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
jeff
A self-hosted implementation of TypeSafe's Jev System One API powered by the 400M-parameter GLiFormer encoder: it serves choice, score, and noul and drops into the official typesafe-sdk via TYPESAFE_BASE_URL, but trails Jev on reasoning-heavy tasks.
- Category
- Practices & Patterns
- Published by
- Community
- Author
- logan-markewich
- Added
- 2026-09-22
Tagscommunitypythonopen-modelsbenchmarksevaluation
Highlights
- Serves choice, score, and noul on a 400M-parameter GLiFormer encoder; the official typesafe-sdk works by pointing TYPESAFE_BASE_URL at it.
- Measured HTTP throughput caps at about 50 requests/s per Modal container, and an A10G outperforms an L4 for direct backend calls and long requests.
- Its benchmark write-up is close on binary sentiment and tied on emotion, but behind Jev on irony, reading comprehension, and the judge and hard tiers.
- Request limits default to 64 questions, 64 labels, and 20,000 state characters, with per-key rate limiting and batching at 16 items and 5 ms waits.
- Quickstart needs Python 3.12 and uv; the server picks CUDA, then MPS, then CPU, and the CPU fallback is reported slower and more expensive than Jev.
Quickstart
bash
uv sync --extra dev
uv run hf download knowledgator/gliformer-large-v1 --local-dir models/gliformer-large-v1
JEFF_API_KEYS=devkey uv run jeffWatch out
MIT-licensed. Needs Python 3.12, uv, and a local GLiFormer checkpoint downloaded from Hugging Face; hosted cost figures are estimates that depend on deployment throughput.
More like this
3.6kGitHub stars
An independent baseline that reads typed option probabilities straight from a frozen Qwen3.5-4B's logits in one forward pass, reproducing Jev's interface pattern with open models rather than Jev's undisclosed model or training.
Practices & Patterns#community#python#open-models
CommunitySemIf
3.2kGitHub stars
Apache-licensed, locally runnable Jev-style decision models (0.8B, 4B, 9B on Qwen3.5) with released weights, training code, a System One-compatible server, frozen eval suites, and a playground.
Practices & Patterns#community#python#open-models
Communitykev
296GitHub stars
An independent open reproduction of the System One model class: Qwen3.5-based 2B and 35B mixture-of-experts models that return typed Choice, Score, and Noul probabilities in one forward pass, with nothing distilled from Jev.
Practices & Patterns#community#python#open-models
Communitydecider
From the community
Posts from builders shipping with Jev right now.
AI multiple choice, not essay writing
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
Reranking 33,047 catalog entries
拿 Jev 做搜索重排，我先泼一盆冷水：单独用，它没打赢向量检索 TypeSafe 的 Jev 这阵子很火，一堆项目拿它做重排。我们在 Agent Skills Hub 的 33,047 条目录上认真测了一次，164 条中英文真实查询，9,831 对分级标注，整套只花了 2.6 美元 三个结论 01｜单独重排，约等于没赢 Jev 重排 bge-m3 Show more
有美团、阿里的老哥嘛？ 试试加一路召回、重排（离线、近实时实现），我觉得有奇效 他在文本理解上 跟之前机器学习、llm很不一样 还能自动打标签做特征