Vibe coding gets a bad rap: an engineer draws the line between vibes and real engineering
bendee983 · x · 2026-10-16
bendee983 argues vibe coding's bad reputation comes from conflating categories:
- Not every use of AI coding agents is vibe coding — nearly all engineers now use them.
- Vibe coding = vague, generic prompts (e.g. 'clone App X for Y') plus generic feedback, without overseeing intermediate decisions like architecture or reviewing code.
- Real software engineering (incl. agentic engineering) = keeping all core disciplines while using AI agents — you own the code, understand the architecture, and can investigate errors.
The core claim: criticism should target the unreviewed, unaccountable workflow, not the tools themselves.
More from coding & agent
- Sarvam AI x Figma: Indus-Powered Agents Now Design Directly in Figma via MCP — itsOmSarraf_ · 2026-10-16
- Indie dev adds MCP server to $49 Mac VM app so agents break throwaway clones, not your Mac — ScholarBackground836 · 2026-10-16
- ComfyUI drag-and-drop broken? Node packs hijacking global drop handlers and how to find them — Inside_Chocolate_967 · 2026-10-16
- Why social-media AI demos look strong but your AI feels weak: the Agent four-piece framework — yangyi · 2026-10-16
- Duplicate webhooks, billed retries: the hidden costs of wiring a transcription API into an agent — Acrobatic-Farmer-109 · 2026-10-16
- Constraints you force on models today will become tech debt in months, warns dev — zack_overflow · 2026-10-16