Thoughts on developer tools, infrastructure, building in public, and the art of using and building AI tooling. Join us as we share lessons learned, failures overcome, and the occasional rant about DevOps.
For years the AI coding tools didn't impress me. Then last October someone said the word 'Cursor,' and I haven't come up for air since. The honest inventory, with benchmarks.
Agentic coding didn't delete the work. It picked it up out of the middle of the pipeline and set it back down on the two ends. Same total, redistributed.
We curse hallucination as the cardinal sin of LLMs. It's the same property we praise when the model writes a test we didn't think of. The bug and the feature are one thing, pointed two directions.
Most prompts get treated like a Slack message to your past self. The ones that actually work get treated like code somebody else is going to read.
Get the latest posts on AI tooling, infrastructure, and building in public delivered to your inbox. No tracking pixels, no behavior emails — just the posts.
We respect your privacy. Unsubscribe at any time.