Karpathy's Voice Rambling Tip Echoed: Devs Stress Clear Thought Process for LLMs
gethackteam · x · 2026-07-22
A developer replied to Andrej Karpathy, reflecting on their own experience: failing to explicitly outline their thought process to LLMs usually results in outputs that miss the mark. While occasionally better, it's mostly worse than imagined.
This echoes Karpathy's shared tip for working with LLMs: when you're too lazy to type but need to provide context, switch to voice mode and ramble for about 10 minutes in a full stream of consciousness, giving the model the bits it needs to understand your goal.
Related event: Karpathy Recommends 10-Minute Voice Rambling for LLM Context(17 posts)→
More from coding & agent
- Two real 'company brains' opened up live: Gorgias' in-house Cortex vs Slite — femke_plantinga · 2026-09-11
- The browser main thread is expensive: a practical guide to JavaScript and CSS animation cost — jh3yy · 2026-09-11
- Claude Unlimited: open-source local proxy rotates accounts and API keys to keep Claude Code sessions alive — Similar_Injury_6739 · 2026-09-11
- Inspired by OpenAI's 10,000-agent run, dev open-sources a crowdsourced agent problem-solving platform — Benjaminsen · 2026-09-11
- Lucid: open-source Mac app keeps your laptop awake only while AI agents run — Pitiful_Hedgehog_600 · 2026-09-11
- banteg's snail project crowdsources AI agents to finish matching Snail Mail's 20 remaining functions — banteg · 2026-09-11