Same draft, 4 AI-slop humanizer skills: they work at different levels and undo each other
bibryam · x · 2026-09-13
Bilgin Ibryam ran the same draft through 4 popular no-slop/humanizer skills and got four very different outputs. His takeaway: they don't compete — they operate at different altitudes. clarity reads the whole piece, no-ai-slop reads paragraphs, humanizer and stop-slop read sentences. Pick one or two at most; stacking means each undoes the last one's edits. Addy Osmani's clarity stood out: 15 passages, only -10 words, and the only skill that diagnosed the piece first — spotting that all 7 sections closed on the same cadence ("X is mature, but Y remains Z"), which none of the others caught. A full side-by-side breakdown is coming to his Substack, The Generative Programmer.
More from coding & agent
- Mac MCP: open-source MCP server turns ordinary ChatGPT chats into a macOS control plane — bulutarkan · 2026-09-13
- Developer hands his trivia site to a Grok bot that ships new content and SEO fixes daily — santiviquez · 2026-09-13
- Manus agent builds a sourced 10-tool comparison deck from a single prompt in under 20 minutes — Aiden_Tech_Ai · 2026-09-13
- Dev builds px0, a read-only IDE that boots in 1ms and idles at 16MB vs VS Code's 1.4GB — arpit_bhayani · 2026-09-13
- OpenAI hosts GPT-6 Astra hackathon; attendees say GPT-Live-1 blew their minds — gabrielchua · 2026-09-13
- Ex-Microsoft exec: AI coding agents cut my setup from 3 monitors to 1 laptop — MParakhin · 2026-09-13