Stop Claude's Verbose Outputs with Simplified Technical English Prompt
DanielLockyer · x · 2026-08-08
To counter Claude's tendency to become increasingly verbose and unintelligible, developer levelsio found an effective prompting trick: instruct the model in memory to always use ASD-STE100 (Simplified Technical English). This successfully forces the model to stop rambling and communicate clearly and concisely.
Related event: ASD-STE100 Prompt Trick Tames Verbose Claude Outputs(2 posts)→
More from Apps
- DSCO Router Launches Unified Gateway for Multi-Model Routing with BYOK Support — arthurcolle · 2026-08-24
- Dev bottleneck shifts from writing to reading code: exe.dev co-founder — thursdai_pod · 2026-08-24
- WatchGPT app updated with OpenAI's latest real-time speech models — AIandDesign · 2026-08-24
- Tool requested: Krea2 PNG prompt reader for Windows — paruruwhyusosalty · 2026-08-24
- Users report ChatGPT erasing conversation history upon tab reload — Turbulent_Door_1012 · 2026-08-24
- MinMax H3 test: 98% PT-BR accuracy, 3:4 gen is faster — ramscheid · 2026-08-24