slop-filter

How it uses Jev

1. It reads the text of each post as it nears your screen. 2. It asks TypeSafe Jev 30 narrow questions about how the text is written, not what it says. Human tells come first: an invented word, a joke, a stretched or repeated word, a typo. A confident one settles it as human. Then the AI tells. A person can be generic or repeat the post they answer, and that is not AI. The tells are in the cadence: the "it's not X,…

Highlights

• Scores every post in your feed for how likely it is to be AI-written.
• Collapses the ones over your threshold. One click shows a post again.
• Animated mode lets you watch it work: a scan line runs over each post, then the post turns green and stays, or turns red and folds away.
• Can be tuned to your own judgment. Mark posts as AI or Human , then fit the weights from your labels.
• Blocks accounts. After three flagged posts from one account it offers to block it. A blocked account's posts are hidden on sight and never scored again. Hover any score for a Bloc…