Denny Zhou: Least-to-Most Prompting Was an Early Agent Harness, Hitting 99% on SCAN

denny_zhou · x · 2026-09-08

Google researcher Denny Zhou reframes his 2022 least-to-most prompting work in today's language: it was an early agent harness — decompose a complex task into smaller ones, then repeatedly call an LLM to solve them one by one ("Decompose. Solve. Repeat.").

Original post →

More from coding & agent

coding & agent channel →