Dev drops AI code arbitration: models are just better at writing code now
Sauers_ · x · 2026-09-05
In a thread with thkostolansky, developer Sauers explains why he no longer uses an 'arbitrator' model to check AI-generated code: models are simply good enough at writing code, making arbitration not worth it. He still does manual review when safety matters, just less often — batching multiple changes into one review pass.
Related event: Developer Drops Model Arbitration as AI Code Gets Good Enough(3 posts)→
More from coding & agent
- Grady Booch revives Weinberg's 1971 quip: software so buggy one woodpecker could destroy civilization — Grady_Booch · 2026-10-23
- One Agent Replaces Half an SDR Team: Full Lead-Research-to-Email Workflow — tibo_maker · 2026-10-23
- Why don't coding agent harnesses ship with their own sandbox? Only amp does — Aryvyo · 2026-10-23
- Dev builds a VST synth with Codex and MCP, lets the AI jam in his studio — Yamapama · 2026-10-23
- AgentsInTheCloud update: use your Claude subscription with built-in coding agents — lucasmeijer · 2026-10-23
- Phone agents vs. secure screens: banking apps treat helpful agents like malware — ghostmalone02 · 2026-10-23