Holy crap, this JEV direction is really something else.
Highlighted a Monad developer's open-source AI-native on-chain trading system built on Jev, which lost over 300% in a 14-hour demo.
The original post, translated
Holy crap, this JEV direction is really something else. Monad developer @jarrodwatts directly turned it into a pure AI-native on-chain automated trading system, with both the code and frontend fully open source. The demo ran for 14 hours and lost over 300%; don't look at the returns for now, the architecture is truly brutal. I've also messed around with GPT/Claude for trading decisions before, and the most annoying thing is that it first spews out a bunch of essays, and engineers still have to dig through the nonsense
Show the original post in its source language ▾
卧槽，JEV 这个方向真有点离谱。 Monad 开发者 @jarrodwatts 直接把它做成了一套纯 AI 原生链上自动交易系统，代码和前端全开源。 演示跑了 14 小时，亏了 300% 多，收益先别看，架构是真狠。 我之前也折腾过 GPT/Claude 做交易判断，最烦的就是它先给你吐一堆小作文，工程师还得从废话里抠
The post above is a machine translation from zh; the untranslated text is in the fold-out.
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 general Jev builds. 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. Browse the full case library for the work it sits next to.
Keep browsing: all 1173 Jev cases · more from @nice11018 · builders · what Jev is
Last updated: 2026-09-22 · sources & corrections · every card links to its author's original post