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 to Harness Coding Agents with the Right Infrastructure | Blogalexlavaee.me
- Best practices for Claude Code - Claude Code Docsanthropic.com
- How Claude Code is built - by Gergely Orosznewsletter.pragmaticengineer.com
- Harness design for long-running application developmentanthropic.com
- Building Effective AI Agents \ Anthropicanthropic.com
- Scaling Managed Agents: Decoupling the brain from the hands \ Anthropicanthropic.com
- How we built our multi-agent research system \ Anthropicanthropic.com
- Claude’s Constitution \ Anthropicanthropic.com
- Building Effective AI Agents \ Anthropicanthropic.com
- Towards self-driving codebases · Cursorcursor.com