Skip to content

Code Is Free

ryan-lopopolo's axiom (AI Engineer London 2026): once agents can produce, maintain, and refactor code at high quality, code stops being a scarce resource that must be rationed.

"Code is free. And I know this is maybe a scary thing to hear because code carries maintenance burden, but it's free to produce, free to refactor, and it is not a thing to get hung up on anymore. We think of code as burden because it's a synchronous attention drain on the human engineers on our team. But the models are incredibly patient. They are infinitely parallel."

Consequences Lopopolo draws

  1. Maintenance burden dissolves. Refactors, rewrites, and deletions are cheap. "Large scale refactoring in this world is free."
  2. Migrations finish. "There's no longer going to be a migration that hangs open for six months… you can just fire off 15 agents to drive that work to completion."
  3. P3s ship. Priority stack flattens — see harness-engineering.
  4. Internal tools get first-class localization, accessibility, i18n from day one "without really having to trade against any of my other teams capacity."

Tension / contested implications

  • Maintenance burden isn't just labor cost. Operationally more code means more surface area for bugs, security issues, and knowledge fragmentation — Lopopolo addresses this with non-functional-requirements-as-prompts and "systematic elimination of durable classes of failures" but doesn't dispute the surface-area point directly.
  • "Free" is a misnomer. The cost moves to token spend + review bandwidth + guardrail engineering. Lopopolo explicitly calls out "getting tokens to be spent in CI is a necessary part here" and describes short-term velocity hits to invest in guardrails.
  • Counterpoint from andrej-karpathy (adjacent): "you are still responsible for your software just as before, but can you go faster?" — agentic-engineering treats code quality as still-scarce, not code volume.