AI-written code runs 3x longer and is harder to read: reading it all is quixotic, economist argues
paulnovosad · x · 2026-09-17
paulnovosad's hands-on take: AI code is 3x longer and harder to read; his projects span 5–25,000 lines nobody can carefully review. Verification is essential, but expecting humans to read all AI code is quixotic.
Related event: Economists Debate Whether AI-Generated Code Needs Human Review(2 posts)→
More from coding & agent
- Agent safety startup Raindrop raises to $50M total, launches Simulations to catch failures pre-production — ycombinator · 2026-09-18
- YC-backed Raindrop launches Simulations to catch AI agent failures pre-production — ycombinator · 2026-09-18
- RedMonk: Developers were the new kingmakers — agents are next in line — rseroter · 2026-09-18
- openwiki v0.5.2 adds bob coding agent integration, now 6 total — LangChain · 2026-09-18
- The 'Seniority Cliff': skipping junior-level friction may hollow out engineering intuition — Jumpy-Increase9337 · 2026-09-18
- Aident's First Skill Uses Agents to Submit Products to 30+ Directories at Once — alifcoder · 2026-09-18