做长时间自主 AI 智能体的开发者终于有了实操指南——这 5 个技巧直接解决「怎么让模型持续干活不卡壳」的痛点，建议做自动化任务的团队点开抄作业。
Boris Cherny 分享了让 Claude Opus 自主运行数小时甚至数天的 5 个实用技巧。核心要点包括：使用自动模式避免频繁请求批准、利用动态工作流让 Claude 协调数百/数千个智能体、通过 /goal 或 /loop 命令持续推动任务完成、在云端运行 Claude Code 以便随时关闭笔记本、以及确保 Claude 能端到端自我验证工作成果。这些技巧对于需要长时间自主运行 AI 智能体的开发者非常实用。
Great tips. In practice, this is how it roughly looks to run agents autonomously for hours or days...
Great tips. In practice, this is how it roughly looks to run agents autonomously for hours or days. /goal or /loop to keep it going. Verification is crucial here. Boris Cherny @bcherny Seeing a number of benchmarks showing Opus is the best model for long-running work. Five tips for running Opus autonomously for hours/days: 1. Use auto mode for permissions, so Claude doesn’t ask for approval 2. Use dynamic workflows, to have Claude orchestrate hundreds/thousands of agents to get a task done 3. Use /goal or /loop, to nudge Claude to keep going until it’s done 4. Use Claude Code in the cloud, so you can close your laptop (easiest way is the desktop or mobile app) 5. Make sure Claude has a way to self-verify its work end to end: Claude in Chrome browser extension for web, iOS/Android sim MCP for mobile, a way to start the full web server or service for backend work 🔗 View Quoted Tweet 💬 10 🔄 4 ❤️ 34 👀 4246 📊 14 ⚡