LLMs Are Lowering Coding Cost — But They May Be Increasing Debugging Complexity (opens in new tab)
Over the last few months, I have gradually built a fairly stable AI-assisted development workflow for my side projects. The workflow looks roughly like this. Architecture and design are handled by Claude Sonnet / Opus. I maintain a set of engineering skills and design templates for feature planning. Once the design document is finalized, DeepSeek V4 is responsible for implementation. After coding is complete, I run an independent review workflow inside OpenCode to perform security review, arc...
Read the original article