长时间运行 Agent 的开发者常被 Token 浪费困扰，Boris 的 5 条建议直击痛点，尤其是自验证机制能大幅提升效率，做自动化工作流的团队值得一试。
Boris Cherny 分享了使用 Claude Opus 进行长时间自主运行的 5 条建议，强调 Agent 自行验证工作成果是避免浪费 Token 的关键。建议包括使用自动模式、动态工作流、/goal 或 /loop 指令、云端运行以及端到端自验证机制。这些技巧能帮助开发者让 AI Agent 持续工作数小时甚至数天，而无需人工干预。
长时间运行 Agent，Agent 能自行验证才是关键，否则可能只是浪费 Token
长时间运行 Agent，Agent 能自行验证才是关键，否则可能只是浪费 Token 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 💬 0 🔄 0 ❤️ 0 👀 55 ⚡