Karpathy: Long Voice Conversations with LLMs Can Improve Comprehension Efficiency
Original title:One pattern I find useful for working with LLMs is a nice long ramble session. Sometimes the LLM nee...
AI summary
Andrej Karpathy shared an effective mode of collaborating with LLMs: turn on voice input and ramble freely for about 10 minutes, even if the content is messy and stream-of-consciousness. He found that LLMs are good at reconstructing intent from long, incoherent speech, and their responses are often clearer than the user's initial thinking, reducing subsequent corrections and improving human-AI alignment efficiency.
Key Takeaways
- Andrej Karpathy shared an effective mode of collaborating with LLMs: turn on voice input and…
- He found that LLMs are good at reconstructing intent from long,incoherent speech,and their…
- reducing subsequent corrections and improving human-AI alignment efficiency.
Quick Facts
- Published
- Updated
- Category
- Tutorials & Tips
- AI score
- 78
Karpathy 这条语音输入 ramble 技巧,比精心写 prompt 更符合人性,读完后你也会想试试。
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: Karpathy: Long Voice Conversations with LLMs Can Improve Comprehension Efficiency. July 22, 2026. https://new.nat6.net/en/news/cmrux929g005abinv7sbkrf3l/