Karpathy Shares LLM Workflow Tip: Use Voice for Long Context Rambling
var_epsilon · x · 2026-07-22
Andrej Karpathi highlights a practical pattern for working with LLMs: when the model needs more context but you're too lazy to type, switch to voice mode and just ramble.
By streaming consciousness for about 10 minutes, users can efficiently provide the necessary bits for the LLM to fully grasp their goals.
Related event: Karpathy Recommends 10-Minute Voice Rambling for LLM Context(17 posts)→
More from Apps
- Rork streamlines app screenshot localization across 10+ languages — rudrank · 2026-10-27
- HeyGen + Canva MCP turns slide speaker notes into an avatar presentation video — HeyGen · 2026-10-27
- Google Docs and Drive now natively preview, edit, and collaborate on .md files — rseroter · 2026-10-27
- Krea ships Premiere Pro plugin to generate video and SFX inside the timeline — lmoroney · 2026-10-27
- Meta Testing Live Avatar for Muse on Desktop, Companion Window Leaked — testingcatalog · 2026-10-27
- Paradigm Launches Envoys: Your Claude Code and Codex on Your Research Graph, Free — tensorqt · 2026-10-27