Nate Herk
@nateherk
Jev is tagging X posts in real time for me. Breaking, golden nugget, or slop.
XSocial feeds
Updated Nov 10, 2026
The newest builds with Jev
855 projects, posts and guides about Jev, the System One model from TypeSafe AI. Each entry links to its source and shows the cost and speed its author reported.
- 855builds
- 181guides
- 21use cases
Diogo Almeida
@CompleteSkeptic
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x cheaper (w/ output tokens free) • Frontier composable intelligence optimized for decisions AFAICT the shortest path to AI-based economic revolution
Newest first, 831–863 of 1072. All 1072 in curated order
Trackmind
@0xTrackmind
x.com/i/article/2106…
Guidex.com
Jev Engineering: How to Build Claude Loops That Actually Work Overnight
Trackmind’s X article on Claude loops that run unattended, with Jev as the decision layer.
Movez
@0xMovez
I just built a Jev X Viral Post Analyser. 100,000 viral X posts. 20.4 seconds. $0.67. Claude Opus 5, same corpus, same clock, got through 214 posts and spent $0.98. per post that is ~680x cheaper the full Opus pass would have run $458. viral analysis is the perfect Jev job. • it is not writing, it is 14 yes/no calls per post: > does the hook open a loop, > is there a number in the first line, > is the proof real or claimed. classification, not prose. • what it found: 1,220 posts broke into the top 1%. baseline 1.22%. > superlative claim - 2.34% viral. 1.92x baseline > contrarian take - 1.59%. 1.31x > launch / tool drop - 1.46%. 1.19x and numbered lists, the thing everyone writes: 0.55%. below baseline. the most used hook is the least viral one. full stop. • what you are watching: left is the post under analysis, right is Jev answering 14 typed questions about it, each with a confidence score. the run stops at 20.4s because that is when Jev finished all 100k. pulled the corpus through a few X APIs, one parallel pass into Jev. should I drop it to public? Read my latest article on Jev Engineering below and turn your ideas into reality.
AI Builder Club
@aibuilderclub_
We turned Jev into a general browser skill for agents: jev-browser. Give it a website and a task. The browser opens automatically, and Jev decides every click based on what's on the screen. Here's a demo:
XAgents and browsers
jev-browser, a general browser skill
Paulius 🏴☠️
@0xPaulius
Jev brought us closer to JARVIS it instantly does things like launch agents on a canvas - without awkawardly waiting for slowGPT LLM loop @clonkapp is now the fastest agent orchestrator on the planet
XAgents and browsers
Launching agents on a canvas
Asteri
@Asteri_eth
Claude + Jev is the first agent setup where I stopped babysitting every single step most agents burn frontier tokens on tiny calls like "retry?" or "enough sources?". this one hands them to a model that does 10,000 decisions for ~$0.42 10 min and it runs on your machine: prompt → Claude → Jev picks the move → gate checks confidence → Claude executes → logged result step 1 → get your Jev API key on the TypeSafe site step 2 → clone the router from the GitHub below and install it in one line: python3 -m venv .venv && .venv/bin/pip install -r requirements.txt && cp config.example.yaml config.yaml step 3 → export the key before the first run: export TYPESAFE_API_KEY='YOUR_KEY' put the same line in ~/.zshrc or ~/.bashrc so a fresh terminal doesn't lose it step 4 → give Claude skill/jev-decision-layer.SKILL.md and point it at src/router.py + recipes/. on its own Jev only returns probabilities, the router is what turns them into actions Claude can run step 5 → test the full chain end to end, not just the Jev endpoint: .venv/bin/python -m src.cli '{"goal":"what is 2+2?","kind":"chat"}' the JSON you get back should have action, reason, mode, jev_used and confidence step 6 → start in mode: shadow. Claude works like before while every Jev call is logged next to what Claude actually did. after 20-50 real decisions keep only the question packs that matched step 7 → flip to mode: active with hard gates: 0.80+ acts on its own, 0.50-0.79 only suggests, under 0.50 comes back to you what changed for me: Claude stopped wasting tokens deciding whether to retry, reuse the cache or spin up a subagent. Jev makes those calls, Claude does the actual work, and anything it isn't sure about lands on my desk instead of in my outbox grab the exact stack from the repo, then read how every gate works in the full Jev architecture breakdown ↓
Guidex.com
A Claude + Jev agent setup in 10 minutes
Asteri’s setup hands the small calls an agent makes, such as “retry?” or “enough sources?”, to Jev and not to a frontier model. The post gives about $0.42 for 10,000 decisions and says it runs on your machine.
Hamed Valigholizadeh
@hametgholizadeh
JEV IS INSANE. I gave it 80 real exam questions and 297 practice ones. In 80 seconds, it told me which ones are most likely to appear on the real exam and which ones aren’t. All for $0.0256. Can't stop playing with @typesafeai 😁
Yum⋆₊˚
@yuhasbeentaken
Jev classified 1,315 X posts for about $0.086 in estimated model cost 😂 seeing everyone's Jev demos made me want to build something for my own content research. i'd collected a lot of posts, but figuring out what they had in common still meant opening them one by one and taking notes. so i built a dashboard around Jev. it labels each post across 8 dimensions, including topic, hook and writing style. now i can filter by topic and hook, compare engagement, and open the original posts to see the examples behind each pattern. my archive is a lot easier to learn from now.
keno
@kenonews
JEV makes competitor research feel like a cheat code. Give it your competitors’ ads. Break them down by hook, angle, offer and format. Then turn recurring combinations into a shortlist for your next creative test. From an endless swipe file to “here’s what we should try next.” Your competitors just became your creative department.
XAds and marketing
A shortlist from a competitor swipe file
shawn
@shawnbuilds
Claude Mods are like custom Minecraft servers Claude Code Here's how to use Claude Code Mods + Jev to build your own custom memory harness for Claude Code. It runs in milliseconds, at sub-penny cost compared to subagents ⬇️ x.com/i/article/2106…
Guidex.com
How I Used Claude Code Mods to Build a 3600X Cheaper Memory Harness
shawn’s step-by-step guide: Claude Code Mods plus Jev make a custom memory harness for Claude Code. He says it runs in milliseconds at sub-penny cost compared to subagents.
Nick Khami
@skeptrune
you can make any open source model behave like jev with just a bit of inference engineering. it's shockingly easy. to prove it, we built a new endpoint we're calling deepseek-v4.1-flash-jev. see the demo below. here's how it's done: sglang (an inference engine) offers a scoring endpoint in addition to the normal generation one. in scoring mode, given an input & set of possible answers, it forces the model to produce probabilities for each one. example: > input: what is most common letter in abcccde? > possible answers: a, b, c > output: (c, 0.9), (b, 0.0.5), (a, 0.05) getting the above behavior instead of streamed output is as simple as using sglang's /v1/score endpoint instead of /generate. there's just one other trick required. for deepseek, you have to add a closing think tag before the response. this forces a direct answer instead of a reasoning trace. if you want reasoning, you can do that too, but imo that makes things too slow to be worth it. dsv4.1 flash is not as good as jev, but if we had enough spare compute to experiment with this same approach for a larger model then i think the decision quality would be at least as good, if not better. also, somewhat unrelated, i think decision-making models kill all prospecting & sourcing work. i would have absolutely killed to have jev or similar when i was recruiting @mintlify. absolutely incredible.
XOpen source
deepseek-v4.1-flash-jev
Florian Darroman
@floriandarroman
Jev is INSANE. I asked 100 Indie Hackers to build a post scheduler with: Jev vs Fable 5.1. The results are unexpected 🤯 (You can clearly see Jev is faster at doing stuff)
XBenchmarks and evals
Jev against Fable 5.1, 100 builders
t0t0
@t0t0_build
Un JEV me está monitoreando más de 25 grupos de whatsapp con clientes en tiempo real y evaluando si tengo que saber algo por urgencia problemas, pedidos irresueltos etc. Si tengo algo que saber, le avisa a una LLM que me escriba. 🔥
Ethan Walker
@ethan_walker_ai
🧵 What if the next big AI model isn’t designed to chat? TypeSafe AI is pushing a different direction with Jev, a model built to make structured decisions for software. No essays. No long answers. Just decisions that software can act on. Here’s why this matters 👇
Guidex.com
What if the next big AI model isn’t designed to chat?
Ethan Walker’s explainer thread: Jev is built to make structured decisions for software. No essays and no long answers, only decisions that software can act on.
ares. 🎧
@aresotik
ESTA HERRAMIENTA ACABA DE ROMPER TODO EL MERCADO DEL AD SPY Maxfusion ha cogido JEV, el modelo nuevo de TypeSafe, y le ha metido la ad library entera de una marca → 1.891 anuncios clasificados → 19 segundos → 0,12 $ Y no es un resumen: cada anuncio etiquetado por etapa del funnel y estilo creativo, más la radiografía completa de la cuenta Llega pronto al MCP de maxfusion
Hiroyuki Ota (ほた)
@hota911
Jev にぷよぷよをさせてみた。 - 実行エンジンは https://github.com/puyoai/puyoai 。ゲームはリアルタイムで進行 - 盤面とそれぞれのポジションにおいたあとの結果を与え、①今どのフェーズか ②フェーズごとに、戦略からどの結果がベストか の1+3つの質問をして、選択肢を選ぶ 画像は Random に勝つ様子。決断が早いぶん Random も強い。 最初は盤面だけ渡して、単にどこにどの向きで落とすか判断させていたが弱すぎたので、配置後の結果を選ばせるようにしたり、戦略を渡したり、判断を多段化した結果なんとか3連鎖もでき Random に勝てるようになった。
Anusha
@acharyaagamya
I made a Magic Jev Ball for code reviews 🎱 Click it on any GitHub PR and ask: "should I approve this?" It checks CI, diff size, and reviews, then lets @typesafeai Jev decide your fate in ~200 ms No more thinking. Just shaking.
Guidevercel.com
Triage GitHub pull requests with OpenAI’s Decisions API
Vercel’s six-minute guide. Ask two narrow questions about one diff: which review track fits the change, and does it require existing callers to migrate. Application code collects the evidence and uses the answers to organise review. The method carries over to any decision model.
Jiaqi Gu
@droidqw
github.com/droid-Q/jev-sk… ，基于 jev 的 skills 路由
GitHubRouting and model choice
jev-skill-router
Chris Adcock MD 🍊💊
@ChrisAdcockMD
Took Gregor’s Ultrafast idea and wired it into Grok Bot. @bot @OpenRouter @typesafeai @gregpr07 Your bots can now use Jev to drive the real Chrome on the machine instead of slow look-and-click. Drop in the API key you already have (OpenRouter or TypeSafe), and it gets going. It also walks your existing bot workflows and flags which decisions Jev can take over — the quick yes/no and “pick one of these options” calls — so you’re not guessing where it helps. Share link if you want to try it: https://x.ai/bot/sM_Xi4OF09cGU8KGyLvlC
XAgents and browsers
Jev driving real Chrome from Grok Bot
Geek Lite
@QingQ77
复刻 Jev 的并行决策思路，让 0.6B 小模型一次前向直接输出完整概率分布，不做输出 token 解码。 github.com/TianyuCodings/…
Guidetechcrunch.com
The maker of Jev valued at $7.5B weeks after launch
TechCrunch on the round: TypeSafe AI raised $870 million at a $7.5 billion valuation, led by Andreessen Horowitz with Sequoia and DCVC. The company claims a third of the Fortune 500 already use Jev.
Trinay Hari
@hari_trinay
Built a construction plan-set classifier with Jev. Proq turns civil and building plan sets into bills of materials using an LLM pipeline we built on GPT-4.1. Jev classified an entire 26-sheet plan set in 2.9 seconds for $0.0052. It matched GPT-4.1 and GPT-6 Astra on 100% of sheet-level classifications while running 17–21x cheaper and 5x faster than our production pipeline.
Sim Audience
@SimAudience
Jev is WILD I gave it two launch tweets and fed it over 4000 demographic profiles of real survey participants Twelve seconds later, a simulated A/B test tied to actual personas voting on the best tweet you can just do things i made it 100% free (link below)
Izzuddin
@Izzuddin_Shafi
1/8 Saw Jev from @typesafeai on my feed, so I made it play Pokemon Showdown. Codex built the harness. It was damn fast. Its choices were a mixed bag. Full match, video 1/2. This is a saved replay with decision data, latency and added reading pauses.
XGames and real time
Jev plays Pokémon Showdown
Guidea16z.com
Investing in TypeSafe AI
Andreessen Horowitz explains why it led the round. It calls the Jev launch the biggest narrative violation it has seen this year, and says Jev reached 1 trillion tokens generated in 3 days after launch.
Saeed
@stringsaeed
built a highlighter on jev paste any language → my code tokenizes → jev names the lang, colours every word, then says which of 9 lint rules fire and where nine rules in code. jev just answers. near instant lab.saeed.sh/highlight
appcypher
@theappcypher
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.
ラプター | 高専 ロボコン ビジコン
@Raptor_zip
型付き意思決定AIモデル「Jev」で双腕ロボを動かした結果まとめてみた🦾 3層制御のうち意思決定（2層）をJevに任せ、IKや物理計算はコード側に分離する構造を作りました。500msの応答と0.5円/試行で早くて激安。
XRobotics and devices
A dual-arm robot with Jev in the middle layer
- Response
- ~500 ms
- Cost per attempt
- ~¥0.5
Guidehuggingface.co
Decision models on the Hugging Face Hub
Hugging Face gave decision models their own tag, an icon on model pages and a filter on the Models page. GGUF decision models are tagged automatically from their llama.cpp metadata.
Ranjan
@manofsteel3129
built askjev on typesafe jev for all-site navigation with claude you talk to claude in plain english and askjev runs your real browser on any site. jev decides every next click — open pages, switch tabs, scroll feeds, fill forms, run multi-step goals without you babysitting the DOM. mcp server + chrome/brave extension. auto-connect once, then stay in chat while the browser moves. claude handles the conversation. jev handles the decision on each step. askjev is the hands on the web. install: load the extension → paste your typesafe key → auto-connect → restart claude → talk example: use askjev, open http://x.com and scroll my feed and find the best posts http://github.com/ranjan2829/AskJev npx -y askjev-mcp
GitHubAgents and browsers
AskJev
Tamir
@TamirSPIRITT
introducing JevForm, a form that dynamically branches and chooses what to ask next usinng @typesafeai’s Jev in my life i’ve made hundreds of forms with crazy if/then logic. Jev solves it. built with @vercel json-render (by @ctatedev), so theoretically it can support any generative form UI, and @DavidKPiano’s xstate for the actual state Play with it here: https://jevform.spiritt.app/
Live siteUI
JevForm
aniol
@0xaniol
today i built talkr, a speech analyzer using @typesafeai > talkr gives you a topic > you talk about it for 30s > jev analyzes your speech: pauses, filler words, repetitions, confidence, clarity > you get a score and feedback to improve can’t wait to 10x my speaking skills
The newest Jev builds, by the day they were added
Same directory, different order: the entries added most recently, rather than the curated order the home page opens in. The date on a card is the day it was added here, not the day its author published it — this directory is newer than most of the work in it.