有人把语音、屏幕和文字打包成一个任务喂给智能体，纠正循环几乎消失，试试这个思路。
Karpathy提出长语音漫谈在多模态下效果更佳。用户分享了一种将长语音笔记、当前屏幕、注释和精确文本打包成单个“task”单元的提示方式。智能体从多个信号中重建意图，大幅减少纠正循环，从而高效交接更大块的工作。该方法适合需要复杂上下文理解的智能体交互场景。
Karpathy's point about long voice rambles goes further when you add more modalities. My favorite ...
Karpathy's point about long voice rambles goes further when you add more modalities. My favorite way to prompt agents lately is a bigger unit I've been calling a task. A task bundles a long voice note, the current screen, annotations, and exact text into a single turn. The agent reconstructs my intent from all of those signals, so most of the correction loops disappear and I can hand off larger pieces of work. elvis @omarsar0 x.com/i/article/2079… 🔗 View Quoted Tweet 💬 7 🔄 2 ❤️ 19 👀 3374 📊 9 ⚡