跨国深谈

循环 (loop)

Properties1
aliasesloop, loops

17分钟阅读

跨国深谈← 返回←循环 (loop)
循环

循环 (loop)

概念 · 又名 loop / loops
本站收录 10 集 · 69 条金句 · 关联 10 个

集里怎么说它

① 提到它的金句

69 条

奖励循环需要强大，它需要立即生效，它需要情感化，这样当这个人做你想让他们做的事情时，他们感觉就像赚了一百万美元一样爽。
The reward loop needs to be powerful, it needs to be immediate, and it needs to be emotional, so that when this person does the thing that you want them to do, they feel like a million bucks.
—— Hilary Gridley · [65:58]

指向原始笔记的链接

而且我认为智能体的主流架构就是一个带工具的 for 循环。
And I think the prevailing architecture for agents is a for loop with tools.
—— Ankur Goyal · [06:28]

指向原始笔记的链接

而对于我最关键任务的生产服务器，我仍然想要人在回路中。
And for my most mission critical production servers, I still want a human in the loop.
—— Vineet Edupuganti · [14:27]

指向原始笔记的链接

智能体就是一个带工具的 for 循环。
Agents are a for loop with tools.
—— Ankur Goyal · [16:13]

指向原始笔记的链接

最大的陷阱之一是如果你陷入这个循环，如果我再给产品添加一样东西，它最终就会变得很棒。
One of the biggest pitfalls is if you get into the loop of, if I just add one more thing to the product, it’ll be finally great.
—— Max Schoening · [01:00]

指向原始笔记的链接

如果他们知道如何调整 UI 的小细节，但他们不理解智能体循环是如何工作的，我会更倾向于那种对理解智能体循环如何工作有深厚亲和力并且能够设计它们的设计师或产品经理，而不是那些能编写传统软件并调整样式的人。
If they know how to tweak small details of the UI, but they don’t understand how an agent loop works, I would much rather take the designer or PM that deeply has an affinity for understanding how agent loops work and can design those than someone who can write traditional software and tweak styles.
—— Max Schoening · [09:23]

指向原始笔记的链接

智能体运行内部执行循环。我设定方向，我在外部循环中做决策。
The agent runs the inner execution loop. I set the direction and I make decisions in the outer loop.
—— 嘉宾 · [23:04]

指向原始笔记的链接

未来不是 20 个终端。而是更好的循环。
The future is not 20 terminals. It’s better loops.
—— 嘉宾 · [24:49]

指向原始笔记的链接

总的来说,我们正试图迈向一个人类不需要参与其中的世界。
In general, we are trying to move to a world where humans don’t need to be in the loop.
—— Cat Wu · [15:46]

指向原始笔记的链接

但如果你给人们工具，并且他们自己创造了那个最终结果，他们就会建立信念，因为他们参与其中，使用了他们的批判性思维，他们通过做事建立自己的信念，然后他们真的相信最终结果。
But if you give people tools and they create that end result themselves, they build conviction because they’re in the loop, their critical thinking is used, they are building their own conviction by doing, then they really believe in the end result.
—— 嘉宾 · [118:16]

指向原始笔记的链接

但是在今年结束之前，我很确定循环工程的概念将会被随后发生的事情和事物发展方向的演进所淘汰。
But before the year is out, I’m pretty sure the notion of loop engineering is going to be kind of antiquated by what follows and the evolution of where things are going.
—— Chris Benson · [25:28]

指向原始笔记的链接

对我来说,AGI 是一个可以在没有任何人在循环中的情况下自我改进的模型。
For me, AGI is a model that can improve itself without human in the loop in any way.
—— Jerry Tworek · [38:21]

指向原始笔记的链接

我认为那部分将是困难的，但我认为那将是 AI 最大的机会空间所在，就是在那里的所有事情上减少人在回路。
And I think that part’s going to be difficult, but I think that’s going to be where the biggest opportunity space is at with AI is to reduce the human in the loop on everything there.
—— Chris Blackburn · [30:21]

指向原始笔记的链接

这里的重点是它正迅速将人类从网络安全环路中操作员的位置上移除，最多只能成为环路上的操作员，你在观察这个环路，你可能拥有有限的输入和观察，但是这个环路发生得太快，人类无法进行干预。
The point here is it is rapidly moving the human out of the position of being the operator in the loop on cybersecurity to at best being an operator on the loop where you’re observing the loop, you may have limited input and observation, but the loop is happening too fast for human intervention to occur.
—— Chris Benson · [34:21]

指向原始笔记的链接

我认为在智能体循环和弄清楚如何开发系统方面仍然存在天文数字的机会,这些系统使你能够在持续反馈循环中花费 1000 倍或 100 万倍的 token 来推动结果。
I think there’s still just astronomical opportunity in agentic looping and figuring out how you develop systems that enable you to spend 1,000x more or 1,000,000x more on tokens to drive an outcome in a continuous feedback loop.
—— Alexandr Wang · [27:11]

指向原始笔记的链接

我认为我们在 Meta 内部看到过这样的案例,如果你能开发出正确的智能体循环,并且你有正确的评估或正确的指标供智能体优化,你可以让一群智能体非常非常轻松地、非常非常容易地完成比 100 名工程师团队更多的工作。
I think we’ve seen, internally at Meta, cases where if you can develop the right agentic loop and you have the right eval or the right metric for the agents to optimize, you can have a swarm of agents accomplish more than a team of 100 engineers very, very handily, actually, very, very easily.
—— Alexandr Wang · [28:09]

指向原始笔记的链接

AI 审批的 PR 以及总体上 AI 编写的代码甚至可以比仅有人类在流程中所做的更安全、质量更高。
AI approved PRs and AI written code in general can be even safer and even higher quality than what you’re doing with just a human in the loop.
—— Claire · [03:47]

指向原始笔记的链接

当每个人谈论智能体时，他们真正谈论的只是一个在循环中运行、调用工具的 LLM。
When everyone talks about agents, what they really talk about is just an LLM running in a loop calling tools.
—— Harrison Chase · [02:47]

指向原始笔记的链接

然后第三，创建你自己的持续学习循环，爬坡机器，它将让你的 AI 投资为你的公司复合增值。
And then three, you create your own continuous learning loop, hill climbing machine that will allow your AI investments to compound the value of your firm.
—— Harrison Chase · [09:52]

指向原始笔记的链接

字面上看，在我们把自我改进循环上线后的第一周内，那大概是两个月前左右，错误率下降了 8 倍。
Literally within the first week of us putting the self-improvement loop online, which was like two months ago or something, it went down by 8x the error rate.
—— Flo Crivello · [24:46]

指向原始笔记的链接

任何超出两秒循环的东西,你本质上就会失去沉浸感。
Anything beyond a two second loop, you essentially lose the feeling of immersion.
—— 嘉宾 · [23:17]

指向原始笔记的链接

超过两秒的循环，你本质上失去了沉浸的感觉。
Anything beyond a two-second loop, you essentially lose the feeling of immersion.
—— Elliot · [23:17]

指向原始笔记的链接

但是如果只是让你的循环构建所有东西，而在爆炸半径周围没有任何护栏，在关于你如何看待质量的周围没有任何护栏，我认为这是灾难的配方。
But simply just having your loops build everything without having some guardrails around the blast radius, without having guardrails around how you think about quality, I think is a recipe for disaster.
—— Addy Osmani · [66:33]

指向原始笔记的链接

我的激进观点是：只要有对的团队、对的想法、对的学习循环，你的 TAM 几乎是无限的。
My hot take is that with the right team, the right idea, and the right learning loop, your TAM is almost infinite.
—— Willem Avé · [22:28]

指向原始笔记的链接

模拟是内循环——快、免费、可以在任何真人暴露前跑成千上万次;但真实患者是外循环,那才是唯一真正的证明所在。
Simulation is the inner loop. It’s fast. It’s free. You can do thousands of runs before anyone actually real is exposed. But real patients are the outer loop, and that’s where the only real proof is.
—— Jared Joselowitz · [15:40]

指向原始笔记的链接

提示词正在迅速变得过时。提示词正在被循环取代。
Prompting is rapidly becoming passe. Prompting is being replaced by loops.
—— Manoj Saxena · [49:38]

指向原始笔记的链接

所以是的，我想我们都想要这种自动改进循环，但它们不适用于产品。
So yeah, I think we all wanted these sort of like automatic improvement loops, and they just don’t work with product.
—— Ryan Carson · [20:25]

指向原始笔记的链接

人类仍然在循环中,并且实际上加入了自己的判断、品味和销售独门秘诀,但他们不再是从一张白纸开始。
The human is still in the loop and actually adds their own judgment and taste and sales secret sauce, but they’re no longer starting from a blank slate.
—— Flora Liu · [16:31]

指向原始笔记的链接

循环会累积。而你必须在整个过程中都让上下文的使用保持高效。
The loops compound. And you have to be efficient the entire way through with your context.
—— Peter Werry · [12:25]

指向原始笔记的链接

这样我们在不需要人的环节就把人从流程里移除了。
So we kind of remove the human from the loop where we don’t need it.
—— Jesse Lumarie · [06:55]

指向原始笔记的链接

如果你在 vibe coding,如果你整天和你的智能体来回对话,你当然不会看到 4 到 5 倍的生产力提升,因为你全程都在循环之中。
If you are vibe coding, if you are having a back and forth conversation with your agent all day long, of course, you’re not going to see 4 to 5x productivity improvements because you are in the loop the entire time.
—— Clare Liguori · [11:21]

指向原始笔记的链接

从产品开发的角度看,我们的目标并不是让客户在没有人在环的情况下操作整个系统。
The goal that we have from a product development standpoint is not to have a customer operate the entire system without a human in the loop.
—— Andrew Garvin · [07:18]

指向原始笔记的链接

如果你连一个单一的智能体循环都建不好，为什么还要去构建一个多智能体编排系统呢？
if you can’t build a single agentic loop, why go in and try to build a multi-agent orchestrated system?
—— Roberto Milev · [01:28]

指向原始笔记的链接

归根结底，订阅模式将会发生改变，从人在环中变成人在环上，或人不在环中。
So bottom line, the subscription model is going to change with humans in the loop to becoming humans on the loop or out of the loop.
—— Anil Nadiminti · [05:52]

指向原始笔记的链接

而且实际上，这种特异性——能够精确调整你正在审查的内容——在你走向工厂的过程中变得越来越重要，因为说真的，工厂将要产出的量，你必须让人类退出代码审查的循环。
And in fact, this specificity, you know, being able to tune exactly what you’re reviewing becomes increasingly important as you move towards factory because really the volume a factory is going to put out, you have to get humans out of the loop for code review.
—— Drew · [20:02]

指向原始笔记的链接

可以这么说，你会不断地做循环，直到你有太多的循环，以至于你的大部分工作都在维护循环、以及构建用来观察它们的循环。
It’s sort of, you’re going to keep working on loops until you have so many loops that most of your work is in maintaining loops and building loops to observe them.
—— Drew · [44:52]

指向原始笔记的链接

你比只是写个提示词时更多地把自己从循环中抽离出来。这样你才能真正把自己扩展放大。
So you’re taking yourself out of the loop more than you are with just like a prompt. That way you can actually scale yourself.
—— Tyler Folkman · [05:26]

指向原始笔记的链接

循环会帮你爬到局部最优，然后进入平台期——你需要某种分布之外的思考，需要人类直觉，需要有人真正帮你降落到下一座山的山脚下。
The loop will help you climb to the local maxima, but then it plateaus and you need some sort of out of distribution thinking, you need human intuition, you need somebody to actually help you land at the base of the next hill.
—— Anish Acharya · [15:15]

指向原始笔记的链接

现在，我认为我们有点处于这种厄运循环中：我们超支，同时我们使用不足。
right now I think we’re kind of in this doom loop where we’re overspending and we’re underusing.
—— Maximillian Piras · [09:52]

指向原始笔记的链接

所以在这个世界里，智能体在掌控，人类在环路中。
So in this world, the agents are in control and the humans in the loop.
—— Jonathan Gordon · [14:01]

指向原始笔记的链接

即使你的模型每天都在改进，别人也可以每天都在蒸馏它。这些循环可以以同样的节奏运转。
Even if your model is improving every day, people could be distilling it every day. So the loops could just operate at the same pace.
—— 嘉宾 · [19:57]

指向原始笔记的链接

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。
Almost all of that has gone out the window since prompt engineering and context engineering, loop engineering.
—— Robert Lucero · [25:19]

指向原始笔记的链接

循环会帮你爬到局部最高点，但随后它会进入平台期。你需要人类的直觉。
The loop will help you climb to the local maxima, but then it plateaus. You need human intuition.
—— Anish Acharya · [00:55]

指向原始笔记的链接

所以我们的看法是，做出决策的那部分，也就是定义功能、定义 API 表面积、定义抽象层，那些是非常需要人在环的，我亲自上手和 Claude 一起做。而写代码、执行的部分，才是被自动化的部分。
So the way we see it is the part which is where the decisions are being made, right, which is defining the feature, defining the API surface area, the abstraction layer, those are very human in the loop, right, where I’m hands on with Claude. And the code writing part, the execution part, is actually the part which is automated.
—— 嘉宾 · [16:57]

指向原始笔记的链接

我发现正确的路径和那些没有附带反馈循环的路径之间有很高的相关性。
I find a very high correlation between the right path and the ones that don’t have feedback loops attached.
—— Tobi Lütke · [37:59]

指向原始笔记的链接

所以我认为唯一的解决方案就是自主性，对吧？把人类从回路中拉出来，让他们不用看着回路转圈、在坏事发生时按下按钮。
And so I think the only solution to this is that autonomy, right? Pull the human out of the loop, make them not watch the loop go round and push the button when something bad happens.
—— Marc Brooker · [26:05]

指向原始笔记的链接

我认为,相信我可以拿一个大模型放进自我改进循环、然后这个模型就会生成意志,这是异想天开。
I think it’s wishful thinking to believe that I can take a big model, put into a self-improvement loop, and this model is gonna generate will.
—— Daniel Dines · [12:47]

指向原始笔记的链接

我们想说的是，这是暴露给自动研究层循环的正确表面，因为它足够小以便控制，但至少在某种程度上仍然足够丰富，能够改变社会行为。
We’re trying to say this is the right kind of surface to expose to an auto-research layer loop because it is small enough to control, but it’s still rich enough to change the social behavior to some extent at least.
—— Erina Karati · [16:49]

指向原始笔记的链接

所以这个循环基本上应该像一个棘轮：尝试一个改动，给它打分，只有当记分卡改善且护栏完好时才保留它。
So the loop should basically be like a ratchet. Try a change, score it, keep it only if the scorecard improves and guardrails whole.
—— Erina Karati · [18:07]

指向原始笔记的链接

问题不在于循环本身，而在于你如何定义在循环中什么叫「完成」。
The question is not the loop itself, but the question is how you define what it means to be done in the loop.
—— Tereza Tížková · [10:36]

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

OpenClaw 的创造者 Peter Steinberger 说，你不应该再去提示编码智能体了，你应该去设计那些提示你的智能体的循环。
Peter Steinberger, who is the creator of OpenClaw, says that you shouldn’t be prompting coding agents anymore, you should be designing the loops that prompt your agents.
—— Laurie Voss · [04:53]

指向原始笔记的链接

这里的赌注是，循环设计可以替代检查。
The bet there is that loop design substitutes for inspection.
—— Laurie Voss · [06:21]

指向原始笔记的链接

所以你把人类从环中拿掉，你不只是失去了一个审查者，你失去了那个难以被欺骗的东西。
So you take the human out of the loop, you don’t just lose a reviewer, you lose the thing that was hard to fool.
—— Laurie Voss · [21:26]

指向原始笔记的链接

确保 AI 不断前进的最好方式,是闭合研究与部署的循环。
The best way to ensure that we move AI forward is to close the research and deployment loop.
—— Jonathan · [53:36]

指向原始笔记的链接

我们仍然认为在进入生产环境之前需要有一个小小的人类在环中,至少目前是这样。我们都知道终极未来是要避免这一点。
We still believe there’s like some little human that needs to be in the loop before going to the production, at least at this point. We all know that the ultimate future is to avoid that.
—— Zilvinas · [10:25]

指向原始笔记的链接

对我们来说，TypeScript Go 让构建获得了 10 倍提升——在智能体运行自动化 PR、需要 CI-CD 循环来获取反馈改进代码的规模下，这是一个巨大的提升。
And for us, TypeScript Go was a 10 times improvement in our builds, which at the scale of automatic PRs running with agents and them needing that CI, CD loop for feedback to improve the code is a massive improvement.
—— Harald Kirschner · [07:36]

指向原始笔记的链接

如果你的智能体无法直接使用你的应用、你的产品来获得「一切是否正常」的反馈循环，那么这是一项非常值得的投资，每次你做 UI 工作时都会有回报。
If your agent cannot use your application, your product directly to get this feedback loop of is it all working, then that’s a really big investment that pays off every time you work on UI.
—— Harald Kirschner · [08:48]

指向原始笔记的链接

必须去搭建和摆弄你的 loops,这也许是让人们感到兴奋的事，但我不认为这会是它最终运作的方式。
Having to set up and fiddle with your loops is something that maybe people get excited about, but I don’t think this is the way that it’s going to work.
—— Tibo Sottiaux · [00:46]

指向原始笔记的链接

还是更自动化的方式，比如用记忆或 prompt 优化之类的工具，这个复利循环非常重要，要构建到你的系统中并由你掌控。
Or more automatically, whether that’s with memory or prompt optimization things, this compounding loop is really important to build into your systems and to own.
—— 嘉宾 · [06:23]

指向原始笔记的链接

你知道的，我可以这么告诉你：如果你在检测和响应环节中还有人工参与，你会太慢。
You know, over time, I can tell you this, if you have humans in the detect and respond loop, you’re going to be too slow.
—— Kevin Mandia · [22:18]

指向原始笔记的链接

我们习惯于考虑建模能力、为任务构建合适的沙箱、把任务放进去，而现在我们开始看到，这个个体循环更安全，因为它拥有的访问权限比整个工作流实际拥有的要少。
We get used to thinking about modeling capabilities, building the right sandbox for the task, putting the task in, and now we’re starting to see that this individual loop is safer because it has less access than the entire workflow effectively has.
—— Jim Clark · [15:54]

指向原始笔记的链接

我觉得这里愤世嫉俗的循环是：做一个 demo，融一笔种子轮或 A 轮，说你会把它做可靠，最后却从来没有把它做可靠，然后转而做一个 human-in-the-loop 版本的东西，而不是真正把这个任务自动化。
My cynical loop here is make a demo, raise a seed or series A, say that you’re going to make it reliable, never end up making that reliable, pivot into a human-in-the-loop version of this thing instead of actually automating the task.
—— Diogo Almeida · [17:33]

指向原始笔记的链接

慢慢地加入越来越多的逻辑，因为要在像 Claude Codes 和 Codexes 这样的东西里添加额外的 harness 逻辑非常困难，因为它们的核心循环就是一个 while 循环。
That slowly add more and more logic because it’s very hard to add additional harness logic into like the Claude codes and codexes because their core loop is just a while loop.
—— Diogo Almeida · [82:37]

指向原始笔记的链接

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。
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]

指向原始笔记的链接

有时我觉得我们可能处于某种失忆循环中，对吧？我们的智能体经历推理阶段、行动，成功完成了一些任务，但随后就有点忘记了它们学到的东西。
Sometimes I feel like we’re in maybe like an amnesiac loop, right? Where our agents go through this reasoning phase, acting, they successfully complete some task, but then kind of forget what they’ve learned.
—— Will Lyon · [00:41]

指向原始笔记的链接

在我们不用手工重写的情况下，这就变成了每个组织或每个用户构建这些流水线时的一个自我改进循环。
Without us rewriting by hand, this then became a self-improving loop per org or per user that was building these pipelines.
—— Abhi Arya · [13:45]

指向原始笔记的链接

而我们发现，那个能闭合回路的更简单的东西，才是能扩展的东西。
And what we found is that the simpler thing that closes the loop is the thing that scales.
—— Daval Ajada · [14:37]

指向原始笔记的链接

花了几个小时就超越了我们在有人参与的情况下做了两年的工作。
It took a few hours to outperform the two years of work which we’d done with human in the loop.
—— David Silver · [31:02]

指向原始笔记的链接

② 出现在这些集

10 集

③ 关联

点进去有真内容 —— 本页主要出口

智能体 · Codex · Cursor · OpenAI · Claude Code · Anthropic · vibe coding · harness · 技能 · Anish Acharya

反向链接