跨国深谈

确定性 (determinism)

Properties1
aliasesdeterminism, deterministic

14分钟阅读

跨国深谈← 返回←确定性 (determinism)
确定

确定性 (determinism)

概念 · 又名 determinism / deterministic
本站收录 6 集 · 17 条金句 · 关联 10 个

集里怎么说它

① 提到它的金句

17 条

我超级喜欢，因为我向组织解释的所有事情等等，人类天生是不确定的。但我们现在正在添加更多的智能体。我们更加不确定了。所以我需要某种程度的确定性。
I’m a big fan of, because of everything I explained to organizations and so forth, is that humans are non-deterministic by nature. But now we’re adding more agents. We’re even more non-deterministic. So I need some level of determinism.
—— Heitor Lessa · [33:53]

指向原始笔记的链接

这是在确保模型拥有主观能动性来自由推理和行动与构建一个 UX 之间的张力，这个 UX 需要具有很好的交互性，具有以可预测和确定性方式渲染的丰富元素。
the tension between making sure the model has agency to reason and act freely with building a UX that’s kind of nicely interactive, has rich elements that are rendered in a predictable and deterministic way.
—— 嘉宾 · [06:47]

指向原始笔记的链接

之前，传统软件是确定性的，你可以预先定义好权限。但现在，随着智能体变得自主、试图解决更多问题，它们在做的事情在运行时发生改变。
Earlier, traditional software was deterministic. You could define the permissions. But now, as agents become autonomous and they gain and they try to solve more problems, what they’re doing changes at runtime.
—— Tushar Jain · [03:37]

指向原始笔记的链接

如果你的 Skills 没有正确的结构，那你就不真正拥有一个确定性的工作流。
And if you don’t have the right structure of your skills, then you’re not really having a deterministic workflow.
—— Imad Touil · [06:45]

指向原始笔记的链接

而且我强烈建议，在一个不确定性的系统里，你至少要让请求尽可能具有确定性。
And I would highly recommend that you at least make requests as deterministic as possible with an undeterministic system.
—— Kanish Manuja · [09:12]

指向原始笔记的链接

很多业务运营是完全确定性的，所以有很多 AI 被用在了不该用的地方，只是在让你花钱。
A lot of business operations are fully deterministic, so you Do m that there’s a lot of AI that’s being used in places that it shouldn’t be used and it just costing you money.
—— Ran Arusi · [21:56]

指向原始笔记的链接

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?
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]

指向原始笔记的链接

执行是你押上身家性命的部分，所以它必须是确定性的；而判断是增加细微差别的部分，那才是你唯一能放进概率性东西的地方。
Enforcement is the part that you bet the house on, so it has to be deterministic, but judgment is the part that adds nuance, so that’s really the only place that you can put anything probabilistic in there.
—— Sarah Sanders · [16:15]

指向原始笔记的链接

当我们放眼观察，即便是我们自己的、比如客户对智能体产品的使用，人们使用智能体做的事情中，绝大部分——实际上是 80%——他们或许应该使用老式的确定性代码才对。
And when we look across like even our own, like in customers usage of agentic products, the vast majority of what people are using an agent for, 80% in fact, they probably should be using actually old fashioned deterministic code.
—— Wade Foster · [15:08]

指向原始笔记的链接

但实际在运行的仍然是一个非常确定性的工作流，只是在最必要的地方交织着 AI。
But what is actually running is still a very deterministic workflow with AI interwoven in like the places that is most necessary.
—— Wade Foster · [19:18]

指向原始笔记的链接

所以 harness 工程的目标是一次又一次地创造可靠且可预测的输出，而推理模型是非常非确定性的。
So the goal of harness engineering is to create reliable and predictable outputs over and over, whereas a reasoning model is very non-deterministic.
—— Ignacio Martinez · [11:26]

指向原始笔记的链接

我听到很多工程师谈论如何把 LLM 变成确定性流程,而我的主张是:有很多问题是确定性算法无法解决的。
I hear a lot of engineers talk about how we turn LLMs into deterministic processes, and my contention is actually there’s a lot of problems that you can’t solve with deterministic algorithms.
—— Cody Menefee · [16:22]

指向原始笔记的链接

我从来没有见过一个提示词或一个确定性工具,能够在没有人类参与的情况下,以任何有意义的方式驱动代码库的可维护性并对抗模型写出不可维护代码的倾向。
But I have never seen a prompt or a deterministic tool that can drive code-based maintainability and fight the model’s tendency to write unmaintainable code in any meaningful way without a human in the loop.
—— Dex Horthy · [27:15]

指向原始笔记的链接

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。
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]

指向原始笔记的链接

我们用确定性代码的时候日子有多好过。就像，天哪，我还记得计算机完全按我们说的去做的那些日子。
how good we’ve had it with deterministic code. Like, oh my god, I remember the days when computers did exactly what we told them to do.
—— Amjad Masad · [39:15]

指向原始笔记的链接

你会在我构建的很多其他技能里看到这一点，就是我尝试把确定性的部分提取出来变成代码，只把真正需要判断力的部分留给智能体。
And you’ll see this in a lot of the other skills that I’ve built, is like I try to extract out the deterministic parts and turn that into code and just leave only the parts that actually require judgment to the agent.
—— Poteto · [21:46]

指向原始笔记的链接

这是我喜欢思考的另一个核心的事情，或者说是我的核心原则之一，就是如何非常高效地利用确定性和非确定性，让智能体在非确定性的部分大放异彩，因为那就是它们被训练来做的。
That’s another core thing or one of my core principles that I like to think about is how do I make very efficient use of determinism and non-determinism and let agents shine at the non-deterministic parts because that’s what they’re trained to do.
—— Poteto · [23:50]

指向原始笔记的链接

② 出现在这些集

6 集

③ 关联

点进去有真内容 —— 本页主要出口

智能体 · 技能 · 验证 · Heitor Lessa · Brendan McManus · Wade Foster · Gabriel Spencer-Harper · Poteto · Viren Baraiya · 规范驱动开发

反向链接