{"slug": "corpus-linguistics-tool-measures-ai-generated-prose-quality-against-linguistic", "title": "Corpus linguistics tool measures AI-generated prose quality against linguistic standards", "summary": "A Show HN post with 16 upvotes introduced deslop, a Claude skill that revises drafts to strip fingerprints of LLM-generated prose using rules drawn from corpus linguistics and psycholinguistics research comparing human and model text. The tool was validated against three public corpora in which humans and models answered identical prompts, and it targets enterprise governance needs for objective prose quality metrics beyond subjective review by detecting and removing recurring LLM artifacts such as specific phrase patterns and discourse structures.", "body_md": "# Corpus linguistics tool measures AI-generated prose quality against linguistic standards\n\nAccording to a Show HN post (16 upvotes), deslop is a Claude skill that revises drafts to remove fingerprints of LLM-generated prose using rules derived from corpus linguistics and psycholinguistics research comparing human and model text, validated against three public corpora where humans and models answered identical prompts. The tool addresses enterprise governance needs for objective prose quality metrics beyond subjective review. Deslop detects and removes recurring LLM artifacts such as specific phrase patterns and discourse structures.\n\n## Topics\n\n## Sources\n\n- Official[Read article](https://github.com/etodanik/deslop)\n\n## Go deeper\n\nThis intelligence is sourced automatically from public sources across the web and synthesised by the Prefactor AI pipeline. Stories are reviewed before publication.", "url": "https://wpnews.pro/news/corpus-linguistics-tool-measures-ai-generated-prose-quality-against-linguistic", "canonical_source": "https://www.getreadyforagents.com/news/deslop-ai-prose-quality-measurement-tool/", "published_at": "2026-11-17 19:07:25+00:00", "updated_at": "2026-11-17 20:29:35.583696+00:00", "lang": "en", "topics": ["ai-tools", "large-language-models", "natural-language-processing", "generative-ai"], "entities": ["deslop", "Claude", "Show HN", "GitHub", "Prefactor AI"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/corpus-linguistics-tool-measures-ai-generated-prose-quality-against-linguistic", "markdown": "https://wpnews.pro/news/corpus-linguistics-tool-measures-ai-generated-prose-quality-against-linguistic.md", "text": "https://wpnews.pro/news/corpus-linguistics-tool-measures-ai-generated-prose-quality-against-linguistic.txt", "jsonld": "https://wpnews.pro/news/corpus-linguistics-tool-measures-ai-generated-prose-quality-against-linguistic.jsonld"}}