No Slop Manifesto tops 1,000 signatures: humans review the plan, design, result
annbordetsky · x · 2026-11-20
dexhorthy of Factory presented the "No Slop Manifesto" at the AI Engineer code summit, co-written with speakers and attendees. Core claim: "there will always be alpha in reviewing something" — as agents write more code, humans should review the plan, the design, and the result, with review depth proportional to the stakes.
The manifesto has gathered over 1,000 signatures, including internet pioneers (BIND/DNS contributors), distinguished engineers at major cloud providers, long-time Rust compiler maintainers, software engineering professors at Purdue, Berkeley and Stanford, and employees of OpenAI, Glean, PostHog, Baseten and more. Read and sign at slopmanifesto dot com.
More from coding & agent
- ARTEX, built by a university student, tames autonomous security-testing agents with dual-graph stateful design — cyb3rops · 2026-11-20
- Vork: open-source headless 3D and VFX engine built for AI agents — ravisparikh · 2026-11-20
- Victor Eijkhout's free Parallel Programming textbook now online with AI tutor — burkov · 2026-11-20
- OrcaRouter launches Shield: AI-native defense that deceives offensive agents with decoys — cyb3rops · 2026-11-20
- The 6-folder second brain: a schema doc so Claude stops re-learning your business — evielync · 2026-11-20
- An "AI truth economy" proposal: hash-chained, user-owned logs for every agent action — Educational_South_20 · 2026-11-20