Agentic AI's leap: from Sonnet 3.5's Factorio benchmark to today, 1.5 years later

john_lam · x · 2026-09-11

John Lamb looks back at his own tweet from 1.5 years ago, when Sonnet 3.5 completing tasks and building entire factories in Factorio emerged as a landmark agentic AI benchmark — and reflects on how far agent capabilities have come since.

Related event: John Lam Compares AI Agents' Factorio Progress Over 18 Months(2 posts)→

Original post →

More from coding & agent

coding & agent channel →