AI-slop / de-slopping
The recognizable stylistic tells of unedited LLM prose (em-dashes, the 'it isn't A, it's B' antithesis closer, guru cadence) and the mechanical/prompt-level passes that strip them so generated content reads as genuinely human-authored.
grounded in: Recent commits 47bc298 'ban em-dashes entirely (prompt + mechanical strip)', ecc99cf 'ban the it-isn't-A-it's-B antithesis closer (top AI tell) in de-slop pass', 6af639d 'builder-not-guru voice, expan
Connected concepts
Hallucination control, Social distribution, Grounding & fact-checking, Guardrails / bounded autonomy
Explore it live in the knowledge graph →