Cognition 搞了个 Devin Fusion，把两个模型搭配起来干活，编程智能体成本降了35%，用着还挺顺。
Cognition 推出 Devin Fusion，一种用于智能体编程的混合模型架构。其中副手模型负责检索信息和浏览来源，前沿模型制定实施计划并委派子任务。测试显示，该架构将 Fable 级别智能的推理成本降低35%，同时保持良好使用体验。相比传统模型路由，它虽通过基准测试，但实际代码合并率更高。
Watch Devin Fusion work: The sidekick model handles fetching information and skimming sources. The...
Watch Devin Fusion work: The sidekick model handles fetching information and skimming sources. The frontier model makes a plan for implementation, then delegates well-scoped sub-tasks to the sidekick with its own cached context. Your browser does not support the video tag. 🔗 View on Twitter Cognition @cognition Conventional model routing sucks. It passes benchmarks but fails to write code you'd actually merge. Introducing Devin Fusion, a new hybrid-model harness for agentic coding. In testing, it reduces the cost of Fable-level intelligence by 35% and still feels good to use. 🔗 View Quoted Tweet 💬 7 🔄 9 ❤️ 78 👀 10254 📊 15 ⚡