Devin的7倍PR增长和80% AI提交率证明了异步智能体在工程中的实际价值，做AI编程工具或自动化工作流的开发者值得深入了解其背后的架构思路。
Cognition联合创始人兼CPO Walden Yan与Open-Inspect创始人Cole Murray在播客中讨论了工程从本地IDE向云端后台智能体迁移的趋势。Devin在Cognition仓库中的代码提交占比从16%增长到80%，PR数量增长7倍。他们解释了12月模型拐点后规格到PR工作流成为现实的原因，以及测试比计算机使用更难。还探讨了Devin如何分离大脑与机器、MCP在生产智能体集成中的不足，以及PM、支持团队和SRE如何将Slack消息转化为PR。
🆕The Age of Async Agents: Devin’s 7x PR growth, 80% AI commits, background agents, memory, testing,...
🆕The Age of Async Agents: Devin’s 7x PR growth, 80% AI commits, background agents, memory, testing, & Open-Inspect latent.space/p/cognition Y @cognition cofounder + CPO @walden_yan and Open-Inspect creator @_colemurray explain why engineering is moving from local IDEs to cloud background agents, how Devin went from 16% to 80% of commits across Cognition repos, why spec-to-PR workflows became real after the December model inflection, why testing is harder than computer use, how Devin separates the brain from the machine, why MCP is not enough for production agent integrations, and how PMs, support teams, and SRE workflows are starting to turn Slack messages into pull requests. Your browser does not support the video tag. 🔗 View on Twitter 💬 1 🔄 2 ❤️ 8 👀 1051 📊 4 ⚡