Developer Postmortem: Fully Autonomous AI Coding for Complex Projects Fails
MarcJSchmidt · x · 2026-07-25
A developer shared lessons learned from six months of using AI tools like Claude, GPT, and Kimi for fully autonomous coding, which ultimately failed. For non-standard, complex projects, letting AI take the wheel leads to a decayed codebase filled with inconsistent files and drifted assumptions.
He has since shifted to a human-in-command strategy: he now writes the core code and pseudo-code himself, using AI only to fill in the blanks. He also intentionally writes documentation in his own language—being purposefully vague or specific—to maintain 100% understanding of the project. He also noted the struggle of finding the perfect claude.md prompt to stop the AI from overstepping and wrecking the codebase.
More from coding & agent
- One CLAUDE.md snippet stops Claude Code and Codex from using deprecated APIs — umeshonai · 2026-10-26
- HarnessMM paper cuts agent token use 87.9% on DeepSeek harness by reusing decisions — blaizedsouza · 2026-10-26
- NVIDIA open-sources SkillSpector, a security scanner for AI agent skills — NVIDIA · 2026-10-26
- Huashu Design 3.0 turns one agent prompt into deliverable design, 26k stars — alchaincyf · 2026-10-26
- OpenBot is a local-first desktop workspace for persistent AI teammates — nightly-labs · 2026-10-26
- Open-source agentic social scheduler Postiz hits 38k GitHub stars — gitroomhq · 2026-10-26