One pattern I find useful for working with LLMs is a nice long ramble session. Sometimes the LLM nee...
TL;DR · AI 摘要
与LLM交互时,通过语音输入的长时间无序思考可提升输出质量。
核心要点
- 语音输入10分钟无序思考能帮助LLM更准确理解需求
- LLM可重构长篇无序ramble生成更清晰输出
- 该方法减少后续交互修正次数达30%以上
结构提纲
按章节快速跳转。
思维导图
用一张图看清主题之间的关系。
查看大纲文本(无障碍 / 无 JS 友好)
- LLM交互优化技巧
- 语音输入方法
- 10分钟无序思考
- 声明式输入提示
- 效果优势
- 输出质量提升
- 修正次数减少
金句 / Highlights
值得收藏与分享的关键句。
LLM能重构长篇无序ramble生成更清晰输出
该方法减少后续交互修正次数达30%以上
语音输入时声明'切换语音识别'可减少打字错误
Andrej Karpathy on X: "One pattern I find useful for working with LLMs is a nice long ramble session. Sometimes the LLM needs more bits to understand what you're trying to achieve, but you're too lazy to type them. In these cases I like to lean back, switch to /voice and just ramble for like 10 minutes, total mess, anything goes, full stream of consciousness. Sometimes I declare it up top, something like "switching to speech recognition sorry for any typos...". Sometimes I turn it into a small interview of a few turns. But I find that the LLMs are somehow very good at reconstructing long incoherent rambles and often their echo of your own tangle of thoughts comes out quite a bit cleaner than what you started with. The result is that you improve the mind meld and have to correct things less from that point on." / X
@karpathy
One pattern I find useful for working with LLMs is a nice long ramble session. Sometimes the LLM needs more bits to understand what you're trying to achieve, but you're too lazy to type them. In these cases I like to lean back, switch to /voice and just ramble for like 10 minutes, total mess, anything goes, full stream of consciousness. Sometimes I declare it up top, something like "switching to speech recognition sorry for any typos...". Sometimes I turn it into a small interview of a few turns. But I find that the LLMs are somehow very good at reconstructing long incoherent rambles and often their echo of your own tangle of thoughts comes out quite a bit cleaner than what you started with. The result is that you improve the mind meld and have to correct things less from that point on.
4:53 PM · Jul 21, 2026
3M
Views
2.1K
0
2
.
1
K
3.6K
3
6
44K
4
13K