Cursor's recent experiment involved running hundreds of AI agents for nearly a week to build a web browser, writing 1M+ lines of code across 1,000 files (Simon Willison/Simon Willison's Weblog)

Simon Willison / Simon Willison's Weblog: Cursor's recent experiment involved running hundreds of AI agents for nearly a week to build a web browser, writing 1M+ lines of code across 1,000 files  —  Scaling long-running autonomous coding.  Wilson Lin at Cursor has been doing some experiments to see how far you can push a large fleet of “autonomous” coding agents: