The first time the model finished one of my sentences, I was writing about a caregiving tool for an aging parent. I paused at the end of a clause. The completion appeared in my draft. I read it. It was correct. I kept writing. Three weeks later, I went back to that section and could …
The model that knew too much and understood nothing · Hanh D. Brown Read More »
Creating consistent designs throughout your application seems like a very trivial task that you can achieve with coding agents. However, if most of your code is written by coding agents, I believe this can quickly turn into an application with a lot of different design elements if you don’t pay close attention to exactly how …
How to Build Consistent Designs with Claude Code Read More »
The sentence is not about loss. Loss has already been described too well by too many machines trained on too much literature. The sentence is about the cadence my mother sang while she cooked. I do not remember the words. I remember the cadence. IN THIS ESSAY 01The category is embodied continuity, not autobiography, the …
What the machine simply cannot ever manage to say to you · Hanh D. Brown Read More »
Here’s a function most reviewers would wave through. It fetches some orders, calls an API, logs a line, returns a result, and every test on the happy path passes. It also builds its own HTTP client, waits on the network forever, and logs “processing failed” with no way to tell which job. And there’s no …
7 Python Best Practices Senior Developers Follow (That Beginners Often Miss) Read More »
The decision before the sentence# Before a writer commits to a sentence, they have to commit to a position. Most don’t. They write the sentence first and hope the position emerges from it. Not for me. IN THIS ESSAY 01The decision that arrives before the sentence does 02What the decision actually is when you write …
On writing like you genuinely mean every single word · Hanh D. Brown Read More »
Somewhere in your company there is a slide that says something like this: customers who enabled the AI assistant retain 15 points better than customers who did not. It has a bar chart. It has been in three executive reviews. It is driving next quarter’s roadmap. Nobody randomized the AI assistant. It shipped to eligible …
I have been a real estate investor for eighteen years. My first home was in Plymouth, Michigan, in 2008. Since then I have moved into multi-family. I started building with AI when ChatGPT shipped in November 2022. The first practice is far older than the second, and it is teaching the second most of what …
The other twenty years of a long working life ahead · Hanh D. Brown Read More »
Introduction Spaghetti code is hard to work with because its logic is tangled. A function in Python can handle several related steps and still be perfectly readable. Problems start when different responsibilities become tightly connected, dependencies are unclear, and changing one piece of logic requires tracing through unrelated parts of the code. Breaking code into …
From Spaghetti Code to Clean Python: A Beginner’s Guide Read More »
I keep a folder of sentences I have not implemented yet. I do not call it the almost folder. I do not call it the failure folder. I call it the working folder, because the work is what is in it. I believe in starting before I know what to do. The discipline is to …
The sentences I keep from other people’s good writing · Hanh D. Brown Read More »
Building on the momentum of 3.7 Flash from three weeks ago and marking our third Flash release in only six weeks, today we’re introducing Gemini 3.8, our best reasoning and coding model yet, at the same speed and low cost of 3.7. Gemini 3.8 introduces 2 variants: Gemini 3.8 Flash: our most intelligent workhorse model, …
Introducing Gemini 3.8 Flash and 3.8 Flash Cyber Read More »
