VERCEL + CLOUDFLARE + CLAUDE CODE all picked up... Jev in 6 days... an AI that can't write a single word became the fastest adopted model on Vercel's AI Gateway Jev decides → big model thinks → code authorizes TypeSafe dropped it on September 15, founder Diogo Almeida worked on ChatGPT research at OpenAI it answers three ways: pick one option, rate it on a scale, or yes/no with a percentage "which agent next?" comes back as Researcher 71% / Coder 18% / Reviewer 11% Vercel says almost 13% of its paying teams tried it within the first 24 hours on Vercel's leaderboard it pulled about 26% of all requests but only 1.8% of tokens TypeSafe's own tests: up to 194x faster and 445x cheaper than regular models TypeSafe calls it a System One Model, named after Kahneman's Thinking, Fast and Slow your expensive model stops burning tokens on yes or no questions and only gets the hard ones 6 days, 110 community use cases, zero words written ↓show more

This is absolutely f*cking insane. you can put a... $0.042-per-million-token model in front of Claude and let it decide what Claude ever has to see. that's Jev signal routing, and the trick is stupidly simple: Jev takes the first look at everything. Claude only gets the hard cases. instead of: data -> Claude -> tokens burnt $ it's: data -> Jev -> only the unsure ones -> Claude and here's the part people miss. every Jev answer comes with a probability. that's your router: -> Jev is sure? its answer is final -> Jev hesitates? the case goes up to Claude set the cutoff once, by testing on your own data, not by guessing. 3 repos that already do the routing for you: -> duckdb-jev: route your data. Jev labels every row straight from SQL, up to 1,000 calls in one request -> quicksilver: route your files. Jev checks all 187 files in parallel and Claude gets the 4 that matter. ~2.4k tokens instead of ~26k -> jev-router: route your models. before every message Jev decides simple or hard and sends it to the fast model or the strong one. works with your normal Claude login where this pays off right away: -> support tickets -> your inbox -> lead lists -> messy spreadsheets -> comment moderation on a public benchmark Jev labeled 1,000 rows for $0.015. Claude charged $0.80 for the same job. faster. cheaper. way fewer tokens burned. Jev sorts the mail so the genius only opens what matters. Claude thinks. Jev routes. code does the job.show more

You've probably scrolled past a dozen posts about Jev... this week without anyone telling you what it actually is. It's the first model from TypeSafe, a lab started by one of the researchers behind ChatGPT. It's a decision engine: you give it options, it picks one and tells you how sure it is. It cannot write a single word, and that is the interesting part. Every other AI you use writes. That is the whole interface. So when software needs a plain yes or no, we make a model write a paragraph and then dig the answer back out of it. Fine in a chat window where a human reads it. Bad inside software, where code has to act on it. The bet is that the valuable half was never the writing. It was the deciding. That problem showed up in WordPress years ago, and it is the reason WPVibe works the way it does. The AI does the work. Anything permanent stops and waits, because a delete that skips the trash is not something software should decide on its own.show more

Built a model router with Jev by TypeSafe AI.... Jev decides what model fits your request best and the request is sent to that model.show more

You can now use Jev right inside Claude Code... 🤯 It's called jev-model-router, an early access mod built on Claude Code's new function hooks. Before every turn, it checks in with Jev and asks: > how mechanical the task is > how much reasoning it needs > whether it's risky Then it routes: → it'll move up to a stronger model on weak evidence, and only drops to a cheaper one when it's confident the task is simple → every decision gets logged in your transcript → if the call fails, your request runs untouched Setup: 1. copy the install command: npx claude-code-templates@latest --mod productivity/jev-model-router 2. paste it inside Claude Code 3. run claude with CLAUDE_CODE_ENABLE_FUNCTION_HOOKS=1 set 4. accept the trust prompt on first launch Link: Also works with no api key, it just falls back to a built-in classifier with no confidence score. For real jev routing, add your typesafeApiKey or gatewayApiKey to ~/.claude/settings.json. Follow me for more AI workflows and tutorials.show more

EXCUSE ME?? IQuest raised a 320B model from its... very first token, then gave it over a million exams with three proctors on every single one the exams are real executable containers. one check runs while the environment gets prepped, one while the code executes, and a full trajectory audit after. if the model tries to peek at hidden tests, it gets flagged, so every pass it learns from is earned it's called IQuest-Q1, an open model built to live in your terminal → 15B active out of 320B, only 8 of 256 experts per token → 29T training tokens, context stretched 32K → 128K → 512K → SFT, RL in real environments, then multi-teacher distillation (MOPD) → runs inside Claude Code, Codex and other agent scaffolds my favorite speed trick: an MTP layer gets reused as a drafter that guesses the next tokens, and the main model checks them. long sessions get way cheaper on the same parameter budget the team calls this an early release. a first model with training this strict makes me want to see the second one try it:show more

Jev by TypeSafe AI is now on OpenRouter, in... beta. Jev is a System One model. Instead of generating text, it takes your app's state plus a typed question and returns a typed decision with a probability attached. There is no JSON prompting, parsing layer, and nothing to validate against.show more

it's f*cking insane.. Anthropic just dropped a Claude Code... setup that makes tokens up to 97% cheaper Opus brains, Sonnet bill: > Sonnet runs your session and writes the code > Haiku subagents grab the small tasks > Opus steps in only when Sonnet gets stuck > it checks the work, digs into the problem and puts Sonnet back on track $19.50 saved on every 1M tokens a Haiku 5.5 subagent writes, compared with Opus 5.5 one command sets it up: npx claude-code-templates@latest --setting model/sonnet-opus-advisor-haiku-subagents the easiest money you'll save on Claude Code this yearshow more

this is pure f*cking treasure TypeSafeAI engineers spelled out... in their docs exactly how Jev fits inside an agent, and these patterns are perfect one rule behind all of them: the LLM thinks, jev decides, code acts I mapped them into 9 live schemes: > model routing jev picks the cheapest model that can do the step > guardrails screens what your agent reads before it acts > tool-call gating every tool call gets allow, ask or deny before it runs > inbox triage the agent only opens what actually needs a reply > reranking jev scores 30 passages, the agent gets the best two > llm evals grades the output and sends it back if it falls short > bulk labeling one question fanned out over a huge table, the agent reads the counts > real-time control games, bots, trading loops: a decision every tick > confidence gate act, confirm or hand it to a human. your code sets the thresholds, not the LLM why it works: > ~100 ms per decision > $0.042 per 1M input tokens, output tokens free > calibrated probabilities on every answer one LLM does the thinking. jev makes the thousand small calls in between save this before you wire your next agentshow more

Code LLaMA is now on Perplexity’s LLaMa Chat! Try... asking it to write a function for you, or explain a code snippet: 🔗 This is the fastest way to try AI at Meta’s latest code-specialized LLM. With our model deployment expertise, we are able to provide you with this model less than 24 hours of it’s release. What’s next? We’ll integrate code LLaMA into Perplexity, all in service of providing you with the best answers to your most technical questions!show more

Opus 5.5 + GrokBot + Jev... I can't believe... that I build it I packed the best of AI into ONE agent - now 99% of people’s AI agents look dumb, slow, and expensive Try here (free): prompt → GrokBot → Jev chooses LLM → Claude / GPT working on GrokBot's computer 24/7 → result → Jev sends only the tasks Grok is weak at to Opus or GPT → Jev picks the best model for each task - for example, Claude for motion design and Codex for web design → runs on the ChatGPT and Claude subscriptions you already pay for (API also work) → works on GrokBot computer while you keep chatting → checks every result against the goal before you see it → GrokBot gets smarter and cheaper at the same time → And plenty more features in a bot everyone will call "obvious" by 2030 Try Jevopus, thank me later - then read the article on the full Jev architecture ↓show more

this is certified f*cking gold a 23-year-old from China... runs 300 Claude Code agents at once with Jev engineering, and not one of them gets to lie to him he opens the dashboard live: 300 Claude Code agents running in parallel Jev checking every output against its source in about 100 milliseconds pointed at 100 companies in the EV market: > pass 1 - 12 rejected: wrong revenue, dead citations, empty fields > pass 2 - 3 rejected > pass 3 - zero. every row filed straight into an Obsidian vault the whole trick is the split Claude Code does the work, Jev decides whether each claim actually matches the source Jev never writes a second opinion. it answers yes or no with a confidence score, at $0.042 per million tokens in and the loop won't stop while anything is still wrong an analyst team bills weeks for 100 verified company profiles. he gets them in one run one model writes, a cheaper one decides, and nothing ships until it says yesshow more

We (Claude and I) made a new package: voxmlx... It's an MLX implementation of Mistral's Voxtral mini realtime speech recognition model. It supports streaming audio and runs pretty fast on a laptop. To use it, simply: `uvx voxmlx` Also I did not write a single line of code for this package. Every line of code was written by Claude Code. More on that in thread.show more

this is pure f*cking treasure A Stanford AI research... group finally drew the perfect RAG system: retrieval, Jev and agents in one loop, and it fixes the 3 things that break every RAG app: > the LLM reads 20 passages when only 3 matter > it answers questions your docs can't answer > it trusts whatever text it retrieves here's how it runs: > a lead agent sends the query > hybrid search pulls the top 20 candidates, dense + keyword > ONE Jev request scores all 20 + 2 gates: answerable? injection? > only passages above 0.6 reach the writer agent > a second Jev call checks every claim against its source > grounded answer, with citations and when the docs don't have it: > answerable fails, the writer never runs > a researcher agent rewrites the query and retries once > still nothing? "not in the docs". zero tokens spent on a guess retrieval casts the net. Jev decides what's real. agents do the work save this before you build your next RAGshow more

✅ BENCHMARKED: TensorFold made Qwen3.8 27B more than 3x... faster on my 64GB M5 Pro Mac mini, on two versions in one day. In the morning I tested 1.2.1. On its own, the model wrote about 17 tokens a second. I then switched on the DFlash2 drafter, a small helper that guesses the next few tokens so the big model only has to check them and it jumped to 56. And later in the afternoon Ash Hart shipped 1.2.2. His release notes focused on other hardware, so I reran everything on my Mac mini. On mine it runs within a few percent of 1.2.1, and the drafter still makes it 3x faster. With randomness off, the answer came out word for word the same as without the drafter. - Chat, 3.26x faster on 1.2.1 and 3.35x on 1.2.2 - A 31K token prompt, 2.94x and 2.77x - Code, 5.4x and 5.5x, up to 91.90 tokens a second - 28.5 GiB peak memory on both - New in 1.2.2, the first request doesn’t wait for the drafter to load A massive thanks to Ash Hart and all the contributors behind 1.2.2. The TensorFold challenge from Yukon is open until Nov 6th if you want to try pushing it further on your own Mac.show more

Nace shows Drex playing a strategy game. i gave... it a harder opponent: my timeline Spoiler Guard sends each post to the new decision model and blurs the spoilers, 352 post checked in one session with sub-second calls → 128K context window, per Nace the first and only decision model at that size → #1 on the Decision Index, a Jev rival for $0.04 per 1M input tokens → no text generated, just a probability per post try it with 250M free tokens from Nace AI:show more

I couldn't f*cking believe this Stanford AI research team... gave Grok Bot a human brain setup. JEV is the fast gut brain. It scans everything in milliseconds and makes the easy calls. Grok is the slow thinking brain. It only wakes up for the hard ones. Here are the commands that wire the two together: /plugin marketplace add rashedInt32/jev-mcp /plugin install jev@jev-mcp → Grok gets Jev as tools: classify, score, check npm install -g @dzhng/jevgrep jg "how are payments retried?" ./my-project → ask what the code does, get the right files back. the author measured ~30% lower cost on the same tasks npx skills add altryne/jevify --skill jevify → teaches your agent to hand the bulk yes/no work to Jev on its own > and fast-jev-compaction swaps Grok bot’s summary for Jev decisions: it drops stale tool calls and keeps everything else word for word. Faster runs, smaller bills, barely any compute wasted. Save this before your next session, then read the full guide below:show more

so we already have an open source alternative to... jev... and it's 6-7x faster?! it's a typed-decision classification system: no chat, no generated text, just fast yes/no, scoring, or choice answers. > runs in under 1gb of memory > free on hugging face > runs on a laptop, or even a phone there's a real demo where it plays snake live, making a fresh decision every single move. two honest limits, straight from the project itself: > only 512-1,024 token context, some cases won't fit > weaker generalization than jev out of the boxshow more

Jev dropped and people immediately started doing stupid sh*t... with it people gave this thing trading bots, browsers, Doom, drones, dinosaurs and tax forms and basically said: “you decide.” here’s what happened: > jev-trader Jev gets a new Monad block every ~300ms and decides whether to place a live limit order. no essay. just the decision. 1,911 stars ▸ ⁠ > jev-ultrafast a browser agent where Jev decides every click. the text model only wakes up when something actually needs to be written. 16,758 stars ▸ ⁠ > jev-doom-agent someone compiled actual Chocolate Doom to WebAssembly and let Jev make the tactical decisions every frame. yes. Doom. ▸ ⁠ > jev-t-rex-runner remember that stupid Chrome dinosaur? now Jev plays it. jump → duck → run → repeat ▸ ⁠ > typesafe-chess Jev went against a real chess search engine. two games. colors swapped. the search engine won both — and overruled Jev’s first instinct on roughly half the moves. ▸ ⁠ > jev-drone camera → Jev → drone. a simulated quadrotor has to clear five stations while Jev looks at the situation twice a second and decides what happens next. ▸ ⁠ > tax-doc-classifier then someone gave it IRS forms. 261 documents. 100% strict accuracy. roughly $0.001/page. ▸ ⁠ > killmyidea this one is evil lol tell it your startup idea. Jev looks at it from different angles and gives you: KILL / FIX / SHIP ▸ ⁠ > jev-curate throw huge Parquet / JSONL datasets at it. Jev judges 1,500+ rows/sec and keeps only the stuff that passes your rules. ▸ ⁠ > pg-jev and now it’s inside PostgreSQL. ask questions about your own tables in plain English → get the decision back. ▸ ⁠ and this is the weird part: none of these need Jev to write you a beautiful paragraph. they need it to look at a situation and pick: BUY / WAIT CLICK A / CLICK B JUMP / DUCK KILL / FIX / SHIP KEEP / DROP that’s basically the whole Jev idea. LLMs think and write. Jev decides. code does. full setup + my three-question Jev test belowshow more

ASI Alliance’s new open AI picks an answer and... says how sure it is Singularity Compute, which runs on SingularityNET's tech, released Super Decider, a model that anyone can download and use for free under an open license. Instead of writing text, it picks from options a developer sets, such as which team should handle a support ticket, and gives each option a probability in about 0.3 seconds. The model is live on ASI:Cloud (ASI:Cloud). In the company’s own testing, it scored 85.6 on NVIDIA’s When2Call benchmark, ahead of TypeSafe’s Jev and Cloudflare’s Clef, but 1.6 points behind Clef on a tool-selection test.show more