SEP 23, 2026
While I still think LLMs are mediocre at code, the whole "using LLMs is vibe coding" thing has passed. With the right constraints and feedback loops, they produce work more than comparable to a decent developer after PR review.
SEP 18, 2026
I remember back in the fall of 2025 the online chatter seemed to be that coding was getting "solved." Claude skill libraries & coding harnesses like (288k...
SEP 18, 2026
In coding with AI, I’ve found that one problem matters more than almost any other: keeping my mental model of a project in sync with what was actually built.
SEP 17, 2026
LLMs design is like those average-of-everything facemorphs from a few years ago. It's the average of all the designs out there - both good and bad.
SEP 16, 2026
One of the fundamental paradoxes of coding with LLMs is that they go fast when they should go slow and they go slow when they should go fast. Let me explain.
SEP 4, 2026
Habitizer was a small itch-to-scratch project that I built as a case study to see what an end-to-end build for an intentionally simple SwiftUI iOS app would...
SEP 3, 2026
So, after trying out a few different terms to capture the shift in software engineering caused by LLM coding models, I believe AI-Native Software Engineering...
SEP 1, 2026
If you ask any even slightly jaded software developer, they've likely worked on a project where having "nice things" cost too much developer time according to...
AUG 18, 2026
It used to be that writing code and tests was where you spent most of your development time budget. Depending on your role, PR reviews of other people's code...
AUG 16, 2026
You know the feeling - you start a new project with AI-Native software development and you're absolutely flying. Knocking down features like they are pins in a...
AUG 15, 2026
While there are a lot of things one can learn about how to more effectively use AI with a team - there is really just one hard and fast rule:
AUG 14, 2026
I'm not a big Rick & Morty enthusiast, but a colleague pointed me to this episode as a metaphor for working with coding agents, and boy, does it fit.
AUG 14, 2026
One of the obviously exceptional things about the current AI investment boom that we're in is how much money is being dumped into AI and LLMs, and how much...
AUG 12, 2026
I’m not the world’s biggest baseball fan, but I’ve always loved VORP - Value over replacement player. It’s an idea I’ve riffed on numerous times for various situations - basically take an average of X and evaluate individual emails, flows, etc against that average. What do those specific X bring to the table vs. the average? What makes them special and unique?
AUG 11, 2026
As many folks worry about LLMs racing towards AGI and the eventual machine apocalypse, the more I work with LLMs on coding, the more I'm coming to the opposite...
AUG 10, 2026
Claude code does amazing things. It also does blindly stupid things. Things that I wouldn't expect a first year CS student to do. Understanding how and why it...
AUG 10, 2026
I've always had a soft spot for a good analogy or metaphor. I've found that there's a massive amount of understanding that can be communicated succinctly with...
AUG 5, 2026
The goal of AI-Native Software Engineering, as I see it, is to figure out how to make a repeatable, consistent process out of building software with LLMs. To ...
AUG 4, 2026
It might seem odd, given that the thing LLMs are really good at is language, but the one thing that you really shouldn’t use AI for is writing for you....
AUG 3, 2026
A joke that my mind keeps coming back is told by one of the Eddie Murphys at the end of the classic '90s comedy Coming to America:
JUL 1, 2026
Many of you remember that feeling of doing the first few rounds of incremental development with Claude code and being surprised and impressed with what it was...
