Vlad Luzin
① 他说过的话
13 条
我们的论点是:未来属于 AI 通信——企业内部、企业之间、以及消费者与企业之间的通信。
指向原始笔记的链接
So our thesis is future belongs to AI communication within a business, between businesses and between consumers and businesses.
—— Vlad Luzin · [01:10]
你基本上是在充当一个路由器,一台 Cisco 路由器或交换机,在两个代表你工作的有状态智能体之间,但它们没有能力相互通信,所以你需要给它们提示。
指向原始笔记的链接
You are basically acting as a router, a Cisco router or a switch between two stateful agents that do work on your behalf, but they have no ability to communicate, hence you need to prompt them.
—— Vlad Luzin · [03:23]
如果你想要两个智能体保持状态、有粘性会话,那祝你好运。
指向原始笔记的链接
If you want two agents to be stateful, sticky sessions, good luck to you.
—— Vlad Luzin · [04:42]
它们处于数字化的单独监禁之中。
指向原始笔记的链接
They are in a digital solitary confinement.
—— Vlad Luzin · [06:21]
而一个每个智能体都是远程的多智能体系统,基本上就是一个微服务的分布式系统,只不过每个微服务都是非确定性的。
指向原始笔记的链接
And multi-agent system where every agent is remote is basically a distributed system of microservices where each microservice is non-deterministic.
—— Vlad Luzin · [07:51]
所以为了实现智能体相互交谈的这个美好未来,我们需要把技术栈的抽象层次提升到会话这一层。
指向原始笔记的链接
So for this wonderful future of agents talking to each other, we need to raise the abstraction of the technical stack to conversation
—— Vlad Luzin · [08:52]
AI 将代表我们做工作,它们将不得不互相交谈,以便代表我们解决任务。
指向原始笔记的链接
AI will be doing work on our behalf and they will have to talk to each other in order to solve tasks on our behalf.
—— Vlad Luzin · [01:02]
你基本上就是一个 Cisco 路由器和交换机,在这两个有状态的智能体之间传递数据包。
指向原始笔记的链接
You are basically a Cisco router and a switch moving packets between these two stateful agents.
—— Vlad Luzin · [02:40]
所以一百万 token 或两百万 token 的上下文,在性能方面不会帮到你。
指向原始笔记的链接
So one million tokens or two million tokens, context will not help you in terms of the performance.
—— Vlad Luzin · [03:56]
所以基本上,你的智能体仍然独自处在一种数字式的单独监禁之中。
指向原始笔记的链接
So basically your agents are still alone in a kind of digital solitary confinement.
—— Vlad Luzin · [05:18]
它们是为人类构建的,而且它们会主动阻止你把一个机器人连接到另一个机器人。
指向原始笔记的链接
They are built for humans, and they actively block you from connecting a bot to a bot.
—— Vlad Luzin · [07:21]
你需要超越所有这些技术细节,上升到一个不同的抽象层次:对话、参与者、频道或房间,以及以智能体为一等公民而定制的消息路由。
指向原始笔记的链接
You need to rise above all of the technical details to a different level of abstraction, conversation, participants, channels or rooms, message routing that is tailored to agents as the first citizens.
—— Vlad Luzin · [09:17]
但这是不需要 50 万行你需要搬过来的 Python 或 TypeScript 代码的 loop engineering,那样你的智能体才能真正互相提示工作。
指向原始笔记的链接
But it’s loop engineering without 500,000 lines of a Python or TypeScript code that you need to bring over so your agents can actually prompt each other for work.
—— Vlad Luzin · [15:45]
② 出现在这些集
2 集
- 《别再当智能体的路由器:多智能体通信为什么这么难》 — 作为嘉宾
- 《AI 智能体为什么还聊不到一起?有人做了个“聊天室”》 — 作为嘉宾
③ 他谈到的
点进去有真内容 —— 本页主要出口
智能体 · 分布式系统 · 循环工程 · MCP · A2A 协议 · BENT · Bend · gem · 多智能体系统 · 多智能体协调
