I built an AI Trend Analyzer to stop myself from doomscrolling
As a content creator in the tech space, I found myself caught in an all-too-familiar trap: endless hours of doomscrolling through social media and news aggregators, trying to stay on top of the latest trends.
The signal-to-noise ratio was abysmal—for every meaningful tech development, I had to wade through countless memes, heated arguments, and clickbait. I knew there had to be a better way.
Continue Reading →Giga: An AI that actually understands your codebase
Modern software development is complex. Our projects have hundreds of files, intricate dependencies, and carefully thought-out architectural decisions.
While AI coding assistants are powerful, they often feel like well-meaning but forgetful colleagues—you have to keep reminding them about your project structure, tech choices, and coding patterns.
Continue Reading →Is AI ready to be a mid-level engineer?
Mark Zuckerberg recently claimed AI will replace mid-level engineers by 2025.
As someone building AI developer tools and studying their real-world implementation, I believe this fundamentally misunderstands both the current state of AI and the role of mid-level engineers.
Here’s what Meta is missing.
Continue Reading →Stop Using Just One AI Model in Production
Learning why model redundancy > optimization
It started with a frustrating Thursday afternoon. Our code analysis service was hitting rate limits constantly, and I was doing what any reasonable engineer would do: optimizing our token usage, implementing better queuing, and trying to squeeze maximum performance from our chosen model.
Nothing worked. Or rather, everything worked a little bit, but not enough.
Continue Reading →LLM “Structured Outputs” are Missing the Point
Last week, my AI coding assistant generated a perfectly-structured code review suggestion.
The format was immaculate - every field properly typed, every attribute carefully specified, the suggestion clear and actionable.
There was just one problem: it fundamentally misunderstood how our authentication system worked.
Continue Reading →What 6 hours at HN #1 actually does to your traffic
“Every developer has that one post they almost didn’t write…”
For 2025, I decided to get back into technical writing.
I’ve been obsessing over getting AI to actually understand production code. Not just generate it, but really grok what’s happening in a mature codebase.
After countless nights exploring this rabbit hole, I wrote about a breakthrough I had.
Sunday morning, I posted it on HackerNews. “Why not,” I thought, “maybe someone will find it interesting.”
Then I went back to my weekend.
Continue Reading →The day I taught AI to read code like a Senior Developer
A messy experiment that changed how we think about AI code analysis
Last week, I watched our AI choke on a React codebase - again. As timeout errors flooded my terminal, something clicked. We’d been teaching AI to read code like a fresh bootcamp grad, not a senior developer.
Here’s what I mean.
Continue Reading →