"Tell AI to build Netflix": viral exchange reignites debate on AI coding limits
burny_tech · x · 2026-11-01
A viral X exchange pits AI-coding skeptics against enthusiasts. A critic taunts the 'no security vulnerabilities' claim by challenging advocates to have AI build Netflix end-to-end — data models, infra, CDN, recommendation engine, PCI-compliant payments — with zero human input, quipping that 'adding make-no-mistakes to the prompt really helps.'
The reblogger counters that the bar is absurd: human-written software also ships with vulnerabilities. The exchange captures the community's ongoing split over vibe coding versus production-grade software.
More from coding & agent
- traits.sh turns agent code-review feedback into reusable traits, enforcing Redacted for secrets — samgoodwin89 · 2026-11-01
- Google's rakyll: agent quality hinges on locked-down, reproducible environments — IaC principles still apply — rakyll · 2026-11-01
- Pre-call guardrails that stop a runaway AI agent before the bill arrives — MaverikSh · 2026-11-01
- Browser-Based Video Mapping Built with Claude Code, Open for Agent Remixing — ismaelfaro · 2026-11-01
- Dev runs Codex-driven Blender 3D modeling agent through 8 iterations, hits prompt limits — ZeYanjie · 2026-11-01
- Craft team open-sources Craft Anything for understanding how any software works — ismaelgokufox · 2026-11-01