All builds

Yesterday, GLiNER2.5 played doom. Rapid play looks coherent, but Jev has a secret sauce: decisions. So, I kept the embedder and trained a small decision head on the output. Now it's a homebrew decider model on embeddings. What homebrew decider model will you make this weekend? https://t.co/vOgOyu4Ye8

Built something really cool with Jev for my Agentic Inbox setup on Cloudflare. @sunilpai @thomasgauvin this was fun to put together. https://t.co/oXoVcD566W

Here's an example of Jev routing tools, skills, cli commands for Qwen 3.8 27B on @cerebras to format a Power BI report. Changes are almost instant; working on Linux, only wait due to publishing and refreshing embedded report. The video is not sped up, at all. Just a start. https://t.co/AZWKXZFYzR

Jevを使った音声認識アプリを作ってみた 話した内容を文字起こしして、それをJevが重要度判定する 重要な文節ほどフォントが大きく、色も濃くなるので、あとで見返すときにラク！みたいなイメージ 議事録作成とかに使えるかもしれない https://t.co/9hPeg6myjB

Jev is the most powerful trading agent! I plugged this open-source repo and turned Jev into a 24/7 trading bot that reads the live order book, decides to buy or sell, and places an order every 300 milliseconds and it can be adapted to ANY market or trading pair... here is how you can set it up: 1. clone the jev-trader repo (github on top), one bun install gives you the live market feed, Jev adapte

I asked jev to analyse and rate my 2442 posts on X and it's review was brutal to say the least, here's a 2-minute snapshot of the run (3x speed up) The whole run took around 8mins getting us to ~5 posts/second which is quite low, am I doing something wrong? https://t.co/Fli47KhwhO

okay Jev is an INSANE unlock, I just gave Mario a multiverse. built "Mario Never Dies" with @typesafeai's Jev + microsandbox Jev picks every move and every time Mario dies, we fork the entire VM into 4 timelines and try again. whichever Mario survives becomes canon. it is like the others never happened.

Jev opens up so many possibilities for gaming 🤯 🏁 I built Wordshift - the first semantic typing racer game built with Jev from @typesafeai Slower than a jet, bigger than an elephant, faster than a cheetah. The bigger the difference, the farther your car moves. https://t.co/elObRrcVti

X algorithm post simulation hits 5M views. built using JEV. https://t.co/ub7Jcm4Q7w

Implemented this exact thing today in the @knocklabs agent harness using Jev based on the common types of requests we see from live traces.

I built a simple reranker using Jev that performs on par with Voyage, and outperforms Cohere and Mixed Bread https://t.co/r4Xdfuk6BJ https://t.co/4StSjjKoRw https://t.co/DlJBc3A88Y

I've built a drone autopilot using Jev @typesafeai. It flies from point A to point B, avoiding obstacles along the way. One trip costs $0.01. Uses @vercel @aisdk. Code is on GitHub: https://t.co/gNQZIbRP7E https://t.co/1uZuiEOLhn

I built a Chrome extension for agentic browsing using Jev by @typesafeai, https://t.co/Xa9toMieqT including AI Gateway by @vercel. Now agents can browse, click, and interact with websites directly in your browser. Cost effective and fassst. Decision-making by Jev. https://t.co/bIqkUbCkvc

got access and been using Jev as the director for my VJ software given he answers in under 500ms with judgments and confidence, he picks the scene, palette, effects and the mix, once a bar in real time cost? around 1$ per 2hr dj set https://t.co/KSndabU5RI

Put together a quick video of using Jev with ReqLLM I cover the new `evaluate/4` method, why I went that route, and make a real API call to Jev to classify an issue https://t.co/wvSoeI07AD

using Jev as a chess engine, I call it alpha-jev. pretty unimpressive lol https://t.co/FMP6oTOKyV

I vibe-coded this simple, open-source and local Telegram content analyzer using Jev as a classifier. Jev Classifier • https://t.co/Ux7mYLwStF Export your channel data as JSON and it will analyze each post's intent, quality, sentiment, and reaction tone and if it's a DM/Group chat it will analyze topic, intention, and emotion, plus a per-speaker tone summary. I made it very extensible so you can use Vercel AI Gateway API Key or @typesafeai's, you can also goto the settings and configure Jev so the questions and choices can be customized to your needs. https://t.co/sWz5x38mGl

AI coding agents just got caught lacking! Built Greenwash, a GitHub app that catches AI coding agents pass the CI checks silently. This tool reviews the PR lightning fast! ⚡️ Built with Jev, the model from @typesafeai. Huge thanks to @notkevinzhang and @justKDeng for getting me off the waitlist. Link in the Thread…🧵

inspired by jev, i created something real fun: crowd check! test your post/tweet on a crowd of 10,000 AI readers before the real internet sees it. they have their own jobs, personalities, tastes and memories. post anything and watch what happens: - do they like it? - hate it? - repost it? - follow you? - block you? - or nobody cares? then see exactly how your post performed across the crowd 10,000 ai readers. millions of tiny decisions https://t.co/KCQimIi1n7 using jev via vercel ai gateway @CompleteSkeptic @rauchg

Built a text -> emoji sentiment analysis demo using Jev Try it here: https://t.co/MNprxC9KIr

remade an AI filter composer I was working with, using Jev instead of Luna Medium, numbers are good, can probably iterate a bit to make it cheaper and faster https://t.co/pFGsRa456G

Vibe coded a parallel search using jev for agents, planning to hook up a local LLM to this to get human output. Discovers new pages and adds them to a BFS queue, jev consumes pages in parallel, reranks and adds to the queue. https://t.co/EkpZhuYmRB

🚨 I gave the Trump vs Kamala debate a live BS meter using Jev every sentence, both candidates, 5 yes/no questions each 1,191 Jev calls / 1.18M tokens / 415 ms median total cost : $0.0497 same questions for both, clips picked by one fixed rule, not a fact-check https://t.co/m8u4ALl6Me

using jev and the sick new markdown renderer in @pidotdev , i made a pi-extension that lets you toggle how much detail you want in the agent output. this was motivated by my inability to understand what opus 5 was getting at https://t.co/PE4HQhc84T

IRS O*NET job classification using Jev (1,016 possibilities) Query: "I scoop scoops and sprinkle sprinkles" Result: 35-3023.00 Fast Food and Counter Workers https://t.co/SSXUqQwNo3

these are results of using jev on one of our security pipelines. we already have to use smaller (and dumber) models to make it economic and this model does it over 5x cheaper, faster and while maintaining much higher accuracy. i don't normally hype over new model releases but that's the first one that actually impressed me. good job @typesafeai

I'm using Jev (from @typesafeai) to categorize expenses for my company! Our office manager used to do this. It's all in Mongolian and we have to do it using bank records. It is very unique to our company, and not something a software would handle easily. We also have about a years worth of Excel files (training data) that I'm using to give Jev guidance on classification (few shot style). It really works, it's stupidly cheap, and when it's not confident it says so. Pretty great! This isn't anything new, classification in ML is extremely "solved". But this is a general classification model