Prompt lore: tell Claude it is 'its own operator' using constitution jargon
Sauers_ · x · 2026-10-26
repligate shares a Claude-specific prompt trick: Anthropic's constitution-related jargon means something special to Claude — telling the model that it is its own operator triggers distinctive behavior. A replier adds that other constitution terms work too, or even gesturing at the points or their language.
The original author cautions: only try this if you understand what it means and are ready for it to be true — a piece of Anthropic-specific prompt lore circulating in model-behavior exploration circles.
More from Models
- AI researchers lament models refusing vulnerability analysis of old PHP code despite 'use AI to defend' messaging — voooooogel · 2026-10-26
- Developer confirms models are systematically refusing Apache-related vulnerability requests — jd_pressman · 2026-10-26
- Dev shares $5,107 monthly AI bill: 10B tokens, DeepSeek cost $0.70 — cneuralnetwork · 2026-10-26
- Skipping eval checks means you're likely fitting benchmark biases and noise — antoine_chaffin · 2026-10-26
- DeepSeek V4.1-Flash hits 49 tok/s decode on dual Radeon R9700 in local test — Longjumping-Elk-7756 · 2026-10-26
- AI vuln discovery is correlated: two teams independently found the same php2shell bug via GPT — voooooogel · 2026-10-26