WHAT NEW IN X11.06 FRI

AI collections from X · 23 collections · 69,408 posts

jevIMAGE

mu-agent embeds Jev in the harness to settle 35 decision points locally in about 0.3 seconds

The author describes how mu-agent deeply embeds Jev in the harness to handle 35 micro-decision points such as new task vs. correction, output selection, and command validation, executed locally by Laya in about 0.3 seconds, with desktop, npm, and GitHub ways to get started.

SuSu_酥酥👅
@NFT_ChenArchived 2026.09.27Originally posted 2026.09.26
mu-agent embeds Jev in the harness to settle 35 decision points locally in about 0.3 seconds (image 1 of 3)
mu-agent embeds Jev in the harness to settle 35 decision points locally in about 0.3 seconds (image 2 of 3)
mu-agent embeds Jev in the harness to settle 35 decision points locally in about 0.3 seconds (image 3 of 3)
SuSu_酥酥👅 @NFT_ChenOriginally posted 2026.09.26
Open original on X

💥厉害了!0.3秒拍板,大模型终于不当保姆了!将Jev深度融合进Harness,让 Jev 和 Laya 兼而得之! 大模型是发动机,Harness 才是整台车。每一轮对话里那几百个没人认真做的小决定,终于有人接了,本地执行走 Laya,判定又快又稳。 核心亮点: 🔹Jev 接管 35 个判定点:新任务还是纠错、输出哪几块有用、命令是不是你要的、做完验过没有——一次约 0.3 秒,几乎无感。 🔹本地由 Laya 执行:微决策不下放到大模型,本地 Laya 直接拍板,延迟更低、成本更稳 🔹上下文只留这一步:无用技能/MCP 不进场,工具输出逐块过滤,重复日志直接折叠,过期结果直接扔掉 🔹干活和说话拆成两套模型:Jev 挑出真正的新消息,交给会说人话的模型(如 Claude Opus 4.6)讲给你听,人话不污染干活上下文 🔹蜂群中间加闸门:多只「蜂」分头查,Jev 决定说不说、告诉谁、前后对不对得上,把最该传的信息交给最需要它的子 agent 怎么上手: 1️⃣桌面端:macOS / Windows / Linux 直接装 2️⃣命令行:npm i -g mu-agent 3️⃣GitHub:https://github.com/qybaihe/mu 模型越强,越不该把微决策也扔给它。Jev 进 Harness,本地 Laya 执行,车才真正能开。 #Jev #Laya #Harness #AIAgent #黑客松 #mu #进化酒馆 #TypeSafe #多智能体

This post quotes another post: “Stanford and Nvidia's CLM beats Jev by 4-13x on decision speed”

x.com/nft_chen/status/2103741553126805531Archived 2026.09.27 10:11