TL;DR of my new article: WTF is Jev by @typesafeai, and the 9 things people are already building with it. The thesis: 𝗮 𝗰𝗼-𝗰𝗿𝗲𝗮𝘁𝗼𝗿 𝗼𝗳 𝗖𝗵𝗮𝘁𝗚𝗣𝗧 𝘀𝗽𝗲𝗻𝘁 𝘁𝘄𝗼 𝘆𝗲𝗮𝗿𝘀 𝗶𝗻 𝘀𝘁𝗲𝗮𝗹𝘁𝗵 𝗼𝗻 𝗮 𝗺𝗼𝗱𝗲𝗹 𝘁𝗵𝗮𝘁 𝗰𝗮𝗻𝗻𝗼𝘁 𝘄𝗿𝗶𝘁𝗲 𝗮 Show more
x.com/i/article/2100…
Core ConceptsSystem One model
System One
The class of AI models built to make fast, structured decisions software can use directly, named after Kahneman's fast-thinking System 1.
- Category
- Core Concepts
- Also known as
- System One model
- Related terms
- 5
- Directory entries
- 4
- Docs
- docs.typesafe.ai
- Added
- 2026-09-24
Definition
A System One model understands natural-language input like an LLM, but returns typed decisions and probabilities rather than generated text. You define the possible answers through the Choice, Score, and Noul primitives, and the model never invents a value outside them.
The name comes from Daniel Kahneman's Thinking, Fast and Slow: System 1 thinking is fast and intuitive, System 2 slower and more deliberate. System One models emphasize fast, focused judgments inside a larger code-owned workflow.
Tagscorearchitecture
Related terms
Definitions that connect to this one.
JevTypeSafe AI's flagship model and the first System One model: typed decisions and calibrated probabilities instead of generated text.Core ConceptsAI primitiveOne of TypeSafe's small, typed building blocks — Choice, Score, Noul — that pair a question with a typed answer you compose in code.Core ConceptsTyped decisionA model output that conforms to a software type your code expects, rather than free-form text that has to be parsed.Core ConceptsSystem Two taskWork that needs extended, multi-step reasoning; the docs treat it as a signal to decompose rather than a job for Jev.Core ConceptsAI-powered softwareThe architecture TypeSafe recommends: code owns the workflow and the model appears only where programmable common sense is needed.Core Concepts
From the directory
The idea behind Jev: models that return typed decisions and probabilities instead of generated text, named after Kahneman's fast-thinking System 1, with confidence to route around uncertainty.
Sites & GuidesDocs#official#docs#architecture
Official
The canonical introduction: Jev is TypeSafe's flagship model and the first System One model. Send state and typed questions, get structured answers your code can use directly.
Sites & GuidesDocs#docs#official#primitives
Official
The launch story: why TypeSafe built decision models, the side-by-side demo, the Doom and Wikiracing bots, and the published workflow evals.
Sites & GuidesArticle#official#announcement#benchmarks
Official
TypeSafe AI's official launch post: the company is out of stealth and developers can get access to Jev from the website, alongside the founder's launch thread.
Sites & GuidesPost#official#x#launch
Official
From the community
Posts from builders shipping with Jev right now.
WTF is Jev, and 9 things people are building
Voice-controlled computer use on a Mac
I built a voice controlled computer-use for my mac using @typesafeai's Jev and it's INSANE how fast it is! I can dictate "open the notes app and create..." and the app opens before I even finish my sentence.
The use cases Jev unlocks
You still don't understand the use cases Jev unlocks. I've been waiting for something like this since early ChatGPT models. prediction: we will see the fastest-growing SaaS by MRR in history within the next month or two
19 open-source Jev projects
一个只会做选择题的小模型，能长出多少玩法？ TypeSafe 的 Jev 就是这么个东西：给它最多 255 个选项，几百毫秒挑一个，再附一个校准过的置信度，输出 token 免费 结果开发者们已经拿它做出了 19 个开源项目，加起来 6800 多星 挑几个最有意思的 jev-ultrafast，browser-use 出品，2700 星，一句 Show more
Jev Calc: a notebook that calculates anything
i made a smart calculator notebook using jev it can calculate ANYTHING!! 😅
Day-one notes from a skeptic, in Chinese
一些关于 Jev (@typesafeai) 的 notes 研究了一天 Jev，带来的新鲜感迅速回落，这好像就是一个更快的通用分类器/决策器，LLM 完全可以做到。 而且因为不了解模型背后的参数规模（应该不会很大），世界知识可能不一定有常规 LLM Show more
@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