① 他说过的话

11 条

但现实中，在工程工作里，我们 70% 的时间花在另一头，不是生成新软件，而是在生产系统上，基本上就是运行和修复软件。
But in reality, for engineering, 70% of our time is spent on the other side, not generating new software, but rather in production systems, basically running and fixing software.
—— Varun Krovvidi · [02:31]

指向原始笔记的链接

这时候失望就开始出现了，在大多数情况下，大多数人把它称为“最后一英里”，但那是你和 AI 一起要跑的最漫长的一英里。
That is when the disappointment starts to set in, which in most cases, most people dub it as the last mile, but that is the single longest mile that you have to run with AI.
—— Varun Krovvidi · [05:13]

指向原始笔记的链接

我们真诚地相信，你在生产系统上所做的所有这些工作——比如修复问题或者日常运行你的软件——在大部分情况下都应该由智能体来完成。
So we genuinely believe that all of this work that you do on production systems, like fixing issues or running your software on a day-to-day basis, should be done by agents in most part.
—— Varun Krovvidi · [05:57]

指向原始笔记的链接

而工程师应该只是运行那些智能体，由智能体负责修复和运行你的软件。
And engineers should just be running those agents, where agents take care of fixing and running your software.
—— Varun Krovvidi · [06:14]

指向原始笔记的链接

这会成为一个巨大的问题，因为遥测数据实际上是无限的。
This becomes a huge issue because telemetry is literally infinite.
—— Varun Krovvidi · [09:31]

指向原始笔记的链接

模型是用来取悦你的。
So models are there to please you.
—— Varun Krovvidi · [09:52]

指向原始笔记的链接

所以模型是专门被设计来给你连贯的答案，而不是因果关系。
So models are specifically designed to give you coherent answers but not causality.
—— Varun Krovvidi · [10:01]

指向原始笔记的链接

现在，当你在其上叠加时间维度的讨论时，你的 AI 系统应该在第 100 次调查中仍保有之前那次调查的上下文，否则你就是在再次从零开始转轮子。
Now, when you add temporal discussions on top of it, your AI system should have the same context of a previous investigation in the 100th investigation, or else you’re starting the wheel from the same time again.
—— Varun Krovvidi · [11:30]

指向原始笔记的链接

但作为目标真正重要的是，AI 解决那个具体问题所需的精确上下文量是多少。
But what matters as a goal is what is the precise amount of context AI needs to solve that specific problem.
—— Varun Krovvidi · [12:59]

指向原始笔记的链接

就像我提到的，这是我们在 Resolve AI 的系统里构建的首要原则之一，即根因始终基于一条因果证据链。
Like I mentioned, so this is one of the first principles that we’ve built into our system at Resolve AI, where the root cause is always based on a causal chain of evidence.
—— Varun Krovvidi · [13:35]

指向原始笔记的链接

回到我之前提到的，如果你把一个 AI 逼得够紧，它就会开始同意你。
Going back to what I mentioned, if you push an AI hard enough, it will start to agree with you.
—— Varun Krovvidi · [19:25]

指向原始笔记的链接

② 出现在这些集

1 集

• 《让 AI 真正接管运维：Resolve AI 的六大支柱》 — 作为嘉宾

③ 他谈到的

点进去有真内容 —— 本页主要出口

Resolve AI · 智能体 · on call · 事故 · 模型编排 · 上下文工程 · 因果推理 · 护栏 · 评估 · Slack

④ 也在聊「智能体」的人