Harness: I made Jev control the player, has access to WASD, space, click, and mouse movements. Astra is the planner that sends instructions to Jev async. Learning: Each time the agent would fail, Astra would add skills as mjs files, that it can draw upon in different scenarios, Show more
CommunityDemos & Experiments
Jev Calibration game
Sixteen true-or-false statements you answer, then Jev answers with a Noul probability. Keeping only its confident calls is the point of the game.
- Category
- Demos & Experiments
- Format
- Playground
- Published by
- Community
- Author
- —
- Added
- 2026-09-28
- Last verified
- 2026-09-28
Highlights
- You answer 16 true-or-false statements. The first shown is whether a tomato is botanically a fruit.
- Jev answers each one with a Noul. The sample reads P(true) and sets confidence to max(p, 1-p).
- The page says keeping only the high-confidence answers pushes accuracy toward 100%.
- A sample decision on the page: the Great Wall claim, answered no at 6% in 191 ms.
Watch out
Independent site, not TypeSafe, and not the AnthusAI calibration study. The accuracy claim is the site's description of the demo. The sample client posts to jevtypesafeai.com/api/v1/decide.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
Hacker News: Show HN: a mouse colony where each next move is Jev or a fixed rule.
1 pointShow HN: Jev-mice – mouse colony simulation using Jev and deterministic engineRead the thread on Hacker NewsHacker News: Show HN: OpenDecision, a local decision model with a Doom demo.
dwa35926 pointsShow HN: OpenDecision – a 400M zero-shot model makes local decisions, plays DoomRead the thread on Hacker NewsX: Jev plus Astra beats the Ender Dragon for under a dollar
X: Jev plays Pokémon Showdown
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.
More like this
A live 2048 board on an independent Jev site. Each move is one Choice over the four directions, with a decision counter, latency, and a running cost.
Demos & ExperimentsPlayground#community#games#playground
Community
A live Tetris board where each piece is one Jev Choice over the legal placements, with latency and cost shown as the pieces drop.
Demos & ExperimentsPlayground#community#games#playground
Community
A Wikipedia race you play against Jev. From the same start article, each hop is one Choice over that page's outbound links.
Demos & ExperimentsPlayground#community#games#playground
Community
From the community
Posts from builders shipping with Jev right now.
Inferring Jev's internals from 1,000 calls
Jevの内部アーキテクチャを推測している技術記事(Jev’s Architecture Unmasked)からメモ。 ・本記事はJevのAPIを約1万回の呼び出して、内部構造を推測したもの ・従来の言語モデルを用いた分類やルーティングでは、トークンを1文字ずつ逐次生成するために膨大な無駄な計算コストが発生していた。 Show more
The open System One roundup
Jev 发布没几天，开源社区已经开始疯狂复刻了🔥 最值得推荐的五个模型： 1、Laya 421M：原生决策模型，支持 Mac 2、Decider-2B：最像 Jev，基于 Qwen3.5 3、NanoJev 0.6B：专门的 Decision Head 4、Reflex：Qwen3.5 + Direct Logits 5、System-One 4B：专门做概率校准 Show more
Jev 刚发布没几天，开源社区就出现了同款🔥 Decider-2B模型，是基于 Qwen3.5-2B 做了特殊调整 它和 Jev 模型是一样的 只做选择 评分和判断 不是文本类的 LLM 模型 但两者还是有几个明显区别： 1、模型 Jev：闭源 System One Model Decider：Qwen3.5-2B，约 1.9B 参数，Apache 2.0 开源 2、价格
Jev lands on the Vercel AI Gateway
Jev is now available on the @vercel AI Gateway vercel.com/ai-gateway/mod…
Vercel ships the AI SDK provider for Jev
Jev from @typesafeai is on AI Gateway. Build agents that decide, route, score, and stop in milliseconds: 𝚊𝚠𝚊𝚒𝚝 𝚎𝚟𝚊𝚕𝚞𝚊𝚝𝚎({ 𝚖𝚘𝚍𝚎𝚕: '𝚝𝚢𝚙𝚎𝚜𝚊𝚏𝚎-𝚊𝚒/𝚓𝚎𝚟', 𝚜𝚝𝚊𝚝𝚎, 𝚚𝚞𝚎𝚜𝚝𝚒𝚘𝚗𝚜, }); vercel.com/changelog/type…
Computer use at 155× cheaper than Opus 5
i 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:
@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
Foreman keeps coding agents on task
I just open sourced Foreman: a software factory foreman built with @typesafeai's Jev. Coding agents work the factory floor. Foreman watches them, continuously assessing progress, completeness, tests, drift, and verification, and intervenes when needed. GitHub: Show more