X posts

Can we estimate a book’s literary quality and how enjoyable it is to read by using Jev to perform a multicriteria classification of its prose? I wanted to investigate that, so I built Salomón, a tool designed to do exactly this. I analyzed 32 books blind using Jev, and this is the map I got. Infographics, details and links in the thread.

Opencode sends every MCP tool schema to the model on every step. With 18 common MCP servers, that's ~90,000 tokens before the model even reads your request. I built a plugin using Jev that cuts it to ~7,300. (-92%) 🧵

Built a chrome extension that covers distracting youTube videos using Jev https://t.co/5TVn6cnLjD

I made an AI agent using Jev to reply to my wife We’re getting a divorce now and she wants to know who Jason is

I have a script running that's going through all of my magi-code sessions, extracting every bash command and then categorizing them by similarity using Jev. It's going to end up being about ~$0.60-$0.70 to do this for 4200 bash commands and take ~10 minutes with a very inefficient python script My goal here is to identify instances where the model keeps repeatedly writing python or bash scripts to perform very similar actions - and provide the agent with a small set of scripts that do those things for it so it doesn't keep wasting output tokens on writing repeated code.

Using Jev to catch Codex workers ignoring AGENTS.md. Combine live Codex output, Git changes, and AGENTS.md into one observation Use Jev to score the probability that the worker is drifting from AGENTS.md Steer the active Codex turn when drift crosses a threshold, stopping it if the drift continues Added to Foreman, which automatically watches and steers workers on the software factory floor. https://t.co/g9prp3tsy8

I swear this is the last Jev demo I'm doing... 🙏🏻 I'm using Jev by @typesafeai to get a third person opinion on my vibe coded projects... 👀 Checkout FirstScreen 🔗 https://t.co/nZnEsgxl1n As usual, it's again open source so feel free to star the repo if you want : ) For the past three days, I've had access to Jev, and I'm having so much fun playing around with it 🔥 I built Diffjury and JevArena in the past 2 days and shared with you guys on here, and today I built FirstScreen, where Jev basically takes a look at the website and quickly gives a verdict whether it's ready to ship or need

everyone's using jev to route between models. we put it on inbound sales replies the question isn't which model handles this turn, it's whether "sure" means yes. ours used to log that as a rejection and bin the lead [N] real replies through ai gateway. [x]ms p50, whole batch cost [z] papercut on the way: experimental_evaluate doesn't exist in ai v6, evaluation modality is v7 only, and nothing on the gateway model page says so. @vercel worth a line

i just shipped a small repo that will help you understand it perfectly.its a Real-time support triage + response bot using Jev and cerebras https://t.co/l4gFvr0GdW PS if you like it,approve my entry to the hackerhouse. I applied with rewantgoenka87076@gmail.com

exactly!! just shipped a real-time support triage + response bot using Jev and cerebras. https://t.co/l4gFvr0GdW

youre right. For example in a support ticket jev can classify way faster that which agent should get the ticket. I built a Real-time support triage + response bot using Jev and cerebras https://t.co/l4gFvr0GdW

I made a little experiment of using Jev to autonomously move around rooms of my 3d game. Headless operating based on textual position information. Rendering a screenshot at every step to be made into a gif. https://t.co/bCv0aoNxa9

just shipped a Real-time support triage + response bot using Jev and cerebras: https://t.co/l4gFvr0GdW this should help you get started!

I just built a Real-time support triage + response bot using Jev (from @typesafeai) and @cerebras Jev routes the ticket to a specialist agent (general / account / billing / technical) and decides whether a human should take it instead ,Cerebras then drafts the reply using whichever agent Jev picked. Repo: https://t.co/p6y4IQ2VhZ @callmeshuklaji @communidiyi @hackgoofer @dgo_almeida @sydneyrunkle

Built Jev Snake using jev from @typesafeai This is not your classic snake game fyi. 4 modes in total for this game -> Terrain Mode - You can generate objects REALTIME by writing ANY word. - The properties of the object will by given by Jev. - Your snake will react likewise with the object. HOT/COLD Mode - There are 70 fixed words that randomly appear. - Jev decides its effects - Far better you can type out word realtime. Jev will decide its effect too. WORD SNAKE Mode - There are 50 fixed words in vocabulary in our code. - Jev checks whether consequent words are correct or not - Want m

Jev join the race 🔥 Jev read the top 250 Hacker News stories 250 stories 2000 typed judgments in 16 seconds cost: $0.0095 about AI 32% Negative Tone: 41 ( 16% ) Built with Jev by @typesafeai https://t.co/RY3GiLTks9

Jev can tell if your resume is good enough for a job. I added a simple resume scorer using Jev by @typesafeai 1. You give your resume (Doesn't get saved) 2. PDF to Markdown conversion 3. Jev, does the analysis, across on 5 Dimensions 4. Your resume score Jev is quite fast btw. but he is very reasonable, so if the score is low, it is what it is.

#jev #typesafe #flutter #mobile #test Using Jev from https://t.co/wVCGdOU10g, I created a flutter package that allows you to write integration tests for Flutter apps using natural language. https://t.co/hG0mtW2FGp https://t.co/OkXWEkObbJ

Episode 285: Bendcoder We build an experimental coding agent from scratch using Jev from @typesafeai and new programming language Bend2 from @VictorTaelin. ...while playing WoW Forever on CoderOS; demoing the CoderOS GPU-accelerated multiplex panes and hand tracking (goodbye Hyprland, hello Jarvis); and introducing CoderQuest, a forthcoming game for commanding and upgrading coding agents with real-world prizes. Meanwhile in Azeroth, Eetum arrives in Thunder Bluff and purchases a guild charter. Bendcoder repo: https://t.co/UjtjgTEAZS

We did a test using Jev 1.13.0 on official LoCoMo data benchmark. Jev makes AtMem better at putting the right memory first, but it does not yet help AtMem find memories it missed entirely. The significant increase is on how often the correct memory was the very first result. Improved from 33.99% to 54.23% AtMem used about 1,593,522 token and costed about $0.0583 Jev remains as option in the next releases since AtMem Position is local first. We continue to explore more use cases for Jev

What I’m doing with #Jev from @typesafeai: Making Ergod, my multiplayer AI agent, better at the work between “let me check” and actually getting it done. Better research. Clearer comparisons. Fewer dead ends. Small decisions. Bigger capabilities. 🧵 A result can match your keywords and still miss your question. Jev helps assess what’s relevant. Alongside better page reading, Ergod can focus on useful evidence in long articles and wiki pages - with headings and tables kept in context. The follow-up is where this gets interesting. “What about the exceptions?” “Where did that figure come f

I taught SQL to ask questions using jev: SELECT * FROM tickets WHERE jev_bool(body, 'Is this customer angry?') No embeddings. No keyword list. No LLM writing SQL. jevsql: natural-language predicates, a typed control plane that never lets an LLM touch your data... @typesafeai https://t.co/JtqOsiYoIl

made a color palette generator using jev, because why not? given the input, jev returns probabilities over ten hue families, scores for warmth / light / energy, and a font pick. code maps that onto oklch and paints the page. https://t.co/lAe0TlYKdz

Seeing how many people are using Jev to control browsers I wanted to try too. Wrote the wrapper for 'dev-browser' and called it 'jev-browser'. And then tried to put it to a test: "Find the best pricing model for WP Multitool for someone who runs 3 sites, spends 3h/yr on each, and has $50/hr rate and will run them for 2 years." I saw that it did the right steps until the last one. Was adding the Lite version to the cart. That's how I discovered that while my Pricing page LOOKS good it's structurally awful and definitely nor readable for BOTS or SCREEN READERS. Learned something = PR

I made an experimental model router for @pidotdev using Jev as the decision maker. It's not a generic "pick a cheaper model" router. It isolates work into logical threads and prices cache reads/writes, cold context, expected output + the cost of switching back. @CompleteSkeptic @typesafeai This wouldn't of been possible without Jev, it's an amazing primitive to make software with 💪🏻

Every company writes copy rules. Nobody enforces them after launch week. So I made the reviewer that never gets tired. It reads your marketing site on every PR and names each sentence that makes a claim with no evidence beside it. It's using Jev from @typesafeai It doesn't know your facts. It knows what a claim without proof looks like. https://t.co/bHrzAWVicC @MParakhin don't hate me

built using jev @typesafeai https://t.co/CaKowqwRqW

Proof of concept using Jev by @typesafeai to analyze image metadata and estimate how likely an image is to be AI-generated. Built with @laravel, @inertiajs, and @vuejs. Hosted on Laravel Cloud. Thinking of using it to screen photo competition entries. https://t.co/HskTF6u3to https://t.co/3qfC2SC7BB

Using Jev from @typesafeai to improve matching performance, accuracy and cost in our automated @blackbaud RE NXT CRM integration. https://t.co/TVdfZOa3wI

Doc-OCR router using Jev @typesafeai A Jev-powered router that looks at a PDF page by page, decides which pages actually need OCR, extracts the rest locally. Result: save cost on # OCR pages + speed https://t.co/ZjXqHSjSGh

have not seen anyone actually using Jev for robotics outside of a simulation, so here is Jev running with no policy, zero-shot controlling the robotic arm. @typesafeai @CompleteSkeptic https://t.co/a8CUe9PBdo

I started using Jev as a tool call for our users on supercenter. And oh boy are they gonna love this. https://t.co/JXnhrZXogy

i built a website that ranks all 1,025 Pokémon by literally any question you type, using jev it thinks mimikyu is most performative https://t.co/F0qca4H84o

my video on the routing tool blew up on YT! i crossed 10k views in less than 19 hours, i still can't believe it - my most viewed video till date yayee have been consistently doing YT and content in the ai space for last 7 months and finally get to feel this😇 i built this tool yesterday called agent router using jev + herdr, i was awake until midnight doing recording, and publishing the video. today it feels all the efforts are worth it

tenet using Jev is up to 275x cheaper and 104x faster than Claude agents 🤯 Same 2,000-line diff, same rules. tenet: 1.5 s, $0.0036. One Claude Fable 5.1 call: 157 s, $0.99. Your agent fixes its own review findings before you ever see the diff. https://t.co/Rr1BpU53ak

I built a real-time chat where Jev judges every message in before the room sees it. ❌ No keyword lists ✅ Rules are plain English ✅ Unsure? Held for a human Built with Jev (@typesafeai) + @convex + @vercel Try to break it 👇 https://t.co/P5HYDS6aJX https://t.co/gGWn6XmPaA

Built jevscan - a Chrome extension to detect malicious addresses and transactions on @etherscan in real-time using Jev from @typesafeai. https://t.co/gGgITyJgjT

Created a one-off Chrome extension to remove low quality posts (filtered using Jev) from Twitter, and posts with videos. Feed has become so much better.

Spent a day building tenet, a review gate for code that agents write. It judges each commit, commit message and PR against rules written in plain language, using Jev by @typesafeai. The rules come from @poteto's unslop skill, @hvpandya's stop-slop, @dillon_mulroy's anti-slop and @mattpocockuk's new /pr skill. It also generates rules from your AGENTS.md or CLAUDE.md, and you can write your own rules and presets. Here an agent trips four of them, gets blocked in 1.07 s for $0.0003, and fixes its own findings.

My first real experiment with Jev: project scorer. It takes the specs, source code, and graph (Graphify output) from a codebase, then analyzes them using Jev, Lizard, and Networkx to create project "quality metrics" based on a configurable rubric. https://t.co/lCryvd749u