想优化系统提示？这篇告诉你为啥越短越好，还讲了Pi和Claude Code的真实案例。
博主分享经验，指出新模型（如Claude）在理解意图和使用工具方面显著提升，因此系统提示应尽量精简。Pi率先采用了极简系统提示理念，Claude Code通过减少80%系统提示内容获得更好效果。作者建议避免干扰模型能力，提供简洁工具和丰富上下文。目前评估和验证结果是一大挑战，用HTML工件可加速流程。
Recommended reading. But none of it is surprising or new. Newer models got better at understanding...
Recommended reading. But none of it is surprising or new. Newer models got better at understanding intent and using tools. The system prompt should store minimal text with your preferences that informs, not replace, model capabilities. This is why, if you use newer models in harnesses like Pi, the experience has improved significantly. Pi pioneered the idea of a minimal system prompt. Overall, the principle to follow is to avoid getting in the way of the model while ensuring it has the right tools and guardrails/access. In practice, keep your tools and skills simple and provide models with richer context (and different modalities where you can afford it and it helps). The biggest challenge I am facing now is evaluation and verifying results. HTML artifacts are brilliant for this and allow me to move faster. But there are new ways I am using to improve the process. Write-up coming soon. Thariq @trq212 We removed ~80% of the Claude Code system prompt for our newest models, this is what we've learned about writing system prompts, skills and Claude.MDs for them. x.com/i/article/2080… 🔗 View Quoted Tweet 💬 2 🔄 1 ❤️ 6 👀 1409 📊 3 ⚡