Simon Willison • 1/19/2026

Scaling long-running autonomous coding

Read Original

The article details an experiment by Cursor using hundreds of concurrent autonomous coding agents to build a web browser from scratch. The agents, coordinated by planners and judges, wrote over a million lines of code. It discusses the results, initial skepticism, and how the project compares to predictions about AI's role in complex software development.

0 comments
#software development #autonomous agents #ai coding
Scaling long-running autonomous coding

Comments

No comments yet

Be the first to share your thoughts!

Browser Extension

Get instant access to AllDevBlogs from your browser

Top of the Week

1
Quoting Thariq Shihipar
Simon Willison • 2 votes
2
Top picks — 2026 January
Paweł Grzybek • 1 votes
3
In Praise of –dry-run
Henrik Warne • 1 votes
4
Deep Learning is Powerful Because It Makes Hard Things Easy - Reflections 10 Years On
Ferenc Huszár • 1 votes
5
Vibe coding your first iOS app
William Denniss • 1 votes
6
AGI, ASI, A*I – Do we have all we need to get there?
John D. Cook • 1 votes
7
Dew Drop – January 15, 2026 (#4583)
Alvin Ashcraft • 1 votes