Peter Yang's 10/80/10 rule: the last 10% of manual work separates AI slop from quality
petergyang · x · 2026-10-01
Peter Yang shares his "10/80/10 rule" for AI workflows: run a skill to kick things off (first 10%), let AI do the middle 80%, then spend the final 10% on manual feedback and tweaks.
Writing a newsletter, he runs the skill first, gives feedback, and AI handles 80% of the work. He's skeptical of "fully end-to-end automation" claims, arguing that what separates slop from genuinely good output is the human time spent on that last 10%.
More from coding & agent
- Incident Arena benchmark puts coding agents on call for incident response — amankhan · 2026-10-01
- Google: Gemini 4 Argon agents migrate 800k+ lines of C/C++ to Rust, free 300 TiB — xennygrimmato_ · 2026-10-01
- OpenAI's CUA leads on new agent stack: superhuman computer use, Dots cloud computers, Decisions API — OpenAIDevs · 2026-10-01
- AI coding agents use fast WASM sims as oracles to port game code — gandamu_ml · 2026-10-01
- RLTL;DR paper: self-generated feedback breaks Pass@128=0 barrier to 14-31% Pass@1 — burny_tech · 2026-10-01
- Dev claims 'Sonnet 5.5' hits 120-130tps with 100% pass rate on his end-to-end app benchmark — julianharris · 2026-10-01