LangChain Open SWE 按任务自动选模型,单任务成本降 64%
agree - most orchestration steps don't need a frontier model for Open SWE we moved model choice int...
LangChain 把 Open SWE 改成按任务自动挑最便宜够用的模型,成本直接砍掉 64%,还能看看 DeepSeek v4.1 flash 当编排器的实际体验。
LangChain 团队给 Open SWE 做了改造,把模型选择放进 harness,让每个任务自动路由到能通过质量测试的最便宜模型,单任务中位成本下降 64%。用户 @yuhasbeentaken 分享了 DeepSeek v4.1 flash 的用法:它可以承担编排、测试、研究、子智能体协调等多数工作。计划清晰后的重复性实现和代码变更审查、运行检查也能交给它,只有更难的边缘场景才用 Opus 或 Sol 处理。
agree - most orchestration steps don't need a frontier model for Open SWE we moved model choice int...
agree - most orchestration steps don't need a frontier model for Open SWE we moved model choice into the harness, so each task goes to the cheapest model that still does the job, tested against quality. median cost per task dropped 64% langchain.com/blog/how-to-bu… x.com/yuhasbeentaken… Yum⋆₊˚ @yuhasbeentaken the more i use deepseek v4.1 flash, the harder it is to justify using a frontier model for everything. a few more things i’ve noticed: 1. it’s insanely good as an orchestrator. i can let it coordinate coding tasks, testing, research, and subagents without burning frontier-model money. 2. once the plan is clear, it handles repetitive implementation work extremely well. 3. i’ve started using it for verification too: reviewing code changes, running checks, and catching obvious mistakes is cheap enough to do constantly. i still bring in opus or sol for harder edge cases... but deepseek is doing more and more of the actual work. 🔗 View Quoted Tweet 💬 4 🔄 0 ❤️ 7 👀 945 📊 3 ⚡