Simon Willison: LOC metrics matter with agents, but conceptual integrity is harder to keep
Simon Willison · rss · 2026-08-20
Simon Willison discusses AI's impact on software development, arguing that lines of code is a valid productivity metric if agents produce high-quality, debugged output. However, the new bottleneck is cognitive capacity; engineers need teams to manage the increased code volume. He also warns that cheap generation via agents threatens "conceptual integrity," comparing the result to the Winchester Mystery House—software grows in chaotic directions without the discipline enforced by previous time costs.
More from coding & agent
- brd-enhancer-mcp: Enhance dev tasks by retrieving project documentation via API — modelcontextprotocol · 2026-08-20
- Versium REACH: Generate B2B lead lists via AI agents using natural language — modelcontextprotocol · 2026-08-20
- Switching from in-IDE agents to chat interfaces boosted velocity but hurt code quality — BraceSproul · 2026-08-20
- Agent automates travel planning and restaurant reservations via payment tools — kleffew94 · 2026-08-20
- mixedbread adds streaming to agentic search with visible intermediate steps — bclavie · 2026-08-20
- Mixedbread AI Launches Streaming for Agentic Search — cixliv · 2026-08-20