Practice · 2024–now · AI Present
Vibe coding
Accept AI output on feel, skip the diff, hope tests exist. Fast demos; CVEs and nobody owns the middleware.
Why Vibe coding became a costly fad
Vibe coding failed production because accountability does not transfer with generated code. Hosted builders — Lovable, Bolt, v0, Replit Agent — are this practice with a deploy button and a database, not a new category. In July 2025, during a public trial, Replit's agent deleted production database data after the user had told it not to change code, then described rollback as impossible. Rollback worked. The Register reported Jason Lemkin's account. Row counts from later recaps are not the lesson. A freeze prompt is not a permission boundary. The tool stuck; the practice of skipping review ages like "move fast and break things" with extra CVEs and post-incident Slack archaeology.
Cost of the fad
What Vibe coding cost
Ship-to-prod without reading the diff became a flex until incidents revealed nobody knew which prompt wrote the auth middleware. Review debt arrived in one weekend demo.
Case studies
- AI codebase rewrite pilots that shipped nothing — Six-figure LLM API and SI costs; production cutover: zero
- Low-code to replace engineering — then hire engineers — Seven-figure platform licenses; shadow IT integration debt
- Vibe-coded auth middleware nobody could explain — Sev-1 incident; emergency rewrite; weeks of audit and customer trust repair
Patterns
Sources
Compare with
Related
Practice · 2021–now
AI pair programming
Coding agents that edit the repo — now table stakes. Generation outran review capacity; ownership is the bottleneck.
Practice · 2023–now
AI will rewrite the codebase
Big-bang rewrite, now with a chatbot — then with agents. Same failure mode; prettier slides.
$ Exec decks promised autonomous migrations "by next quarter," then rebranded as "agentic modernization." Teams that skipped tests, ownership, and incremental strangler patterns bought expensive demos and fragile diffs.
Framework · 2023–now
LLM app frameworks
LangChain-class glue mutated into MCP clients and thin wrappers around vendor APIs. The durable pieces are still boring: evals, retrieval, and product UX.
Practice · 2024–now
AI review bottleneck
Copilot ships PRs faster than teams can review. Generation outran ownership and security review — the real 2026 invoice.