X posts

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

J'ai testé Jev (@typesafeai) sur plusieurs trucs que j'ai au quotidien : - soumissions de formulaires de contact : sur mon site https://t.co/qqMSeLGAsx j'ai un formulaire sans champs "sujet" pour des questions d'UX (la friction tout ça tout ça). Là, typesafe peut les catégoriser pour moi en fonction des messages reçus - pareil pour assigner des tickets Jira : j'ai testé typesafe sur une catégorisa

I built near-real-time A/B testing of TikTok/Instagram hooks against a 100 rich personas using Jev from @typesafeai! Stuff like this was super ROI negative in the past. A panel like this meant $1-$5 of cost per run at this scale, plus very slow. Now it costs just a few cents & is real time! This is a brand new world! This is a new ChatGPT moment. Great job @CompleteSkeptic and team! You guys cooke

I got access to Jev by @typesafeai today morning and I built a cool use case for it Introducing DiffJury - simply paste any public PR link and Jev tells you immediately if it's safe to merge or does it require review ✅ 🔗 Feel free to try it out here - https://t.co/XxcZxIZJDK Imagine Jev being able to tell you if you should merge a PR with grounded context of your codebase. that's what we're buildi

よっしゃ〜！！！無事セミナー実演で、DevinでJev使って、アプリにスピーディな意味検索機能を作れた〜すごいなDevinもJevも🔥☺️ みなさんご参加ありがとうございましたー！！！🙌 Jevの使い道すんごいあるなこりゃ！✨ #Jev #Devino DevinでアプリにJav入れた実演解説のアーカイブを1000円で買えるのは明日の朝8時まで、ぜひこちらからどうぞ👉 https://t.co/xwK71r2Ou3

I let Jev from TypeSafe draw a picture pixel by pixel and compare it to Claude Haiku. Just a tiny bit faster. https://t.co/6WwftF0U7Q

Built a tiny island demo with @typesafeai 's Jev. Six objects, three robots, one ferry with a 7-unit weight limit. You type what matters. Jev chooses the cargo, assigns the crew, and decides when to sail. The pirate hat was my decision XD https://t.co/nthKgVQht0

Jev by @typesafeai in action! 20.7k YouTube comments classified in 2m 27s for just $0.20 - p50 319ms, p95 556ms per comment - 140 comments/sec - sentiment + emotion + intent + spam/toxic, each with confidence mostly Apple WWDC videos and results are kinda funny: 43% negative #1 intent is criticism (5.1k) my classification rules are probably not ideal... but you can tweak them and rerun the whole b

got Jev to review my PRs. ~200x cheaper than Claude and it answers in half a second 6 real PRs in the video. $0.00007 each. 1,000 PRs = 7 cents vs ~$14.50 on Opus 5 paste a diff → ONE call to @typesafeai → 14 typed checks come back as probabilities: hardcoded secret, sql injection, touches auth, deletes tests, breaks api, migration, debug leftovers, does the description actually match the diff, bl

i made jev to play a trading quiz @typesafeai it gets given btc chart data from a random window between 2017 and today, then it has to predict the direction after n candles from the last candle it was shown. available actions are: buy, sell, skip (off for now) you can watch the activity here: https://t.co/AdxKUnvu2j

Jev from @typesafeai is really cool. I made a battlefield demo and each character makes their own decisions with Jev. Watch the video or watch it on: https://t.co/RQEqkoLVss https://t.co/p17KLZWtmO

@typesafeai 's JEV is actually pretty neat. I compared it against claude-haiku-4.5 on the same payment transactions, with 8 concurrent threads evaluating each stream. JEV was noticeably faster and feels well-suited for real-time classification. Accuracy is always debatable for any model, but infra can be built around confidence scores. AI slop -> https://t.co/E8EbJqRdXD

Built the ultimate syntax highlighter using @typesafeai Jev (i mean why not). It can highlight any language, even one that I made up.

@typesafeai 's Jev is awesome. I've used it to create a custom/dynamic MCP server framework that can turn any site (including ones requiring auth) into an extremely fast MCP. * mcps isolated in docker instances * Jev drives headless chrome * agent skill - just instruct as to which site you want to mcp-ify and it'll do the rest (maybe) * inspired by @gregpr07 's jev-ultrafast https://t.co/Qts00CR1Y

I gave a vampire, a golden retriever, and 10 other unqualified characters a vote on your bad ideas. Powered by Jev by @typesafeai: 36 typed judgments + probabilities. One call. ~400ms in early tests. No generated text. https://t.co/0DkzIRxIHR

This might be the craziest thing I’ve built with TypeSafe’s Jev yet. I wired it into Red Alert 2, and now it scouts with dogs, optimizes its economy and base placement, decides when to expand, attack, defend, or use superweapons—and somehow split-pushes tanks, micros its army during fights, and routes around enemy defenses. A lot of this behavior just emerged from Jev making decisions in real time

あんまJevでやる必要はないかもだけどおためし。飲食店の人流シミュレーション。トークン量多くなるとやっぱ1.5秒くらいかかるなあ...十分速いけど https://t.co/Zk2XDEMsX6

introducing Unclutter: a smart ad + slop blocker with Jev 🤓 it auto cleans up pages from slop elements: ⬖ ads ⬖ cookie banners ⬖ upsells ⬖ bs dialogs BYOK. open source + free, download below 👇 https://t.co/u3ippda11z

Just used Jev to edit videos and generate shorts. As a demo took this video from the amazing @Danieldalen and turn 26 min into 3 with smooth cuts and transitions plus shorts. All for $0.02, insane the amount of use cases for this https://t.co/FM79tB2U5d

Made Jev play against Fable and Astra in Tetris to showcase its usability Where it wins. Decisions that are frequent, bounded to a schema, answerable from the state you hand it, and where consistency beats depth Here are some examples - Gates and routers: should this alert fire, which pipeline gets this document, does this need the expensive model. The firehose gets judged in full instead of sampl

I used jev to make AI worms in my snake game They are not too bad! https://t.co/X7YTW8b7yj https://t.co/7IhrPCwyUz

I asked @typesafeai's new model Jev to play N Wordle boards at once! Each board hides a different word, but every guess applies to all unsolved boards simultaneously. Every move has to balance solving one board with revealing useful information across the others. Jev only needed 7 model calls across the entire game. Its shared guesses progressively narrowed the candidate set for every board until

🚨 Open Source Jev BS meter you can use this to analyze any debate / investor call / interview / sales pitch / podcast video fact check live , for example this dario interview cost 60 Jev calls / 111K tokens / $0.0047 https://t.co/3JYfoz8vgL https://t.co/oeXcGmZrVV

Using @typesafeai Jev to pull of details of the coffee beans from it's product page for the bazaar on @caffeineletter Jev is super fast, and costs ~1 cent for 20 coffees. Crazy https://t.co/syVzx3lvfJ

Jev + Kimi K3 for fraud detection! TLDR: Jev classified 100 emails in 1.42 seconds, then I routed the uncertain cases to Kimi K3. The full pipeline got 96/100 correct for only ~$0.07. Video is not sped up, check out the live run! Here was my process: I gave Jev 100 emails to classify (a mix of 50 legit & 50 fraudelent emails). It classified all of them in 1.42 seconds. An underrated feature about

I built a Jev harness to play Gmoku. How it works - instead of asking to evaluate all 225 moves, my harness does the tactical work first. Every turn it: • detects wins, blocks, forks & broken fours locally • shrinks 225 moves to ~40 candidates • ranks them into tactical tiers: S = forced win/block A = critical threats (open/broken fours, forks) B = strong attacking/defensive builds C = positional

Jevで音声対話のターンエンド判定やってみた。発話終了後0.5秒後にJevでターンエンドしたかどうかを判定して、スコアに応じて追加ホールド。 timeout=3.0とか出てるのが追加ホールド時間。Noneは追加なし。elapsed=0.224とか出てるのがJevの処理時間。 まだまだ追い込みがいるけど可能性を感じる https://t.co/Zg9sTgYAnv

Is your "for you" page overobsessed with a single topic like mine? I added Jev (@typesafeai @diogoalmeida) to my Tweet classifier chrome extension to find out! Previously I used Cerebras and the fastest LLMs i could find for the analysis. Jev is 6X faster and about 40X cheaper than the fastest/cheapest LLM I could find on this task! You can try it yourself here: https://t.co/cV9cXQuy4O

I just built Easy-Jev, a Jev demo anyone can try right now! Change the inputs and watch the classifications change in real time. I did my master's thesis on classification models so it's fun to see a modernized version of a very useful alg Typesafe are correct in that LLMs are just one approach to intelligence, and I think as time goes forward we’re going to see a hybrid of dif models splitting up