CommunityJev Demos & Experiments
Jev Detector
A no-login page that scores pasted prose sentence by sentence with Jev, using a 0–4 style rubric, and highlights only the sentences that cross its threshold.
- Format
- Playground
- Published by
- Community
- Last verified
- Sep 2026
- Platforms
- Browser
- Capabilities
- Requires API key
Highlights
- Paste up to 10,000 words. The server keeps each sentence's position and sends bounded batches to Jev.
- Each batch asks for a 0–4 style score and the strongest signal from a Wikipedia-derived rubric.
- Only sentences over the site's evidence threshold are highlighted, with category, score, and matched wording.
- The score is a style index, not an authorship probability. A sample and an in-place editor are on the page.
Watch out
On 28 September 2026 the page said scanning was temporarily unavailable pending Jev configuration. Text is sent to this site and TypeSafe. Do not paste confidential writing.
Questions about this entry
Short answers drawn from the linked project or page.
No. The page states that text is processed by the site and by TypeSafe, and tells you not to paste confidential writing. It needs no login, which removes friction but not the transmission. Treat it as a public tool for text you would already publish.
No. The page calls it a style signal index and says explicitly that it is a style score, not an AI probability. Each batch asks for a 0-4 score plus the strongest signal from a Wikipedia-derived rubric, which is a different claim from authorship.
It shows an unavailable state saying the operator needs to finish configuring Jev, so it may simply be down when you arrive. The page does not document the evidence threshold, the batch size, or what happens to a request that fails mid-run.
Likely. The server keeps each sentence's position and sends bounded batches, up to 10,000 words, then highlights only sentences above the threshold with category, score and matched wording. Paragraph-level cohesion and mixed human/AI passages are not addressed anywhere on the page.
Up to 10,000 words per scan, with no sentence-count rule. Extremely sentence-dense documents are grouped into adjacent passages so the scan remains reliable and bounded.
It sends bounded batches to TypeSafe's Jev and asks for a 0-4 style score plus the strongest matching signal from a Wikipedia-derived rubric. It highlights only sentences that cross an evidence threshold, showing the signal category, score, confidence and matched wording.
Yes. Revise a detected sentence in its review card and choose 'Apply & recheck' to ask Jev whether the signal remains; the revision applies only after a successful check, and every other highlight stays in place. 'Edit in place' changes the full document instead.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
YouTube: Building a contextual brand-safety scorer on Jev from scratch.
X: A website slop detector that checks 35 tells in 243 ms
X: Breaking, golden nugget, or slop
X: A filter for reply-guy comments
More Jev resources like this
A link-and-discussion site run by Tom Nick. Every post, comment, and username is classified by the TypeSafe Jev API before it can be published.
Jev Demos & ExperimentsPlayground#community#moderation#playground
Community
3GitHub stars
A bring-your-own-key Chrome extension that asks Jev one slop/not_slop Choice per X or LinkedIn post as it scrolls into view, then blurs and stamps anything at or above a configurable threshold. Scrolling never blocks, and each post is scored once from a local cache.
Jev Tools & CLIs#community#chrome-extension#moderation
Community
davertor/jev-slop-guardJavaScript
davertor/jev-slop-guardJavaScriptSixteen true-or-false statements you answer, then Jev answers with a Noul probability. Keeping only its confident calls is the point of the game.
Jev Demos & ExperimentsPlayground#community#games#playground
Community
2GitHub stars
MIT-licensed Chrome extension that asks Jev whether the page, video or post you are on serves your written goals -- a category Choice, a goals Noul and a 0-4 waste-of-time Score -- then blocks or blurs in code, tightening thresholds at 2, 10 and 20 minutes of engaged time.
Jev Integrations & Adapters#community#chrome-extension#digital-wellbeing
Community
plusminushalf/rot-guardJavaScript
plusminushalf/rot-guardJavaScript1GitHub stars
A lightweight Chrome extension that scores selected webpage text for how strongly it resembles AI-generated writing, using Jev inline in the browser after a right-click or Cmd/Ctrl+Shift+Y. It aims to give readers an uncertainty-aware signal without interrupting reading.
Jev Tools & CLIs#community#chrome-extension#ai-detection
1GitHub stars
Interactive media artwork where one post meets 100 fictional observers: for each observer the app asks Jev one Choice plus four Score questions (500 questions total), animates the eyes in Three.js and later exposes the full distribution of reactions in a post-analytics view.
Jev Demos & Experiments#community#interactive-art#threejs
Community
mintannn/THE-HUNDRED-EYESTypeScript
mintannn/THE-HUNDRED-EYESTypeScriptFrom the Jev guides
Original write-ups on what this entry is for.
A game tick is a state plus a legal action list. How Clash Royale, Minecraft, and the earlier Mario, Pokémon, StarCraft, and drone loops ask Jev one step at a time.
Jev Demos & Experiments#gaming#agents#control
Read article
From the Jev community
Posts from builders shipping with Jev right now.