Nobody knows how large software products work

kept by eddie dec 25, 25

Large software products are so complex and rapidly changing that even engineers often cannot answer basic questions about them without investigative research.

There's no reason for software to be slow anymore
AI dramatically reduces the cost of software optimization, enabling workload-specific performance gains that were previously too expensive to pursue.
also on Dan Luu, #developer-tools
You can't design software you don't work on
Effective software design in large existing systems requires deep codebase familiarity, making generic design advice largely useless for practical problems.
also on Sean Goedecke, #organizational-health, #software-engineering, #developer-tools
Why I Ignore The Spotlight as a Staff Engineer - Lalit Maganti
A senior staff engineer at Google argues that long-term stewardship of infrastructure systems yields more impact than chasing high-visibility product work.
also on Sean Goedecke, #software-engineering, #developer-tools
Auto-generating documentation sites from GitHub repos
Mintlify built a multi-agent system that auto-generates production-ready documentation sites from any public GitHub repo by planning structure first, then writing pages in parallel within sandboxed AI agents.
also on #documentation, #software-engineering, #developer-tools
Code Wiki
Google's Code Wiki uses Gemini to automatically generate and maintain interactive documentation, diagrams, and AI chat for code repositories, staying synced with every PR merge.
also on #documentation, #software-engineering, #developer-tools