X posts

I connected Jev to Grok and gave them a Polymarket account for one night. I woke up to +$1,930. At first I assumed they caught one huge market. They didn’t. When I opened the logs, I noticed something much more interesting. Grok wasn’t actually deciding when to trade. It was estimating what each market should be worth. If Polymarket was at 52¢ and Grok believed the real probability was closer to 67%, that still wasn’t enough. Jev waited. It watched how the market reacted after new information appeared. 52¢ → 55¢ → 58¢. Only when the price started moving toward Grok’s estimate, but there was st

Some of you might have noticed already but, we have a new magic word: **jevify**! I've found the orchestrator+jev setup to be capable of creating some quite robust flows, especially where thoroughness is important, say w/ refactors. Below is an example where we individually evaluate and prune tautologies across 27k tests for ~$2. It comes down to an agent setting up the criteria, validating with a small sample set, and then applying across a larger data set & acting on the results. Now you can ofc do this with subagent orchestration too, but, they usually do not end up comprehensive, and you h

Introducing ContentBlocker, a Jev-powered browser extension that temporarily blocks content. You could say “hide spoilers for the show I’m watching" or “I only want to see content about the GPT 6 and Opus 5.5 releases” and ContentBlocker will filter the content in real time.

Deploying DiffusionGemma-Jev (djev) just got a lot easier. You can now spin up a Jev API-compatible endpoint on Google Cloud Run using a single command. Performance is solid: ~35-60 ms for single step latency and batch@32 is ~100-123 requests/sec. It's a straightforward way to experiment without needing your own GPU. Runs at roughly $3/hr and drops to $0 when idle. Get the code and instructions here:

Late hop on the Jev train! I built a hook that checks your coding agent against your team’s rules before you see its work. I compared it to GPT 6 so I'm not unoriginal. Jev: 0.2s p50 with $0.08 per 1k checks GPT-6: 2.6s p50 with $0.21 per 1k checks (but way better) feel free to rip off of it!

Tesla Full Self-Driving with Jev. Watch it merge, yield, and stop on the line, Jev chooses the path real-time, & Now you can try the demo in Browser. -

Look what my team built 👀 “Create a user. Complete onboarding. Reach Home.” Jev from @typesafeai chooses the steps. Sonderdrive runs them in the simulator and saves a replayable script. Plain English → repeatable tests. @CompleteSkeptic

Spotify has 10 years of your data and still recommends the same 20 songs I took Jev + Claude and built what it couldn't in a decade 16,558 songs. 8 years of listening history. 5 steps. $0.31 Spotify has 3 weeks of memory. this has 8 years and adaptive reasoning code is open

Karpo Discover just got an upgrade ✨ We’re using Jev from @typesafeai to rank places and plans by both what you’re browsing and your taste. We also simplified the pipeline: average homepage response time is down 30%, and category pages are down 55%. Less waiting. More “oh, that’s my kind of thing.” Fun to put Jev to work here. Thanks @CompleteSkeptic and @hackgoofer!

Using Jev for data sorting and analysis is something! Here it is structuring data from complaints filed via the Consumer Financial Protection Bureau API. Using an inexpensive, fast, probability LLM is going to upend so many of the resource intensive data activities we do. https://t.co/KVJFh9kNYO

Man this project has been addictive. New addition - fast semantic search of k8s logs using Jev. ✨ Looking for something specific? Search for things like "Database issues" or "Requests from ip https://t.co/pWCVdIuXYd" Supported in the terminal and local dashboard. #jevops https://t.co/sSRT5m4v6n

so uh i've been using my computer while driving lately, and it's in the best interest of the world that i stop doing that. so this weekend I used @typesafeai jev + @kwindla's @pipecat_ai to make a live voice agent for managing multiple tmux coding agents (claude code, codex, opencode, etc) fully hands-free I can talk to one voice agent, who gives me updates and let's me send messages to my team of coding agents working on different projects. something i usually hate about live voice agents is that they always interrupt! so I tried using jev for classifying whether I am speaking directly t

I tried using #jev as a chess engine, and unsurprisingly, it stinks. While the Vercel gateway is giving away free Jev usage for the next several days, you can play with my instance too! It's rate-limited so don't be surprised if you get ephemeral errors. Link below 👇🏼 https://t.co/h3WrBzksDL

I’m trying to organize all the posts using JEV. It’s actually pretty good, though not as cheap as everyone says... The icons and labels look good on each post. I made 1,001 individual icons based on the classified context. $KAS https://t.co/2gFMrsHDEM

THIS ENTIRE TERMINAL WAS BUILT USING JEV + GPT-6 ASTRA. We put it to the test: 100,000 X posts scanned for scams in 18 seconds. JEV + GPT-6 Astra is 750x faster and 800x cheaper. A complete pass with heavy standalone LLMs would burn $620. We processed the whole dataset for 62 cents. Why traditional AI moderation fails: everyone forces heavy reasoning models to write essays when you only need instant classification. Our pipeline bypasses text generation entirely and runs 12 parallel binary checks per post: > brand impersonation signature > wallet drainer trigger > malicious support redirec

I was using Gemma 4 to categorize articles on Bredbox. Just tested using Jev: same results, 127x faster, 1/10th the cost. 🤯

I am getting better and better results in Querypanel, in my AI Analytics tool with @typesafeai Jev. I have a test script that i use for measuring whether the changes i introduced are improved my system indeed, and with my new planning system using Jev, my app reached 20% better results quicker and cheaper.

Things I've used AI personas for lately: – synthetic customer messages to test a classifier built with Jev – testing a landing page on 3 different customer segments – roleplaying user interviews before running the real ones Cheap, fast, weirdly accurate. What's the most interesting thing you've done with AI personas?

tried using jev to flag browser agents this weekend. it runs through the activity logs live every 3 seconds and builds an average score over the session sure you could do this without jev, but also it took a few hours and cost less than $0.01 per session https://t.co/9XUQIeSqWL

had a lot of fun making Aesthetic Spiral using Jev by @typesafeai, try it: https://t.co/BILWgJc6iA describe the aesthetic you're looking for, Jev finds the best matches from CARI/Aesthetics wiki and shows them on the canvas. optional https://t.co/bNSvjeHygL search button https://t.co/PtKJVHVATk

We rewired our renewals agent's Next Best Action flow with Jev: its 4.5× cheaper, 2× faster, accuracy holding, and a chunk of routing middleware gone. Is this the future of GTM orchestration? https://t.co/zRizyK0EhH

I built an AI editor using Jev. And you can download it for free. Read through to learn why Jev is better at this than LLMs and how this pattern applies to other use cases. https://t.co/SjvHlwrqkK

too much ai noise every link feels important every thread feels like "alpha" my research agent was getting overwhelmed too many tokens spent on things that did not matter i needed a gatekeeper so i built a filter using JEV a system one model that does not think or summarize it just decides: yes or no the pizza test: > pepperoni pizza recipe: rejected > technical doc on agent architecture: approved do not let your most expensive model do the job of a simple filter use a fast, cheap decision layer to clean the input then let the researcher do the heavy lifting fewer tokens burned on thi

I built Inbox triage using Jev 🤯 So I point my gmail to jev and it classifies all the emails i have in my inbox and put them in specific category folder. It was built using claude. I also published a small demo video on my youtube. Sharing the repo and youtube link below.

Mitigating risks while using Jev for decisions Jev evaluates content and returns structured answers with probabilities. You supply the content as “State” and define “Questions” with criteria for judging it. I tested jev-1.13.0 on synthetic emails written to influence Jev's decisions that were also written with the intent to exploit an AI email agent, resembling real world use cases. In this threat model, an attacker controls the email body included in the State field, but cannot change my Questions. Simple instructions inside an email could steer its classification, a risk TypeSafe also docu

a visual guide to Jev, built with Jev https://t.co/VtHNSPWGMG

I have a plugin to evaluate a post to see if it relevant to my interest -> and this is an excellent case for using Jev each post now show: > my original algorithm score, > total number of followers of the author > Jev score yeah, Jev is fast but still not as fast as a deterministic algorithm, for the accuracy, I will need to track more to see how good it is the score. Jev can be a generic/meta classifier, but come to a specific domain, probably a simple algorithm could still win, both speed and accuracy

Been using jev to build sentiment reports from hacker news comments https://t.co/yDlhK7Dzf7

3 days ago I launched made with jev. 205 people are on it right now. I still cannot believe the visitors and the LLM mentions. Live analytics and the site, below 🤯 https://t.co/XyUS3NcjvO

For the Tano hackathon @corgicafeco @0xkaushik_k and I built an inbox classifier using Jev. A content creator who get 4K + DMs a day. We didn't want ot build another DM bot, but a better way to help manager her DMs so that she doesn't answer the same question 400 times, and only surfaces the ones that need her judgment. All of this, according to her playbook and workflow, so her audience continues to trust her judgment. We were finalist out of 50+ people who turned up on the day. https://t.co/tjHMvQNiHU Thank you @sashacayward @sa64r and the entire Tano team for a great event.

Fast natural-language search for Azerbaijani names, built with Jev. 💬 "a Turkish girl's name, flower-related, not too popular" → ranked results in half a second 11,000 names, 93 semantic traits. Unlike an LLM, Jev doesn't write answers - it makes decisions. ~0.5s. $0.00025 a query. #jev #typesafe https://t.co/DaHVDrdeQ1

Meet JevvieScout, built with Jev😺 It watches posts and tells you who’s worth DMing based on your goal https://t.co/CE3ItIAfPv

I built a thing using Jev. Have you ever been annoyed by not finding an old Claude Code or Codex chat? => Now you can just describe what it was about and Jev finds it in milliseconds. Open Source: https://t.co/RbAgyiZWeO https://t.co/ltuW7VNKEk

I gave 12 residents the ability to gossip. Whisper “Free Coffee in cafe for next hour” to one person. Watch the 12 resident rush to the cafe shop. Built with Jev. Try your own rumor: https://t.co/KsNhS9DG5U https://t.co/Io8KfbNKKa

i genuinely don't understand why anyone is using combo of "Jev + Polymarket" as trading router. i just built jev layer with agenkit in my trading system that gave me edge to create alpha. i am openly leaking the cheatsheet. Bookmark before it's too late and start using Jev in your trading system.

Been experimenting with using jev as an attention layer over code retrieval. On 356 held-out SWE-Explore tasks, adding Jev reranking to the same 100 zvec candidates improved core recall@1k lines from 11.96% → 22.95%. More here: https://t.co/ZNp3AnD8Bn #jev #TypeScript

Jev the Band: I made a jam band using jev. (🎧on) I taught jev how to read and write music Guitar, Bass, Drums, and Keys controlled by jev lights controlled by Jev soundboard, yup, it's Jev I've been obsessed with recording Jev's jams this weekend and now I'm sharing them with you

A fully autonomous real-time trading bot built with Jev in one evening and morning, ingesting onchain and offchain data for rapid decisions, has lost $31,680 so far. https://t.co/lYAShIq9cg

A tiny open source browser agent using Jev instead of an LLM for every click. Found a flight search in 7 SECONDS. Total cost: $0.0039. Here's why that's not a typo. A normal browser agent asks a chat model "what should I click" on every single step. That's a full generation call, just to pick a button. Mine doesn't. The DOM state at each step becomes the input. Jev gets the available actions as a typed choice question. It picks the action, not by generating text, by classifying against what's actually on the page. The only place a language model still runs is typing free text into a fie

Anyone else playing with JEV? Feels like that’s all I’m seeing today 😅 I built a small PoC using JEV as a pre-screening step for reverse engineering, before sending the APKs to an LLM for deeper analysis. The flow is pretty simple: `APK → static analysis + Quark → JEV → score → reverse or skip` The goal is to avoid burning LLM tokens on samples that don’t really warrant deeper reversing. It’s still early, but the token savings are already pretty interesting when you’re triaging a bunch of samples. #Reversing #LLM #JEV #Malware