A 10-minute voice ramble can be a better prompt than a polished one
eyishazyer · x · 2026-07-22
A simple prompting habit: ramble for several minutes, especially via voice, to give the LLM more context than you would bother typing.
The author says this often works better than trying to craft the perfect prompt up front. He explicitly switches to /voice, talks for about 10 minutes in a stream-of-consciousness style, and lets the model sort through the mess to infer the goal.
Related event: Karpathy Recommends 10-Minute Voice Rambling for LLM Context(17 posts)→
More from Apps
- AI Is Tracking You to Set Personalized Prices — Use VPNs to Exploit Regional Pricing Gaps — DavidLinthicum · 2026-09-11
- Non-coder builds full-featured Android ComfyUI client with ChatGPT, submits to Google Play — ComfierUI · 2026-09-11
- Fully local voice assistant on an RTX 3060 replicates the GPT Live demo in 6.5 minutes — liampetti · 2026-09-11
- Amazon and Google sold 600M+ smart speakers, so why no AGI-era successor? — julianlehr · 2026-09-11
- Internet Archive indexed 4.43M TV broadcasts since 2009 — now you can full-text search what TV said — moonsandhues · 2026-09-11
- MiniMax Music Production Toolkit 2.5 for ComfyUI adds full mastering chain — Vivid_Promise1700 · 2026-09-11