Building a C compiler with a team of parallel Claudes \ Anthropic
anthropic.com · 2,442 words · saved by 1 readers
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
Written by Nicholas Carlini, a researcher on our Safeguards team. I've been experimenting with a new approach to supervising language models that we’re calling "agent teams." With agent teams, multiple Claude instances work in parallel on a shared codebase without active human intervention. This approach dramatically expands the scope of what's achievable with LLM agents. To stress test it, I tasked 16 agents with writing a Rust-based C compiler, from scratch, capable of compiling the Linux kernel. Over nearly 2,000 Claude Code sessions and $20,000 in API costs, the agent team produced a 100,0
related reading
- Effective harnesses for long-running agents \ Anthropicanthropic.com
- When AI builds itself \ Anthropicanthropic.com
- How I Use Claude Code | Philipp Spiessspiess.dev
- A Guide to Claude Code 2.0 and getting better at using coding agents – sankalp's blogsankalp.bearblog.dev
- How Claude Code is built - by Gergely Orosznewsletter.pragmaticengineer.com
- Best practices for Claude Code - Claude Code Docsanthropic.com
- Don’t Outsource Your Thinkingteltam.github.io
- Harness design for long-running application developmentanthropic.com
- Claude’s Constitution \ Anthropicanthropic.com
- An update on recent Claude Code quality reports \ Anthropicanthropic.com
- How Anthropic teams use Claude Code | Claudeanthropic.com
- How I use Claude Code on large projectslocalcan.com