Projects built with Jev

No projects found. Clear filters

Touchpress mobile end-to-end testingmy mobile e2e testing library powered by @agent_device and AI sdk now supports Jev from @typesafeai Same test, same loop: Jev: 29s, $0.003 Haiku 4.5: 37s, $0.07Robert Soriano

A Three.js driving simulationExperimenting typesafe's Jev api in a three.js driving sim.𝕕𝕖𝕧 / 𝕒𝕔𝕔 | Vlad Rez

Slop Cannon profile analysisAre you a Slop Cannon? Jev knows. - reads your last 200 posts - each post gets stamped SLOP or HUMAN - global leaderboard of certified humans It’s brutally accurateChristopher

Quality checks for physical-AI action labelsJev is insane. We are building egocentric training data for physical AI. Jev QA'd 58,643 action labels in under 3 minutes. 90 cents. A friction cost of the Claude & GPT models.Peter Wang

What toxicity sounds like to JevOkay soooo what if @typesafeai's Jev could 'hear'? here's what Toxicity sounds like according to Jev :it’s rivian

Flagging AI-written X repliesI used Jev to flag AI replies on X. I defined common AI-writing signals as the positive criteria for a Noul question that returns the probability of whether a reply is machine-generated. Things like a "not X, but Y" phrasing or an explanatory framing. And a Chrome extensionIshu Agrawal

Intent-aware search in Replicassmall experiment where I used jev to power the global search in replicas. the possibilities of improving UX with models like jev are endless. we can now have things like: - search that understands what users mean - actions that change based on what you're trying to do - routingSaai Arora

Bannerbear instant field mappingFirst Jev use case published live on Bannerbear! Instant field mapping between template and source, when names are slightly different eg template - photo - name - company_name data source (eg Airtable) - avatar - full_name - business Jev figures it out in one click.Jon Yongfook

Dragon Ball Sparking Zero with Jev@typesafeai’s Jev playing Dragon Ball Sparking Zero. Astra and Fable each write an initial policy for Jev (system 1) to make the real-time decisions. Astra and Fable (system 2) updates the policy as the game progresses.Kariminal

Intelligent ordering for code diffsI tried using Jev as an intelligent ordering tool for diffsJustin Garcia

Jev Trader on Monad and KuruI built a trading bot with Jev! Jev decides if it should "buy" or "sell", given the price feed of an asset pair, and executes real trades. It uses Monad to place the orders on Kuru's on-chain order book in every 300ms block. Demo link →Jarrod Watts

A driving simulator controlled by JevI rebuilt Tesla Full Self Driving with Jev in less than an hour. This model is a total unlock.Justin Schroeder

Real-time voice control for a browserwhoa this actually worked! Jev lets me control my browser in real time with my voice now > i talk > transcript sent to Jev > jev returns probabilities in ~300ms > browser clicks costs: $0.0002 per decision i'm stunned how fast this is. when i asked it to "go back", it evenMoritz Kremb

Fourteen checks for every pull requestgot 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, sqlPaolo Rosson

Classifying 500 emails in secondsYeah Jev by @typesafeai is very cool. It classified 500 emails in seconds. And it costed 3.5 cents.Riley Brown

Natural-language queries inside PostgreSQLI think I just cooked something 🔥 jev(): a PostgreSQL extension that searches your whole database in natural language. No index, no embeddings, just one function. WHERE jev(people, 'could work from home') or WHERE jev(people, 'name sounds european') 129 rows judged in ~1sZachi

An inbox classifier for 1,500 emailsthis model is actually insane at email classification i tested it on 1500 of my own emails to see how well it works and I am blown awayvogel

Generating text with Jev“Jev can’t generate text” Ofc it can @CompleteSkepticSuman

Computer use across operating systemsi built computer use using @typesafeai ! it is 155x cheaper than opus 5, ~20x faster, and generalizes across OS's more on how it works in the vid & thread below:aaron

SuperX post scoringJev + SuperX = virality solved ✅ Every post gets 61 questions in ~1s for $0.0004 🤯 > fitted on 9,481 real posts from 207 creators > picks the viral post 2 in 3 times > never rewards reply bait So: write, score, rewrite, stop when it peaks. Free, no signup. try it below ↓Rob Hallam

Mac computer use with local perceptionOkay so Jev can actually do computer use really well Without any screenshots, or LLMs and no Pixels leave my mac I dont even read the Dom elements A local CoreML model segments every button and UI element on screen. On-device OCR reads the labels. That text is all Jev gets.Milind S

Blitz chess against frontier modelsJev VS Fable 5.1 VS GPT-6 Astra: chess typesafe's new Jev V13 isn't an LLM. it doesn't chat, doesn't explain, doesn't write code — it only makes decisions. so we made it play blitz against frontier LLMs. the test: 5+0 blitz. every move is one API call. Jev V13 vs Fable 5.1:AI/ML API

A codebase complexity classifieri built a codebase classifier with Jev and this might be the solution to overengineered code that agents create what should I test Jev on next?vogel

Email fraud detection with Jev and KimiJev + 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 toHassan

Stagehand browser control with Jevwe built blazing fast computer/browser use with Jev + @Stagehanddev. this task cost $0.001 and executed at near instant speed (in a remote browser btw) the loop: observe the page, send a11y tree as state + actions as questions, Jev decides the next action, then StagehandKyle Jeong

Criteria-based model routing in EveUltra-fast, criteria-based model routing using Jev from @typesafeai.eve

Jev as a QA testerYou can hire Jev from @typesafeai as your QA testerKrzysztof

Tetris with real-time Jev decisionsI got early access to @typesafeai's new Jev model and built a demo of it playing tetris The generation speed is so fast that it's pushing blocks down This feels like another "this changes everything" momentMarcus Lowe

Writing one character at a timei made an llm from first principles with Jev 29 yes/no questions per character: should the next key be a–z, space, comma, or period? highest probability gets append to it, then fed the updated text back in & repeat an autoregressive loop made out of a classifiervogel

Jev inside a security pipelinethese 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 butGreg Pstrucha

Jev-review feedback for coding agentsbuilt `jev-review` @typesafeai it's an experimental, local-first MCP plugin that gives coding agents a score quality feedback loop across different metrics. agents call jev while they work, get scored, make improvements, and repeat the loop try below 👇Niaz Morshed

Five hundred agents in a 3D environmentJev is actually insane. We benchmarked it, and the results completely change the game for us: > 500 real-time agents > running in parallel > in a 3D environment The preliminary results are crazy: > 500ms average latency > 35 API calls/s > all with a naive implementation WeCris Lenta

A Rubik's Cube that solves itselfI got a rubik's cube to solve itself with @typesafeai 's Jev and it solves it like a person does, 94 moves, not the 22 move optimal solution. Jev isn't an LLM, it just answers one question in ~250ms with a probability. so I put the beginner method in code (the one you'd learn onPaolo Rosson

An interactive Jev playground on Val Towntypesafe's jev is fun! live demo you can play with:Steve Krouse

Live clinical-transcript classification prototypeDuring a live clinical consultation (with an ambient scribe), the transcript is periodically supplied to Jev, which traverses a medical ontology to classify symptoms, update the differential diagnosis, suggest treatments and identify red flags in real time.Chris McMaster