Damn, the emergence of JEV is very likely the starting
Built a trading bot where Jev reads MON/USDC prices and returns Buy or Sell with confidence, executing on Kuru's on-chain order book every 300ms block.
The original post, translated
Damn, the emergence of JEV is very likely the starting point of automated intelligent trading.
Yesterday JEV was flooding AI circles, and today a Monad engineer used JEV to build an automated trading bot.
It reads the MON/USDC price in real time. JEV is not responsible for writing analysis reports, nor does it explain a bunch of logic to you. It only does the most core thing: decide Buy or Sell, then give a confidence level, and then directly send the trade to Kuru's on-chain order book for execution.
All of a sudden I understood why JEV was made into a model that does not speak.
Trading simply does not need AI to write you a little essay every 300ms. What it needs is:
market data comes in -> decide -> place order -> new market data -> decide again, and this entire loop must be fast enough and cheap enough.
And Monad right now happens to produce a block every 300ms, while Kuru is also an on-chain order book. The high-performance chain handles execution, JEV handles decisions. Put the two together, and it already has a bit of the flavor of an AI-native trading system.
The trading Agent of the future does not necessarily need a super large model that can write research reports. It more needs a brain that can continuously make millions of judgments at extremely low latency.
Yesterday the WL I submitted also passed today. Next I will first give it a taste and see what exactly is going on.
Show the original post in its source language ▾
卧槽，JEV 的出现很可能就是自动智能交易的起点。
昨天JEV在AI 圈刷屏，今天 Monad 工程师就用JEV做了一个自动交易机器人。
实时读取 MON/USDC 价格，JEV 不负责写分析报告，也不跟你解释一堆逻辑，它只做最核心的事，判断 Buy 还是 Sell，再给出置信度，然后直接把交易发到 Kuru 的链上订单簿执行。
这一下我突然明白 JEV 为什么要做成一个不会说话的模型了。
交易根本不需要 AI 每 300ms 给你写一篇小作文，它需要的是：
行情进来→判断→下单→新行情→重新判断，而且这一整套循环必须足够快、足够便宜。
而 Monad 现在刚好每 300ms 出一个区块，Kuru 又是链上订单簿。高性能链负责执行，JEV 负责决策，两个东西拼起来，已经有点AI 原生交易系统的味道了。
未来的交易 Agent，不一定需要一个会写研报的超级大模型，它更需要一个能在极低延迟下连续做几百万次判断的大脑。
昨天我 提交的WL今天也通过了，接下来我先尝尝咸淡，看看到底怎么个事。
The post above is a machine translation from zh; the untranslated text is in the fold-out.
Quoted post
@oragnes543K viewssource卧槽，今天 AI 圈最火的模型，应该就是 JEV 了。 现在所有大模型都在拼更会说话、更会写、更像人，JEV 直接反着来，它根本不生成文字，只负责做判断和决策。 我已经迫不及待用JEV帮我决策自动交易股票和加密货币了😂 官方给的数据非常夸张：20—200 倍更快，40—400 倍更便宜，输入每百万 Token 只要
From the same thread
- @sandyluo459 — 这两天 AI 圈最离谱的事： 一个不会说话的模型火了。 它叫 JEV。不能聊天，不能写代码，不能解释自己。你问它，它只回你三样东西—— 选哪个。多少分。多大把握。 就这。发布当天直接炸。 凭啥？因为它快得不像话：比主流模型快 20–200 倍，便宜 40–400 倍。 同样一个判断，别人花 3 分钱、等 10 秒；它花 0.0004 美元、0.4 秒。 差距是两个数量级。
Engagement when collected
Numbers are a snapshot taken from X when the case was added to the library (schema v1, collected 2026-09-19); they will not match today.
Where this case fits
Filed under agents & workflows. In the pattern Jev is built for, the model answers a bounded question per step — and ordinary code acts on the answer, because the answer is already a value rather than a paragraph. Other posts in the same family are on the agents & workflows page.
Related Jev cases
found the perfect use case for @typesafeai Jev: instant
Agents
Breaking: Browser Use + Jev = Ultrafast Findings flights
AgentsBrowser agents
Jev case: in 40 seconds it broke down 724 live ads from 37
WebsitesAgents
We tested Jev against LLM judges on accuracy
Agents
Keep browsing: all 1173 Jev cases · more from @oragnes · builders · what Jev is
Last updated: 2026-09-22 · sources & corrections · every card links to its author's original post