Multi-Agent Systems: When They Pay Off and How to Build the Harness Around Them
October 10, 2026
In February 2026, Nicholas Carlini, a researcher at Anthropic, described an experiment. He left sixteen copies of Claude to write a C compiler in Rust. Each copy ran in its own container, in a loop that started the next task as soon as the last one finished. The agents claimed work by committing a lock file to a shared git repository. They merged each other’s changes as they went, and no manager agent told them what to do. Over two weeks and nearly 2,000 sessions, they produced a 100,000-line compiler that builds the Linux kernel. The API bill was just under $20,000.1
-
Carlini’s post reports 2 billion input tokens and 140 million output tokens on Opus 4.6. The compiler passes most of the test suites he tried, but he is candid that its output is less efficient than GCC with optimizations disabled. These costs and results come from one researcher’s experiment, not a representative sample of projects. ↩
