Software factories are wrong: property-based testing beats agent orchestration for correctness
blaizedsouza · x · 2026-09-20
Dominik Tornow sparked a discussion arguing that the current "software factory" thinking is wrong: correctness cannot come from orchestration — better workflows, better skills, better instructions, or more agents checking more agents won't work, because "a heuristic cannot certify the result of a heuristic."
He calls property-based testing the highest-leverage skill in software right now: establishing invariants and property assertions is what can actually certify AI-generated code, offering a counterintuitive alternative to the multi-agent-verification trend.
More from coding & agent
- SemiAnalysis: Persistent agents now eat 45% of our AI spend, and Perplexity's harness beats Claude Tags — dylan522p · 2026-11-12
- Ora's Ranker 3.0 grades whether agents can actually use your site; scores drop 40+ points — yenkel · 2026-11-12
- Gemini API Managed Agents now support self-hosted sandboxes, incl. Vercel — steren · 2026-11-12
- Rayline launches ARC, a per-turn model router claiming 90% cost cuts — testingcatalog · 2026-11-12
- Karpathy's llm-wiki: a pattern for building personal knowledge bases with LLM agents — stochasticchasm · 2026-11-12
- Agent self-improvement with frozen weights: failure traces add just 4pp, blind search gets 60% — burny_tech · 2026-11-12