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.
More from coding & agent
- How Comet improved a financial incident remediation agent's score from 0.34 to 0.57 with Opik — dl_weekly · 2026-11-17
- Jason Weston: Harness Optimization Hits 56.0, Distillation Adds 5.5 More — jaseweston · 2026-11-17
- Meta's Self-Improving Memory: agents discover their own memory skills and distill them into weights — jaseweston · 2026-11-17
- Every shows Claude Fable 5.2 building interactive games — slow but token-hungry — every · 2026-11-17
- Two free Wan2.1 ComfyUI workflow sets: native nodes vs Kijai wrapper with speed boosts — asdfghmfker · 2026-11-17
- Will Brown essay: strongest model may be the wrong teacher — SFT, RL and on-policy distillation — heghbalz · 2026-11-17