devwithjevJev Prompt-Injection Guard
Shubham built a prompt-injection guard using Jev. He says Jev answers the question of whether a prompt is an attack in ~150ms with free output tokens.
Shubham@AIgossipTalks𝕏
Hot take: the LLM harness will never look the same after Jev. Why burn a slow, pricey LLM call asking "is this prompt an attack?" when @typesafeai's Jev answers in ~150ms with free output tokens? I built a prompt-injection guard on it. Watch 👇 https://t.co/LACB4J2AtP
The build is presented as an alternative to using a slow, pricey LLM call to check for prompt attacks.
Also filed under Tools & apps
- Meta Ad Analysis Chrome Extension
The Chrome extension analyzes ads from Meta’s Ads Library using JEV (typesafe/jev-1.13) via OpenRouter, surfacing result potential, angle, hook, and niche. The user’s key stays in their browser.
- Jev Plugin for the PI Harness
The repository provides a Jev plugin for the PI Harness.
- Jev Suggestion Plugin for Hermes
The repository is a Hermes plugin named `jev-suggest`.
- OpenRouter Draft Evaluator
This local prototype evaluates and compares drafts generated with OpenRouter using Jev.