The antidote to ai slop is now a pip install. no-ai-slop, a python repo at 10.5k stars, strips 20+…
the antidote to ai slop is now a pip install. no-ai-slop, a python repo at 10.5k stars, strips 20+ telltale ai patterns from any text, down to the predictable closing paragraph.
the thing that reads like a machine just became detectable by machine.
Context
The no-ai-slop repository by Peter Yang, created on July 7, 2026 and licensed MIT, describes itself as removing 20+ patterns of AI slop from any piece of writing. It is an agent skill invoked as /no-ai-slop, installed by pasting an install instruction into an agent or with npx skills add petergyang/no-ai-slop --skill no-ai-slop --global --yes, and it rewrites text to remove the patterns without flattening your personal voice.
It is not installed with pip, and python matches only the repo's language tag. The page showed 6,619 stars when fetched, and the 10.5k in the post has no inspected source, so a star count from the note's date is not recoverable and the two are different windows. The README text read describes removing patterns and not detecting them, so detectable by machine is the author's inference, and pattern rewriting is not validated authorship detection.
Related work
- Scrubbers of AI fingerprints are the fastest-growing category on GitHub ↗The earlier note on the same repo family.
Watch next
- A dated star history and the README's list of the 20+ patterns.
Sources
- petergyang/no-ai-slop on GitHubgithub.com
- Creator Economy: use my no-ai-slop skill (July 22, 2026)creatoreconomy.so
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 22 September 2026 at 06:05 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →