What it is
A Chrome extension that judges each LinkedIn post as it scrolls into view and stamps it BAIT, CORP, or BRAG with the confidence score, leaving the post readable underneath.
How it uses Jev
For each ambiguous post, two Noul questions and a Choice category run on the post text via a local proxy. Jev returns probabilities; the extension branches on is_slop >= 0.60 or is_corporate_slop >= 0.70 to apply a stamp.
Primitives:choicenoul
Technique worth stealing
Local keyword rules settle obvious cases before any API call, and verdicts are cached per post.
Try it
Clone, set .env, run server, load extension/ unpacked in Chrome, open LinkedIn feed.
Evidence
Each line is one question put to Jev about the README. ≥ 0.60 reads as yes, ≤ 0.40 as no; in between Jev is not making a call.
- Jev-centricyes0.96
- Shows a System One patternyes0.92
- Handles uncertaintyyes0.94
- Measuredno0.17
- Runnableyes0.98
- Worth recommendingunclear0.49
- Model replicano0.03
- Problem scopescore on a 0–2 scale0.96
- About Jevyes0.99
Signals by Jev jev-1.13.0, card written by DeepSeek V4.1 Flash from the README on 22 Sept 2026.