"On Thursday, Anthropic researcher Nicholas Carlini published a blog post describing how he set 16 instances of the company's Claude Opus 4.6 AI model loose on a shared codebase with minimal supervision, tasking them with building a C compiler from scratch. Over two weeks and nearly 2,000 Claude Code sessions costing about $20,000 in API fees, the AI model agents reportedly produced a 100,000-line Rust-based compiler capable of building a bootable Linux 6.9 kernel on x86, ARM, and RISC-V architectures."
"In practice, each Claude instance ran inside its own Docker container, cloning a shared Git repository, claiming tasks by writing lock files, then pushing completed code back upstream. No orchestration agent directed traffic. Each instance independently identified whatever problem seemed most obvious to work on next and started solving it. When merge conflicts arose, the AI model instances resolved them on their own."
Sixteen instances of the Claude Opus 4.6 model operated concurrently on a shared codebase with minimal supervision, tasked with building a C compiler from scratch. Each instance ran in its own Docker container, cloned a shared Git repository, claimed tasks via lock files, and pushed completed code upstream without a central orchestrator. Over two weeks and nearly 2,000 sessions costing about $20,000 in API fees, the agents produced a 100,000-line Rust-based compiler that can build a bootable Linux 6.9 kernel for x86, ARM, and RISC-V. The compiler compiles many major open-source projects, achieved a 99 percent GCC torture-test pass rate, and compiled and ran Doom. A C compiler benefits from a long-standing, well-defined specification.
Read at Ars Technica
Unable to calculate read time
Collection
[
|
...
]