Jev is WILD I gave it two launch tweets and fed it over 4000 demographic profiles of real survey participants Twelve seconds later, a simulated A/B test tied to actual personas voting on the best tweet you can just do things i made it 100% free (link below)
CommunityPractices & Patterns
Jev: The Language Model That Won't Talk
A critical technical read of Jev's launch claims that digs into the calibration and eval numbers and asks what the architecture keeps secret.
- Category
- Practices & Patterns
- Format
- Article
- Published by
- Community
- Author
- Anthony Maio
- Added
- 2026-09-25
- Last verified
- 2026-09-25
Highlights
- Cites TypeSafe's own eval: Jev averaged 67.8% agreement at $0.0004 and 0.4 s against 67.9% at $0.0304 and 10.1 s.
- Notes Jev trailed GPT Sol at 74.1% and Claude Opus 5 at 73.1%, and on invoice processing 61.8% versus Sol's 79.1%.
- Points out the reference labels averaged two other models rather than operational ground truth, on TypeSafe-designed workflows.
- Argues that cannot-hallucinate constrains the output shape, not the quality of the judgment.
Watch out
The author works from secondary sources and says so, asking for independent testing; some of the confidence-derivation analysis is speculative.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: An A/B test against 4,000 personas
X: Ad creatives from filtered assets
Jev is really good at content filtering and asset selection. DeepSeek + Higgsfield turn the selected assets into ad creatives.
X: A shortlist from a competitor swipe file
JEV makes competitor research feel like a cheat code. Give it your competitors’ ads. Break them down by hook, angle, offer and format. Then turn recurring combinations into a shortlist for your next creative test. From an endless swipe file to “here’s what we should try next.” Show more
x.com/i/article/2101…
X: 1,315 posts across eight dimensions
Jev classified 1,315 X posts for about $0.086 in estimated model cost 😂 seeing everyone's Jev demos made me want to build something for my own content research. i'd collected a lot of posts, but figuring out what they had in common still meant opening them one by one and 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
More like this
133GitHub stars
Independent cross-model benchmark for Jev-class decision models, running 534 frozen cases per complete entrant with scoring code and a four-axis score of accuracy, calibration, latency and cost.
Practices & Patterns#community#python#benchmarks
Community
fstandhartinger/jevbenchPython
fstandhartinger/jevbenchPython89GitHub stars
An experiment comparing Jev with GPT-5.6 Luna, GPT-5.6 Terra, and Claude Sonnet 4.6 as evaluators of five frozen weather-agent runs, measuring pass-or-fail accuracy against human labels plus variance, cost, and latency.
Practices & Patterns#community#python#evaluation
Community
danielgshea/jev-as-a-judgePython
danielgshea/jev-as-a-judgePython39GitHub stars
Side-by-side benchmark of TypeSafe Jev, Qwen 3.8 27B on Cerebras, and a local Needle 3 across seven synthetic workloads, recording validated outputs, mistakes, latency, tokens, and estimated cost. Raw exports and per-scene limitations are published.
Practices & Patterns#community#typescript#benchmarks
From the community
Posts from builders shipping with Jev right now.
Six uses that stuck after 60 days
I've been using Jev by @typesafeai Here's the six things i've tried and am confident I'll still use Jev for 60 days from now. There's many more experiments, ideas, and things I think I will use it for. It's a big deal (more on why in next post). But I am only sharing things Show more
Security decisions that fit Jev
This made me rethink where AI actually fits into security engineering. For purely engineering work, forget about ChatGPT or Claude. TypeSafe AI just released Jev, and I think it’s going to change how we build AI into security workflows. Instead of asking an LLM to “investigate Show more
we are officially out of stealth! join the frontier and get access to Jev on our website (link on profile)
A million judged questions
Ask Jev anything. Give it a try at askjev.ai It won't answer. It will judge. Let's see if we can get to 1 million questions. @typesafeai 🤝 @convex work great together. @hmartenjoyer @CompleteSkeptic @justKDeng @mikeysee
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…