Cursor团队实战分享：如何搭配不同模型，用最小成本完成高难度编程任务，成本能差15倍。
Cursor团队使用多个AI代理从835页手册重建SQLite的Rust版本，通过100%测试集。成本因模型组合不同而相差15倍。实践建议：用前沿模型做分解和架构设计，用便宜模型执行具体实现。注意代理协调中的偏差和失败。
Recommended reading. (bookmark it) Pay attention to the prices and what a combination of models c...
Recommended reading. (bookmark it) Pay attention to the prices and what a combination of models can unlock for you. You don't need the absolute best model for everything. I am not that impressed with the Rust SQLite replica. A totally new and improved SQLite (or something more creative and new) could be a more interesting test. Takeaways: - Use a frontier model for decomposition, architecture, key design choices, and trade-offs. - Have cheaper, faster workers execute well-defined, narrow implementation tasks. - Do not have planners implement or workers make broad design decisions. Use a swarm or harness with a recursive task tree: planners break the original spec into subtrees, delegate them, and workers operate at the leaves. Cursor argues this helps mostly because each agent has a constrained context, rather than simply because many agents run in parallel. Pay extra attention to biases and failures that might emerge from poor/inefficient agent coordination. Cursor @cursor_ai We had a team of agents rebuild SQLite from its 835-page manual. It created a replica in Rust which passed 100% of a held-out test suite. Interestingly, cost varied 15x depending on which model mix we used. 🔗 View Quoted Tweet 💬 5 🔄 2 ❤️ 11 👀 2113 📊 6 ⚡