Robert Lucero
① 他说过的话
4 条
我们思考 AI 智能体与给组织新人办理入职的区别时,有趣的一点是:我们对一个人投入了大量隐性的信任——认为他们经过了审查和治理,并且有一定程度的控制。
指向原始笔记的链接
What’s interesting about how we think about an AI agent versus onboarding somebody new to the organization is that we put a lot of implicit trust into a person, that they are vetted and governed and that they have some levels of controls.
—— Robert Lucero · [00:00]
随着智能体变得更高效、更有效,我认为我们会更倾向于依靠技术控制作为门禁机制,而不是对它能做什么的主观人为评估——因为再说一次,由于非确定性,你真的很难回头去问一个智能体:你为什么把这些文件全删了?
指向原始笔记的链接
So as an agent becomes more efficient and effective, I think we’re going to lean more on technical controls as a mechanism to gate versus a subjective human assessment of what it can do, because again, the non-determinism, it’s really hard to go back to an agent and ask, why did you go delete all these files?
—— Robert Lucero · [18:36]
从那以后,那套东西几乎全被扔出了窗外,现在流行的是提示词工程、上下文工程、循环工程。
指向原始笔记的链接
Almost all of that has gone out the window since prompt engineering and context engineering, loop engineering.
—— Robert Lucero · [25:19]
工程师的时间只有大约 40% 用于写代码,其中只有约 10% 用于写新代码。也就是说,工程师有 60% 的时间花在非编码任务、非编码工作上。
指向原始笔记的链接
An engineer’s time is only like 40% writing code and only like 10% writing new code. So there’s 60% of an engineer’s time that is non-coding tasks, non-coding work.
—— Robert Lucero · [27:20]
② 出现在这些集
1 集
③ 他谈到的
点进去有真内容 —— 本页主要出口
Brian Houck · Okta · 智能体 · 沙箱 · 护栏 · 身份 · 非确定性 · 服务账号 · AI 采用 · 仓库 AI 就绪度