Been sitting with some data this week: across 22,000 developers, AI-generated code is now up to 42% of what's shipped but review time is up 441%, and PRs wait roughly 5x longer for a human look. 96% of devs don't fully trust the AI code they're reviewing.
That tracks with what...
This week I ran into a failure mode that's becoming common on AI-assisted builds: the agent rebuilding something the team already killed.
On a recent project, I pointed an agent at a module we'd deliberately left half-finished we tried an approach, decided it didn't fit the...
This week I went down a rabbit hole after reading about a Netflix engineer who found that up to 90% of the tokens fed into AI models during agentic workflows are pure waste bloated logs, raw JSON, repeated file trees.
I checked my own setup. Turns out I was doing the same thing:...
A quick note on my own toolchain, since people ask.
I don't use one AI coding tool I use three, and which one I reach for depends entirely on the job in front of me.
...
Quick note from this week's build: I caught myself doing the exact thing I keep warning clients about.
Was moving fast on a feature with AI doing most of the scaffolding - and it worked, first try, looked clean. I almost merged it as-is. Then I actually traced through the edge...
