Why developer capacity should be used to understand problems and create value, not maximized through constant coding and ticket activity.
AI can produce impressive work quickly, but expertise remains essential for judging and using it effectively.
How YouTubeSummary started as a simple teaching project, survived through real use, and only became worth rewriting after organic traffic arrived.
I spent $1.06 in AI tokens and 3 hours building a deterministic multiplayer Pong that 1,000 people can watch simultaneously from a single JSON endpoint
Why desktop AI agents could become the next productivity layer by helping people automate, adapt, and build tools directly where work happens.
Valérian de Thézan de Gaussan