Uncle Bob Says He No Longer Reads Every Line of Code Written by Agents
jameslk · hn · 2026-07-24
Uncle Bob says he no longer reads all the code his agents write
Uncle Bob Martin says his current strategy is not to read every line of code produced by his coding agents.
The comment highlights a growing shift in how experienced developers think about AI-generated code: the bottleneck is moving from writing code to supervising, validating, and constraining agent output. It also raises the practical question of how much of an agent’s work a human can safely trust without review.
More from coding & agent
- Agent verified 'success' after double-voting: a lesson in harness vs model bugs — TejasKumar_ · 2026-10-26
- diginomica: agentic automation hype is overdone, and 'The Hackening' of enterprise security has begun — jonerp · 2026-10-26
- 'Vibe verification': ~60% of AI-written formal specs prove the wrong property — basedjensen · 2026-10-26
- Devin launches Security suite powered by Claude Mythos with $100M+ credits — DevinAI · 2026-10-26
- HackBench injects reward hacks into agent trajectories to stress-test monitors — DanielKhashabi · 2026-10-26
- Hugging Face ships hf CLI updates: deduped cache saves 19GB, faster buckets, retryable GPU jobs — yb2698 · 2026-10-26