Tag
OpenAI's official blog revealed how its core engineering team uses the GPT-6 series (including GPT-6 Astra) and Codex for large-scale codebase maintenance, merging over 1,400 cleanup PRs in two weeks, deleting 800k+ lines of code, and sharing the actual production prompts used for dead-code cleanup, feature-flag pruning, CI optimization, flaky test fixes, and agent instruction self-inspection.
In the era of Vibe Coding, AI makes code generation easy, but software engineering principles like code maintainability and design patterns become more important to address challenges in review, debugging, and refactoring.
The post compares AI agents to 'rockstar developers' who create clever but unmaintainable code, pointing out that agents lack memory of their own actions. It recommends using visible conventions like AGENTS.md, ADRs, and tests to keep agent-generated code understandable by the team.
The author argues that AI agents are both creating and maintaining codebases, questioning the predicted need for human cleanup armies, and suggests that the mid-level developer role is being squeezed.