Content moderation with decision models

Chrome extension that labels every X post you scroll past with six typed Jev questions and shows a live cost counter.

Chrome extension tagging each X post's intent (inform, persuade, provoke, sell) plus rage-bait and hidden-ad flags via Jev.

Experimental Chrome extension that asks Jev closed questions about X posts, X profiles and HN comments and labels them only when clear.

Proof of concept that uses Jev to detect Spanish profanity in word-timestamped audio and beeps it out with ffmpeg without changing duration.

Creator inbox sorter: Jev answers five questions per comment or DM and code decides to notify, draft, like, hide, archive or escalate.

Chrome extension that scores X timeline posts on five dimensions with Jev and dims or collapses them according to your sliders.

Web app that has Jev judge a note.com article's writing quality on eight Score axes plus an overall AI-slop choice and score.

Chinese tool that scans a Bilibili video's comments for rhetorical moves, with eight labels and quoted evidence, optionally via Jev.

Study finding commercial decision models including Jev give different yes/no probabilities on Taiwan statements by Chinese script.

Cloudflare Worker that checks text or usernames for profanity with Jev on Workers AI, including disguised look-alike spellings.

Text review gateway between clients and AI services that classifies each user input with Jev and blocks or logs per configured scenarios.

Video demo app showing Jev use cases with the AI SDK and shadcn/ui, from intent search and model picking to chat moderation.

Public wall where Jev answers short questions yes, no or it depends in about 100 ms and picks which LLM answers signed-in users.

I Ching divination site where charts and verdicts come from code and Jev only classifies the question's topic and screens unsafe ones.

WordPress connector that lets themes and plugins ask Jev typed questions and branch on probabilities, choices or scores.

Go reverse proxy between nginx and an LLM backend that extracts each request's user input, asks Jev if it is harmful, and blocks or passes.

Audience simulator where 10,000 computed personas read your post or listing and Jev decides who sees it and how each reacts.

Comment-moderation demo: one Jev call screens seven hazard Nouls and a severity Score, with the verdict computed by policy thresholds.

Placeholder repository for an indie-media trust and safety gate powered by Jev.

Minimal grammY Telegram bot that asks Jev whether each group message is spam and deletes only high-confidence matches.

Claude Code plugin where a local decision model (Laya, or Jev) flags profane or abusive prompts and an instruct model rewrites them.

Video demo classifying 50 mock YouTube comments with Jev (intent, value, video idea) and comparing speed and cost with GPT-4o-mini.

Chinese multimodal moderation research pairing a Qwen3-VL LoRA evidence extractor with Jev policy decisions, benchmarked against baselines.

Benchmark of zero-shot Jev versus a PyTorch MLP and k-NN on embeddings for Jigsaw toxic comment classification.

Single-tool MCP server that acts as a content-moderation gate using Jev, with noul, choice and score question types and a mock mode.

Hosted comment-moderation playground built on Jev.

Public Jev playground and API site that answers typed Choice, Score and yes/no questions about pasted text in about 0.5 s.