The problem is not the AI code, but nobody knows anything anymore

Automated excerpt

If we think Is writing code dead, and AI is generating all codebases, I still think the bigger problem is people or full teams not knowing anything anymore about the system architecture or the intent behind why certain choices have been made. The specs, code, tests, PRDs, tickets, resolution of those tickets, reports, etc. , everything is made by Claude Code. I think AI writes probably average code (depending on the task and size).

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.