x.com
Nitor on X: 这几天 X 上一直刷到 Jev。
@yuntian9999@yuntian9999listed 47m agoreviewed by Jev这几天 X 上一直刷到 Jev。 最反常的一点是：它根本不写字。 TypeSafe AI 把 Jev 定义成第一款公开的 “System One Model”： 你给它一段状态 + 几个明确问题，它不生成长文，而是直接返回选择、评分、概率和置信度。 官方价格： $0.042 / 100万输入 tokens，输出免费。 TypeSafe 还声称，在它针对 System One 任务的工作流里，Jev 可以做到 20–200× 更快、40–400× 更便宜。 注意，这是厂商自己的特定任务测试，不是“全面吊打 GPT”。 所以我觉得它不是 GPT / Claude 的替代品。 更像是给 Agent 加一个“判断层”： GPT / Claude 写和规划 → Jev 判断 / 路由 → 代码执行 真正值得看的不是又一个新模型。 而是 AI 开始分工了。 ❤️ 0 likes on X
- Author
- @yuntian9999
- Use case
- Benchmarks & Evals
- Added
- 2026-09-25
- Cost
- $0.042
All figures come from the author. Check the source before you quote them.
More in Benchmarks & Evals
- Morgan on X: It has been a really interesting experience to build an eval suite for System On▲ 0x.com
- silentguy on X: Grok Bot does the job, Jev decides where the job goes next▲ 0x.com
- spect on X: The founder of Jev just dropped a 1-hour masterclass on how Jev actually works▲ 0x.com
- Dain on X: A beautiful pattern can still be noise.▲ 0x.com
- Utkarsh Maheshwari on X: Is the Jev hype real,▲ 0x.com
- OpenMed on X: Four typed questions across four authored fictional notes, labels written before▲ 0x.com
Jev guides for this use case
- Using Jev as a judge for evalsGrading with a decision model instead of a prose-writing judge, and why calibrated confidence is the real prize.
- How Jev sorts a build into one of 21 use casesThe 21 criteria Jev classifies against, published in full, plus what the reviewer sees and how ambiguity is handled.
- Jev statistics: latency, cost, and this directory's own numbersPublished benchmarks with their caveat attached, plus live directory figures that update automatically.
Bid history
No bids yet — the first one takes this project straight to the spotlight.