typesafe's jev is fun! live demo you can play with: typesafe-demo.val.run
PrimitivesChoice question
Choice
Pick one option from a set you define; returns the selected option, a probability for every option, and confidence.
- Category
- Primitives
- Also known as
- Choice question
- Related terms
- 6
- Directory entries
- 8
- Docs
- docs.typesafe.ai
- Added
- 2026-09-24
Definition
A Choice question takes a map of options to rubric descriptions and returns the highest-probability option, the full probability distribution, and a 0-1 confidence. A Choice can hold up to 255 options, so large candidate sets need pre-filtering or multiple passes.
Option names and descriptions are both sent to the model; use null when a name speaks for itself. Choice fits answers that are one of a known set with no order between them — routing a ticket, classifying a document, detecting a language — and an explicit other or none-of-the-above option is recommended when the list might not cover every input.
Tagsprimitivesclassification
Related terms
Definitions that connect to this one.
ScoreRate the state against 2 to 10 ordered levels; returns a probability-weighted position, per-level probabilities, and confidence.PrimitivesNoulThe yes/no primitive: one probability from 0 to 1, where the value is the answer and no separate confidence is returned.PrimitivesChoice optionOne key in a Choice criteria map, with a description that can be a string, a structured object, or null.PrimitivesCriteriaThe possible answers for a question: a map of options for Choice, an ordered list of levels for Score, or true/false for Noul.PrimitivesProbability distributionThe floats summing to 1 across your options or levels that every Choice and Score answer returns under probabilities.Answers & ConfidencePrimitive limitsThe hard caps to design around: 255 Choice options, 2 to 10 Score levels, and a 64k context covering state plus questions.Primitives
From the directory
Pick one option from a set you define. Returns the option, the full probability distribution, and 0-1 confidence, with up to 255 options and parallel questions that barely add latency.
Practices & PatternsDocs#official#primitives#choice
Official
The three TypeSafe question types, the typed answers they return, how to choose between them, and how to ask several in a single call.
Practices & PatternsDocs#official#primitives#choice
Official
Two browser games against a live Jev opponent: a first-person quick-scope arena and a neon survival challenge, where Jev picks tactics and authored code handles movement and physics.
Cookbooks & DemosPlayground#community#playground#games
Community
Four board games against Jev where the model picks the move and code keeps the rules: tic-tac-toe, Connect Four, Battleship, and Wordle.
Cookbooks & DemosPlayground#community#playground#games
Community
An autonomous Pac-Man recreation steered by Jev: before each junction the game sends the maze, actors, and legal directions as structured data, and Jev returns one direction with a probability per option.
Cookbooks & DemosPlayground#community#playground#games
Community
A playable Tetris where you can drop pieces yourself or let the TypeSafe Choice primitive pick every move.
Cookbooks & DemosPlayground#community#playground#games
Community
2 more matching entries in the full directory.
From the community
Posts from builders shipping with Jev right now.
A playable 16-judgment demo
AI multiple choice, not essay writing
WTF is Jev by @typesafeai? Here’s the tl;dr ELI5: Think AI multiple choice, not AI essay writing. It doesn’t chat. It makes decisions your software can act on: “Spam or not?” “Which tool should this agent use?” “Does this need a human?” The exciting part: roughly 200x faster Show more
Screening agent actions with Jev
Tested TypeSafe’s Jev (no-text, probability-only model) as an AI agent safety monitor. Checking each action first worked well caught most attacks with almost no false blocks, and much faster than Gemini.
@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
Cua's small System One models
1/ Introducing CUA-S1: a family of System One Models, small, specialized, and built for computer use. Today we're open-sourcing CUA-S1-FORMS, the first in the family: github.com/trycua/cua
A 706K-parameter form filler
cua open sourced a 706k param model that fills a whole form in one 50ms pass the llm agent doing the same form took 23 turns and 39.6 seconds the specialists are going to eat the generalists from the bottom
1/ Introducing CUA-S1: a family of System One Models, small, specialized, and built for computer use. Today we're open-sourcing CUA-S1-FORMS, the first in the family: github.com/trycua/cua
Navigating Neo4j with Jev
Jev 这个 waitlist 还是很给力的，昨天申请，今天就能用上。 给已经拿到 API、但还不知道怎么玩的人整理了一份 Awesome Jev，目前我能确认到的 Jev 项目基本都在这里： 1. jev-ultrafast Browser Use 做的高速浏览器 Agent。Jev Show more
前 OpenAI 研究员 Diogo Almeida 创办的 TypeSafe AI 推出新模型 Jev。它有点像一个能读懂自然语言的超级分类器，不生成文本，只返回选项、分数和概率，专门给软件做判断。 普通大模型需要一个 token 一个 token 往外生成，Jev 则可以并行给出多个结果。TypeSafe 还用新的 RLCD