Economist Pushes Back on 'Read Your AI Code': Nobody Can Review 25,000 Lines
paulnovosad · x · 2026-09-17
Economist paulnovosad argues nobody can carefully read the 5,000–25,000 lines of build code his AI-assisted projects generate and still catch subtle bugs, pushing back on Ryan ReedHill's claim that reviewing AI-written data-cleaning code is quick and lowers replication risk.
Related event: Economists Debate Whether AI-Generated Code Needs Human Review(2 posts)→
More from coding & agent
- LangChain Rebuilds LangSmith Trace Filtering for Faster Agent Observability — LangChain · 2026-09-18
- LangChain rebuilds LangSmith trace filtering for faster, more precise agent debugging — LangChain · 2026-09-18
- Dev: The Smartest Model Isn't the Best at Writing Simple, Mergeable Code — timigod · 2026-09-18
- LinkedIn to present a PyTorch-native GPU retrieval engine powering feed and search — PyTorch · 2026-09-18
- Jev + Kimi K3 cascade classifies 100 fraud emails at 96% accuracy for $0.07 — nutlope · 2026-09-17
- AWS compares Bedrock RAG vector stores: OpenSearch vs pgvector vs S3 Vectors — AWS ML Blog · 2026-09-17