Building recursive agent systems
x.com · 394 words · saved by 1 readers
https://t.co/6nWAu8JVdw
At Cursor, we run thousands of agents to help us train the next version of Composer. We give them research tasks, and if they aren't succeeding or run into issues, they DM us on Slack or page us via PagerDuty. Scaling training for Composer We’ve built an org chart of agents that work together. As we’ve scaled training for Composer, we’ve wanted to run thousands more experiments. This was possible before, but it was slow and hard to keep track of every experiment’s status. To speed things up and parallelize work, we built an always-running agent system (yes, it's a loop). An agent system…
saved by
related reading
- Scaling long-running autonomous coding · Cursorcursor.com
- Towards self-driving codebases · Cursorcursor.com
- Improving Composer through real-time RL · Cursorcursor.com
- Composer2.pdfcursor.com
- How we built our multi-agent research system \ Anthropicanthropic.com
- Training Composer for longer horizons · Cursorcursor.com
- Agent swarms and the new model economics · Cursorcursor.com
- What we’ve learned building cloud agents · Cursorcursor.com
- Building Effective AI Agents \ Anthropicanthropic.com
- Coding Agents & Complexity Budgets | Lee Robinsonleerob.com
- GitHub - karpathy/autoresearch: AI agents running research on single-GPU nanochat training automaticallygithub.com
- A basic systems architecture for AI agents that do autonomous research — LessWronglesswrong.com