a developer and I worked together...
Sep 15, 20255 min readEssential Course Notes on Cloud Native Application Architecture
My experience converting a monolithic app to microservices
Oct 25, 20212 min read