Chrome extension that hides X / Twitter replies matching a natural-language condition, judged by TypeSafe Jev.
Stars measure the whole repository, including work unrelated to Jev.
Documented records the linked documentation or source. JevHunt has not independently run or benchmarked this project.
- Uses the Noul probability from `jev-latest` and hides a reply only when it reaches the threshold. The default of 0.85 is a starting point that has not been calibrated on a dataset; the model can be wrong. Jev's accuracy is currently best in English, so test your own content if you filter other languages.
Evidence commit: 1f78624c00a7fedb2bbd2e982e72e16d4679a24f
Discovered through: github-search.
How we review →