Keeping filler words in prompts encodes real uncertainty and nails it in one shot

brandon_galang · x · 2026-11-17

brandongalang argues this is "peak prompting performance": leave the filler words and hesitation in your prompt. In his view they don't distract the model — they encode your genuine uncertainty while thinking, providing helpful context. The quoted post shows the prompt achieved the desired result in a single one-shot generation.

Original post →

More from coding & agent

coding & agent channel →