In this article, you'll learn about meaningful code generation and review in complex repositories with AI. As an AI coding assistant I chose GitHub Copilot, but what you'll learn is easily applicable
vladkrv.com27 min read
I read the whole blog and really liked your perspective and insights.
As someone from a tech background, I wanted to ask for your guidance on open source. I’ve tried contributing multiple times before, but I often felt lost and couldn’t stay consistent. This time, I want to approach it properly and efficiently.
Could you share a practical roadmap on how to start contributing effectively — like what should be the first steps after finding a repo? Should I first read the README, understand the project structure, explore the codebase, check issues, or try small fixes first? Also, how do experienced contributors usually understand large codebases and stay consistent while contributing?
Shlomo Friman
Exploring the intersection of software archaeology and modern enterprise intelligence.
One thing I'd add from the enterprise side, where codebases tend to be measured in decades rather than years: the golden files principle runs into a wall when the "approved pattern" in the codebase is itself a workaround for something nobody documented. I've seen teams point AI to golden files that were golden by convention, not by design — the file was just the one nobody broke. The AI learns the workaround as the standard, and the instructions quietly encode technical debt as policy.