如果你还没有开始，该如何入门 AI 编程

好了，朋友们，正式的时候到了。

Well, friends, it is officially time.

正式到了不再把用AI写代码当成只是软件工程师的事情的时候了，因为它不是。

Officially time to stop acting like coding with AI is something that is just for software engineers because it is not.

当然，在过去一年半的时间里，随着Lovable、Replit、Cloud Code和Codex这些工具的出现，越来越多的非软件工程师开始学会利用写代码和构建软件的强大能力来解决自己的问题。

Now, obviously, throughout the course of the last year and a half, as tools like Lovable and Replit and then Cloud Code and Codex came online, more and more knowledge workers outside of software engineering started to figure out how to use the power of writing code and building software to solve their own problems.

这不仅仅是那些非软件工程师突然想模仿软件工程师。

And this is not just about all of a sudden those non software engineers trying to act like software engineers.

而是关于找到新的方式，借助自己构建的软件来更好地完成工作。

It's about finding new ways to do their jobs with the aid of software that they can build themselves.

然而，对很多人来说，这仍然感觉遥不可及，难以触及。

And yet for so many people, this still feels so inaccessible and out of range.

但其实不必如此。

But it doesn't have to be.

《AI每日简报》是一个每日更新的播客和视频节目，内容涵盖AI领域最重要的新闻和讨论。

The AI Daily Brief is a daily podcast and video about the most important news and discussions in AI.

好了，朋友们。

Alright, friends.

在我们深入之前，先快速说几个通知。

Quick announcements before we dive in.

首先，感谢今天的赞助商：毕马威、Blitzy、Robots and Pencils 和 Hyperagent。

First of all, thank you to today's sponsors, KPMG, Blitzy, Robots and Pencils, and Hyperagent.

想要收听无广告版本，请访问 patreon.com/aidailybrief，或者你也可以在 Apple Podcasts 上订阅。

To get an ad free version of the show, go to patreon.com/aidailybrief, or you can subscribe on Apple Podcasts.

如果想了解赞助节目的详情，请发送邮件至 sponsors@AIDailyBrief.AI。

To learn more about sponsoring the show, send us a note at sponsors@AIDailyBrief.AI.

接下来，快速宣传一下我们即将推出的“超级智能执行代理领导力项目”。

Quick requisite shill for our upcoming Super Intelligent Executive Agent Leadership Program.

这个项目是由 Newfar Gaspar 主导的，比我们之前办的 Agent OS 和 Claw Camp 风格的项目支持更到位，重点不仅在于教你如何为工作构建代理，还在于如何围绕这些代理搭建系统，让它们能够安全、可靠地融入你的工作流程。

This is the better supported led by Newfar Gaspar version of the Agent OS and Claw Camp style programs that we've had in the past, focused on helping you not only learn how to build agents for work, but how to build these systems around them that allow them to intersect with your work in a safe, secure way.

下一期课程将在劳动节后不久开始，现在已经开始报名了。

The next cohort starts just after Labor Day and is registering now.

最近我和我女儿一个朋友的家长聊了聊，这个人已经重度使用AI好几年了。

I was recently having a conversation with one of my daughter's friend's parents, and this is a person who has been using AI extensively for a couple of years.

他们订阅了好几个不同的服务，而且都是高价位的那种，很多工作都已经转向了AI辅助的模式。

They have multiple subscriptions to multiple different services at high expensive levels and has moved a lot of their work into an AI assisted type of paradigm.

但即便如此，对他们来说，哪怕只是考虑一下AI编程相关的事情，还是觉得特别陌生。

And yet for them, even considering anything surrounding AI coding still seemed totally foreign.

简单来说，他们一直生活在那种协作工作的模式里，从来没跨进过代码的世界，我觉得他们因此错过了不少东西。

They were in short living that co work life, never venturing over into the quad code side of the world, and I think losing quite a bit for it.

我并不是要对大家的选择做任何评判，但我觉得，如果你不是软件工程师，而是一个知识工作者，到了现在这个阶段，工具包里没有AI编程工具，确实会落后于人。

With absolutely no value judgments placed on where people are, I do think not having AI coding tools in your toolkit as a non software engineer knowledge worker does at this point leave you behind.

这周早些时候，我们做了一期节目，讲的是OpenAI最近的企业研究。研究发现，大概在四月底五月初的时候，通过API以智能体方式消耗的token数量，已经超过了通过ChatGPT非智能体方式使用的token数量，而且这个比例还在不断上升。

Earlier this week, we did that episode about OpenAI's recent enterprise research that found that around the end of April, beginning of May, the percentage of tokens that were being consumed via API agentically had flipped the amount of tokens being used non agentically through ChatGPT, and that number has done nothing but rise.

我们还看到，那些排在前10%的企业用户，相比普通企业，AI使用量大约是8.3倍，而且他们部署的应用场景要复杂得多，更多涉及系统层面和整体性的变革。

We saw that the firms who were in the top 10% of enterprise users as opposed to the average firms were using about 8.3x as much AI, and the use cases that they were deploying were a lot more sophisticated, getting much more into systems and overall disruption.

为了强调这不仅仅是软件工程师的事：虽然从二月份的基线来看，企业中工程相关的代码用户增长了5倍，但基本上其他所有职能的增长幅度都更大。

And putting a fine point on the idea that this is not just a thing for software engineers alone: While starting from the February baseline, engineering related users of codecs in the enterprise had grown 5x, basically every other function had grown significantly more.

财务和会计部门使用代码的数量是二月份时的20倍，销售和会计部门是41倍，而法律部门则是二月份时的108倍。

Finance and accounting was using codecs 20 times more than it had been in February, sales and accounting was using it 41 times as much, and legal was using it 108 times as much as it had been back in February.

那么这些人到底在用AI编程做什么呢？

So what the heck are all these people doing with AI coding?

大多数情况下，他们并不是突然想成为公司的软件工程师。

One thing that they are not doing, in most cases, is all of a sudden trying to become the software engineers for their organization.

我觉得这是早期“氛围编程”时代的一个误解，尽管已经过去很久了，但这个误解还是顽固地留在我们心里。

This, I think, was a misconception of the early days of vibe coding that has still a bit stubbornly persisted with us despite it being for a long time not really where people are.

对于知识工作者来说，把AI编程纳入你的AI工具包，真正的理由不是你要变成软件工程师，而是因为我们看到，那些在构建东西的人，相对于其他AI用户，正在不断累积他们的收益和优势。

The real argument for deploying AI coding as part of your AI toolkit as a knowledge worker is not that you're going to become the software engineer, but because we're seeing that the people who are building are compounding their gains and their advantages relative to other AI users.

我们看到典型企业和前沿企业之间8.3倍的差距，相比一月份的2.6倍已经扩大了。

That 8.3 x gap that we saw between typical firms and frontier firms was up from a 2.6 x gap back in January.

但还有很多其他理由让你考虑学习编程。

But there's a lot more reasons that you should consider coding as well.

你已经在做很多非常适合用软件来支持的工作，而且那些你一直以为会阻碍你的障碍，现在基本上都已经消失了。

You're already doing a lot of the activity that would be extremely well suited to being supported by software, and a lot of the barriers that you would have always assumed have kept you back are pretty much just now gone.

现在就开始的原因在于，在你真正开始之前，你很难看出你的哪些问题和工作中其实有可以用软件解决的方案，虽然我们今天会尝试在这方面做很多探讨。

And the reason to start now is that until you do, it's extremely hard to see which of your problems and work actually have software shaped solutions, although we're gonna try to do a bunch of that today.

当我遇到像之前提到的那个朋友那样的人时，我听到了一些很常见的他们还没有完全投入的原因。

Now when I run across folks like this friend that I was talking about before from my town, I hear some pretty common sets of reasons why they haven't fully dived in yet.

很多原因都归结于自我认知。

A lot of them come down to self perception.

就是那种觉得自己“不是搞技术的人”的想法，不管这到底是什么意思。

The idea that they're quote unquote not a technical person, whatever that means.

但如果你已经用AI用了好几年，并且同时在好几个订阅服务之间分配时间，那你绝对有足够的技术能力去涉足这个新领域。

But if you're someone who's been using AI for a couple of years now and is splitting your time across multiple subscriptions, you're certainly technical enough to dive into this other field.

有些人害怕搞坏什么东西。

Some folks have a fear of breaking something.

他们担心自己会犯错，或者让AI去做某件事，结果导致无法挽回的错误。

They're worried that they'll make a mistake or they'll authorize AI to do something that leads to some irredeemable error.

这也不是完全没有道理，但当然有办法来解决这些担忧，而且肯定不应该让恐惧阻碍你。

And it's not that there's no rationale here, but there are of course ways to address those types of concerns, and certainly fear shouldn't be holding you back.

对很多人来说，这仍然是进入的门槛问题。

For a lot of folks it's still perceived barriers to entry.

如果他们一开始就尝试使用终端界面，可能看一眼就转身走了。

If they tried to use a terminal interface first, they might have taken one look at it and turned right around.

而且，可能有些入门方式不对。

And relatedly, maybe some of the on ramps were wrong.

如果他们试图在网上找教程，那些教程可能让他们构建的东西跟他们的工作不相关。

If they tried to find some tutorial online, it might have been having them try to build something that wasn't relevant for their work.

我觉得这是个大问题，他们从自己的角度不确定构建和使用AI编程到底能给他们带来什么。

And I think that's the big one that they're just not sure from where they're sitting what building and using AI coding could actually be for for them.

所以，让我们专门来回答这个问题。

So let's try to answer that question specifically.

我们将从三种构建模式开始。

And we're gonna start with three build patterns.

你可以把构建模式理解为，你写的软件与现有工作之间的关系。

You can think about a build pattern as the software that you're writing's relationship to work that already exists.

我觉得可以分成三类。

I think it falls into three categories.

是复制旧的结果，改变旧工作的完成方式，还是让以前不可能完成的工作变得可能？

Is it reproducing an old output, changing the way an old job gets done, or making a previously impossible job possible?

那么，第一种模式，我们称之为自动化。

So, pattern one, let's call automation.

同样的工作，同样的结果。

Same job, same output.

在这种情况下，结果保持不变，但你不再手工完成。

In this case, the output stays the same, but you stop making it by hand.

比如重命名文件、同步列表、填充模板、重新处理导出文件，诸如此类的事情。

This could be renaming files, syncing lists, filling templates, reworking exports, those types of things.

如果接收这项工作成果的人不会注意到任何变化，那你就知道这项工作属于这种构建模式。

You know that the work falls into this build pattern if someone who is receiving the output of that work wouldn't notice that anything had changed.

如果你构建的软件出了问题，你只需回到手工操作，手动执行相同的步骤。

If the software that you built to do it broke, you would simply go back to doing it by hand, doing the same steps manually.

对有些人来说，这是个不错的起点，因为他们已经知道什么是对的，而且这类工作大多是重复性的，相对你真正想做的事情来说，既费时又耗精力。

For some people this is a good place to start because they already know what correct looks like, and a lot of this is the type of rote work that is time and energy draining relative to the things that you might actually want to be doing at work.

第二种模式，我们称之为升级。

The second pattern we'll call upgrade.

就是同样的工作，但产出是新的。

So, job, but new output.

比如，报告变成实时仪表盘，演示文稿变成网页应用，状态邮件变成自助查询页面。

An example of this would be a report becoming a live dashboard, a deck becoming a web application, a status email becoming a self serve page.

自动化模式下，接收工作成果的人看不出差别，但升级模式下，对方得到的东西明显不同，而且通常要好得多。

Whereas with automation, the receiver of that work wouldn't be able to tell the difference, the person on the other end of this one gets something that is distinctly different and presumably a lot better.

如果做这个的软件出了问题，你可以退回用旧的PDF、表格或开会，但那样做可能会让你很不爽。

Now, if your software broke for doing this, you could fall back to the old PDF spreadsheet or meeting, but it would probably be pretty unsatisfying to do so.

升级工作的回报不只是节省时间，而是让这类重复任务变成真正的资产，成为超越他人、脱颖而出的方式。

The payoff for upgrading work is not just saving time, but that one of these types of recurring tasks becomes an actual asset, and a way to outperform and stand out.

第三种模式最令人兴奋，但除非真正身处其中，否则最难理解。

Pattern three is the most exciting, but the hardest to wrap our heads around until we're actually in it.

那就是发明。

And that is invention.

换句话说，就是新工作、新产出。

In other words, new job, new output.

这种构建模式涉及以前不存在的工作，因为以前用老办法手动做根本不现实，甚至根本不可能。

This build pattern involves jobs that didn't exist before because doing it the old manual way was never practical or even possible.

比如采访每个人、监控数百个来源、测试成千上万种文案组合。

Interviewing every person, monitoring hundreds of sources, testing thousands of different combinations of copy.

在软件出现之前，这些完全超出了可能的范围。

All of these would have been completely outside the realm of the possible in the pre software world.

但现在，突然之间，因为构建，以前不可能的事情变得可能了。

But now, all of a sudden, thanks to building, something that wasn't possible before becomes unlocked.

除了有时候从外面很难看出什么会是这种发明的好的用途之外，还有一个风险，就是由于没有现成的东西可以模仿，你可能会发现自己构建了一种能力，但最终你和其他人都不会用。

Now, in addition to it sometimes being hard to spot from the outside what is going to be a good use of this type of invention, there is also a risk that because there is nothing proven to copy, you might sometimes find yourself building a capability that neither you nor anyone else ultimately uses.

当然，我构建的东西远远多于我日常真正用到的，这就是做这行的代价。

Certainly, I have built far more things than are actually part of my day to day routines, and that's just part of the cost of doing business.

好，现在我们有了三种构建模式：自动化、升级和发明。

So, okay, we've got three build patterns now, automate, upgrade, invent.

接下来，我们来谈谈交付类别。

Next up, let's talk about delivery classes.

这涉及所生产软件的形式，以及谁在使用它、用来做什么。

This is about the shape of the software that gets produced, and it is about who is using it and for what.

理解这一点将决定你需要构建的软件类型的很多方面。

Understanding this is going to determine a lot about the type of software that you need to build.

无论你构建什么，都需要考虑多少安全性、文档、用户界面、用户体验、支持等。

How much security, documentation, UI, UX consideration, support, whatever you're building is actually going to need.

事实证明，这里面的差异很大。

And it turns out there is a significant range here.

所以，我们来聊聊几个非详尽的类别。

So let's talk about a handful of non exhaustive categories.

在光谱的一端，你有原型。

On one end of the spectrum, you have prototypes.

这是一种临时构建，目的是回答问题、测试某种交互或想法，或者帮助推动决策进入下一步。

This is a temporary build whose job is to answer a question or test some sort of interaction or idea or help move a decision to the next step.

你产出的东西实际上可以相当随意。

What you produce can actually be pretty disposable.

你可能是在为自己的工作或团队做原型，或者用原型作为一种新方式，向其他团队解释你希望看到的功能，而以前你无法做到这一点。

You might be prototyping something for your own work or team, or using prototypes as a new way to explain features you'd like to see in engaging with other teams that you weren't previously able to.

这些构建要优化的是速度、清晰度和代表性示例，而不是安全性、深度、可用性之类的。

These are builds that you're going to optimize for speed, clarity, representative examples, not security, depth, usability, anything like that.

在持久性阶梯上再往上，就是很多人所说的个人软件。

Moving up the ladder of durability, we have next what a lot of people are calling personal software.

这是你为自己或身边的小团队打造的工具，以持续可靠的方式处理某个特定需求。

This is a tool that you've built for yourself, or perhaps a small team around you that handles some particular need in an ongoing and reliable way.

原型可以只展示想法，但个人软件仍然需要足够好，真正完成你或团队需要做的事情，但你仍然可以在完美用户体验、权限考虑、视觉打磨、边缘情况等方面做出妥协。

Whereas a prototype can just show the idea, personal software still needs to be good enough that it actually does the thing that you or your team needed to do, but you can still compromise on things like perfect UX, permissions considerations, visual polish, edge cases.

基本上，因为它是为你自己做的，只要你觉得某个妥协值得，你就可以做出那个妥协。

Basically, because it is for you, anywhere a compromise feels worth it to you, you can make that compromise.

这跟下一个类别有点重叠，再往上一个耐久度等级，我们可以称之为生产级软件。

This blurs a bit into the next category, one more up the ladder of durability, which we might call production grade software.

这种软件会被其他人使用，而不是你或者你的小团队。

This is software that's going to be used by other people that aren't you or your small team.

在这种软件里，一旦出问题，可能会损失信任、时间、金钱、访问权限等等。

It's where a failure could cost trust, time, money, access, etcetera.

它必须足够好，让那些不是你的用户，在真实的负载条件下也能正常使用。

It needs to be good enough that users who, again, aren't you can actually use it under realistic load conditions.

必须要有解决问题的途径，因为问题肯定会出现的。

There have to be pathways to solve problems that inevitably come up.

它需要有足够的安全性、访问控制、隐私保护等等，来满足用户的需求。

It's got to have enough security, access control, privacy, etcetera, to meet the needs of whoever the users are.

但还不是面向大众消费的那种。

But you're still not talking about mass consumption.

它仍然是非常小众的，针对特定目的，针对特定人群。

It is still extremely discrete, for some specific purpose, for some specific group of people.

现在需要注意的是，即使个人软件和生产软件，按照我这里的定义，比原型更耐用，它们仍然可以被丢弃。

Now, it's important to note that even though personal software and production software, as I'm defining them here, are more durable than prototypes, they still can be disposable.

如果你的个人软件或生产软件只对某个特定目标在某个特定时间段内有用，然后你就不再使用它，这也是可以的。

It's okay if your personal or production software is only useful for some specific goal for some specific period of time, and then you cease to use it.

这就是现在构建软件与以往如此不同的原因之一，以前我们不会花时间去构建可丢弃的软件，我们会用其他方式解决问题，因为构建那种软件的成本，相对于我们为之投入的时间或特定用例来说，是不划算的。

This is one of the things that's so different about building software now is that we wouldn't have taken the time to build disposable software before, we would have solved it in other ways, because the cost of building that software wouldn't be justified by the amount of time or the specific use case that we were building it for.

这个等式发生了变化，带来了很多有趣的机会。

That equation changes and it opens up a lot of interesting opportunities.

最后一个类别，在耐用性和重要性的阶梯上最高的一级，是真正的产品，它不仅仅是为了服务某个特定群体，而是为了服务整个市场。

The last category, all the way up the ladder of durability and significance, is an actual product that's meant to not just serve some specific group of people, but to serve a market overall.

这时候你才真正像以前的软件工程师一样，发布一些你甚至不认识的人会以某种方式使用的东西。

This is where you really are acting like a software engineer of yore and releasing something where people you don't even know are gonna be using it in some way.

而且，这包含了为大众消费构建软件时一直存在的所有考虑和负担。

And in that, it has all of the same considerations and burdens that building software for general consumption always had.

现在让我用AI DB中的一个演示示例来让你感受一下。

Now let me use a demonstrative example from AI DB to give you a sense of this.

AI日报一个有趣的地方是，我听到很多人说他们喜欢它的信息密度。

One of the interesting things about the AI Daily Brief is that one of the things that I hear most that people enjoy about it is its information density.

大家真的很喜欢每分钟获得的价值比例。

People really like the ratio of the amount of value they get per minute.

不过，对于新听众来说，这种信息密度可能会造成很大的入门障碍。

However, for someone new, that information density can create a really big barrier to entry.

所以有一段时间，我一直在想把每一期内容拆成更小的片段。

So for a while, I had the idea of breaking every edition into smaller chunks.

因为我看到最常见的增长方式是同事之间互相分享节目，所以我想围绕每期节目中的关键引语、主题、想法或数据来组织这些片段，这样听众不仅能分享整个节目，还能分享他们认为对同事有用的具体部分。

Since the most common growth pattern that I've seen is colleagues sharing the show with each other, I wanted to organize those chunks around these specific key quotes or themes or ideas or statistics that comprised any show so that a listener would be able to not just share the entire show, but the very specific part of the show that they thought would matter to their colleague.

这就是我们现在在aideallybrief.ai上看到的网站。

This is what became the current website that we have at aideallybrief.ai.

但这个过程是从一个原型开始的。

But that process started with a prototype.

在我真正构建整个系统之前，我做了很多测试，看看我用的AI是否足够好，能否自动提取这些主题。

Before I actually built the entire system for this, I did a bunch of testing to see was the AI that I was using good enough to actually automate the extraction of these themes.

简单来说，直到我们用了Fable和GPT 5.6才做到。

And in short, it wasn't until we got Fable and GPT 5.6.

但一旦我通过原型验证了它确实够用，我就把它推进到个人软件的下一阶段，真正搭建了提取流程，能把转录稿变成网站上的新一期内容。

But once I had prototyped to figure out that indeed it was good enough, I could move it to the next category of personal software, where I actually built the extraction pipeline that could take a transcript and turn it into a new edition on the website.

这里有些东西是不能妥协的，有些则可以灵活处理。

There were certain things that were noncompromisable here and certain things that I could compromise on.

等我自己用起来没问题了，我就需要让团队里少数几个人也能用，这我还是把它归为个人软件那一类。

And then once I had that working for me, I needed to make it accessible for a small number of people on my team, which I still consider that personal software category.

接下来遇到的问题是，我在社交媒体上投入不够。

The next problem that I had is that I just haven't invested enough in social.

虽然我不认为仅仅自动化内容生产流程就能算作完整的社交媒体策略，但它肯定是任何社交媒体策略的基础。

And while I don't believe that just automating a content pipeline is a sufficient social strategy, it is certainly the basis for any social strategy.

我产出这么多内容，现在又能轻松分段分享，却一直没分享出去，这实在太可惜了。

The fact that there is so much content that I'm producing that now gets segmented in easily shareable ways but wasn't being shared was just dumb.

所以我接下来又做了一个自动化流程，把网站上的提取内容转化成适合Twitter和LinkedIn的社交媒体帖子，然后自动发布。

And so the next thing I built was another pipeline automation that would take the extractions for the website and turn them into social content for Twitter and LinkedIn, and then automatically post them.

在很多方面，这仍然算是个人软件，因为我并不是真的在用它服务别人，但一旦它和现实世界的系统互动，界限就开始变得模糊了。

Now in a lot of ways this is still personal software because I wasn't actually having it serve others, but it starts to get blurry as it interacts with real world systems.

也许对我来说，生产软件更好的例子是我不会给你们展示的那个，那是我正在为赞助商构建的一个新的报告系统。

Maybe a better example of production software for my world is the one that I'm actually not going to show you an example of, but is a new reporting system that I'm building for sponsors.

它不再是那种列着统计数据的邮件或电子表格，而是一个登录体验，赞助商可以随意点击浏览，了解他们广告所在的各集节目的表现情况。这个系统绝对属于生产软件的范畴，不只是为我和我的小团队服务，而是为其他人服务，但这些人是我实际认识的一小群人。

Instead of emails or spreadsheets that have lists of statistics, it's going to be a sign on experience that sponsors can just click around in, get insights about the performance of different episodes that their ads were featured on, and that is one where it is absolutely in that category of production software that is not just for me and my small team, but for serving others, but where it's a very discrete set of others that I actually know.

当然，接下来可能还有下一步。

Now, of course, there could be a next step available.

比如说，如果我想把那个赞助商报告软件变成一个人们可以直接购买的产品，那从我和赞助商共享的生产软件到向别人销售的产品之间，会有巨大的跨越。

For example, if I wanted to turn that sponsor reporting software into a product that people could just buy, there would be a massive leap between the production software that I was sharing with my sponsors and the product which I was selling to others.

所以这就是这两者之间的区别。

So that's the difference between those two.

毕马威和德克萨斯大学奥斯汀分校的一项新研究发现，当人们与AI合作时，相似的技能并不能保证相似的结果。

A new study from KPMG and the University of Texas at Austin found that when people work with AI, similar skills don't guarantee similar outcomes.

研究人员研究了500多名早期职业专业人士，发现表现最好的人通过指导、评估和优化AI的输出，持续放大了AI的价值。

Researchers studied more than 500 early career professionals and found that the best performers consistently amplified the value of AI by guiding, evaluating, and refining its outputs.

这些顶尖表现者，被称为AI放大器，他们的优势不在于知识本身，而在于他们如何与AI协作。

These top performers, called AI amplifiers, weren't defined by what they knew alone, but by how they worked with AI.

想了解更多关于AI放大器与其他人的区别，请访问kpmg.com/us/aiaamplifiers。

Learn more about what separates AI amplifiers from everyone else at kpmg.com/us/aiaamplifiers.

市面上每个AI编程工具首先做的事情都一样。

Every AI coding tool on the market does the same thing first.

那就是开始写代码。

It starts writing code.

而Blitzy恰恰相反。

Blitzy does the opposite.

在写一行代码之前，Blitzy会花几天时间逆向工程你的整个代码库。

Before writing a single line, Blitzy spends days reverse engineering your entire codebase.

数千个代理处理数百万行代码，映射每一个依赖关系、每一个未记录的约束、每一个过去十年做出的架构决策。

Thousands of agents ingest millions of lines, mapping every dependency, every undocumented constraint, every architectural decision made over the last decade.

最终形成一个动态知识图谱，它理解你的软件的方式，就像一位在建筑领域深耕三十年的首席工程师一样。

The result is a dynamic knowledge graph that understands your software the way a principal engineer would after thirty years in the building.

其他工具靠grep搜索和markdown文件来猜测上下文。

Other tools guess at context with grep searches and markdown files.

Blitzy从不猜测。

Blitzy never guesses.

它先建立真正的理解，然后自主交付超过80%的完整软件史诗。

It builds true understanding first, then delivers over 80% of entire software epics autonomously.

经过验证、端到端测试、生产级质量的拉取请求。

Validated, end to end tested, production grade pull requests.

这就是为什么财富500强的工程团队在最关键的代码库上信任Blitzy。

That's why Fortune 500 engineering teams trust Blitzy with the code bases that matter most.

去blitzy.com亲自看看吧。

See for yourself at blitzy.com.

就是blitzy.com。

That's blitzy.com.

我每天都在这个节目里报道AI潜力与现实之间的能力差距。

I cover the capability gap between AI potential and AI reality every day on this show.

大多数公司还在摸索怎么起步。

Most companies are still figuring out how to start.

Robots and Pencils 已经在推出并扩展了。

Robots and Pencils is already launching and scaling.

Agendaq 和生成式 AI 在几周内就投入大型企业的生产环境。

Agendaq and generative AI in production at large enterprises in weeks.

AWS 高级合作伙伴，一年内规模翻了一倍多。

AWS advanced tier pattern partner more than doubled in a year.

而且他们正在招人。

And they're hiring.

有50个空缺职位。

50 open roles.

如果你觉得这个时代不一样，想参与其中而不是旁观，那这值得一看。

If you're someone who knows this moment is different, who wants to be inside it, not watching it, this is worth a look.

在 Robots and Pencils，最好的想法胜出，团队也刻意保持非常高的水准。

At Robots and Pencils, the best ideas win, and the team is purposefully kept super high quality.

这种地方，你会回头觉得是自己做过的最好的决定。

This is the kind of place you look back on as the best decision you ever made.

去 robotsandpencils.com/careers 看看吧。

Take a look at robotsandpencils.com/careers.

本期《AI每日简报》由Hyperagent赞助播出，你可以在那里运行团队可以共同管理的智能体集群。

This episode of the AI Daily Brief is brought to you by Hyperagent, where you run fleets of agents your team can manage together.

新用户可以获得1000美元的推理额度。

New users get $1,000 in inference.

别再依赖本地智能体和聊天工作流，等着你的笔记本电脑被提示了。

Forget local agents and chat workflows waiting on your laptop to be prompted.

Hyperagent在云端部署始终在线的智能体，在你团队已经使用的工具中完成实际工作。

Hyperagent deploys always on agents in the cloud, doing real work across the tools your team already uses.

营销部门的智能体把竞争对手的动作变成落地页。

Marketing's agent turns competitor moves into landing pages.

销售部门的智能体丰富潜在客户信息、起草邮件并更新CRM。

Sales's agent enriches leads, drafts emails, and updates the CRM.

运营代理负责处理文书工作和跟踪预算。

Ops agent chases the paperwork and tracks the budget.

每个代理都能访问共享上下文，并遵循你关于范围和审批的规则。

Every agent has access to shared context and follows your rules about scope and approvals.

是时候让代理像团队成员一样工作了。

It's time you add agents that feel like teammates.

在Hyperagent雇佣你的代理，它由Airtable团队打造。

Hire yours at Hyperagent, built by the team at Airtable.

在hyperagent.com/aidailybrief领取你的1000美元推理额度。

Claim your $1,000 in inference at hyperagent.com/aidailybrief.

好的。

Okay.

现在我们讨论了三种构建模式，以及四种不同的交付类别。

So now we've talked about the three build patterns in these four different delivery classes.

但对你来说呢？

But what about for you?

你工作中的哪些部分可以变成软件？

Which parts of your work could be software?

关于这一部分，我要特别说明一下：没有外人能确切告诉你，你的哪些工作最适合变成软件。

My big asterisk on this part of the episode is that no one from outside is going to be able to tell you exactly which of your work would be best suited to becoming software.

但以下是一些我见过、也亲身经历过的常见模式，或许能帮你打开思路。

But these are some common patterns that I've seen and that I've experienced that could maybe get the juices flowing.

我把它分成了六类。

I've organized it into six categories.

演示类工作、内容类工作、数据类工作、文档类工作、收件箱类工作，以及行政类工作。

Presentation work, content work, data work, document work, inbox work, and admin work.

那么，先说说演示类工作。

So, presentation work.

几乎我们所有人，在某些方面，都需要向别人展示东西。

Pretty much all of us, in some ways, have to show things to people.

这是最适合“升级”模式的一个领域——底层工作不变，但输出形式焕然一新。

And this is one of the best areas for that upgrade build pattern, where the underlying job stays the same but there is a totally new type of output.

所以，想想这些问题。

So think about these questions.

你有没有哪种演示，如果能互动会更好？

Do you have some sort of presentation that would benefit from interactivity?

别用PDF了，直接做个HTML页面。

Instead of doing a PDF, build an HTML page.

其实，我在之前的节目里专门讲过一期，为什么你应该用HTML而不是其他内容形式。

In fact, I have a whole episode in the archive about why you should be using HTML instead of other content forms.

你是不是经常跟不同的人解释同样的事情？

Do you explain the same things to different people?

如果你把同一套信息讲了一百遍，那可能很适合做成一个互动讲解工具，或者一个能回答问题的机器人。

If you've walked through the same set of information a 100 different times, that might be a good fit for an interactive explainer or a bot that answers the questions.

你是不是经常为不同的人做同样的计算？

Do you calculate the same things for different people?

同样，这也可以变成一个自助计算器。

Again, that could become a self managed calculator.

你会帮别人比较选项、方案、供应商、场景或套餐吗？

Do you help people compare options, plans, vendors, scenarios, packages?

那就可以做成一个比较工具。

That could become a comparison tool.

你会负责培训或带新人吗？

Do you onboard or train people?

如果你每次都要给新客户或新员工讲同样的内容，那就可以做成一个引导流程、清单，甚至是一个小测验。

If you give new clients or new hires the same tour every time, that could become a walkthrough, a checklist, or even a quiz.

你会告诉别人进展如何，并发送相关的更新邮件吗？

Do you tell people where things stand and the any update emails that come along with them?

那正好可以做一个自动更新的状态页面，让他们自己查看，不用老来问。

That is waiting for an automated status page so they can just look at it and stop asking.

你是不是经常要查同样的参考资料？

You keep looking up the same reference material?

比如费率、规则、联系方式之类的？

Rates, rules, contact specs?

再说一次，我觉得这非常适合做成一个查询工具。

Again, that sounds to me like great fodder for a lookup tool.

下一个类别是内容工作。

Next category is content work.

这也是一个非常常见的类别。

Another very common category.

AI最擅长的事情之一就是把内容转换成其他内容。

One of the things that AI is the best at is turning content into other content.

如果你把转录稿变成摘要，或者把长内容变成短内容，或者把一份内容变成五篇帖子，这不仅非常适合AI，而且你可能已经在用AI做这些了。

If you turn transcripts into summaries or long things into short things or one thing into five posts, that is not only well suited for AI, and probably you are already using it for such.

你应该建立一个自动化流程来做这件事。

You should be building an automated pipeline for doing it.

想想我为网站构建的提取流程。

Think about the extraction pipeline that I built for the website.

我能不能每天把当天的转录稿扔进ChatGPT或Claude，让它提取所有关键标题，给我一个列表，然后我再手动输入到网页上。

Could I, every day, take the day's transcript, plop it into ChatGPT or Cloud, and ask it to extract all the key headlines and give me a list that I could then go manually type into the web page.

当然可以。

Of course, could.

而且那还是会比我手动提取那些部分快得多。

And that would still be a lot faster than me manually extracting those parts.

但整个流程完全没必要不自动化。

But there's no reason that entire process can't be automated end to end.

这就是我为什么选择去构建软件来做这件事。

And that's where building software to do so came in for me.

下一个类别是数据处理工作，这也是我看到很多非技术背景的知识工作者开始构建软件来帮助自己的最常见起点之一。

Now the next category is data work, and this is one of the most common starting points I see for nontechnical knowledge workers who get into building software to help them.

这很合理，因为很多数据分析师已经有一些用Python处理工作的经验。

And this makes sense given how many data analysts already had some experience writing Python to help with their work.

所以这成为很多人的入门点也就不奇怪了。

It's not surprising that this is an entry point for a lot of others as well.

如果你在做任何重复性的数据分析，比如拉取数据、制作相同的图表、回答业务进展如何，那么构建一个应用，既能提供仪表盘来回答这些问题，又能提供交互式工具让人们提出不同的问题，这绝对是构建软件的一个极佳用途。

So if you are doing any sort of recurring data analysis, pulling the numbers, making the same charts, answering how we're doing, building the application that has both the dashboard that answers it, as well as interactive tools to allow people to ask different questions of it is an incredibly good use of building software.

这基本上就是我刚才提到的AIDB赞助商门户网站的情况。

That basically describes exactly the sponsor portal that I was just discussing for AIDB.

数据工作的另一个部分，跟之前说的内容有点关系，就是数据转换，比如从一个系统导出数据，然后手动整理成别人需要的格式，就像把CRM导出变成销售表格。

Now another part of data work that kinda goes back to that content piece is data translation, where you export from one system, rework it by hand into a format that someone else needs, like a CRM export that becomes a sales sheet.

如果第一步是自动化部分流程，那第二步就是建立一个软件管道，从头到尾全自动完成。

If step one was automating parts of that process, step two is to build a software pipeline that just does it all end to end.

这种模式在下一个类别——文档工作中也很常见。很多知识工作者选择自己建软件而不是只用AI，是因为他们发现，对于反复做的事情，AI能加速，但如果想进一步自动化，就需要自己开发软件来实现。

And that pattern again shows up a lot in the next category, document work, where a lot of the starting point for knowledge workers building instead of just using AI is that if they had already figured out that on a thing they do over and over, AI can speed up doing that thing, there might be a further step to further automate it if you build software to do that automation.

比如反复填写相同的模板，对大量文件做同样的操作，像重命名、转换格式、调整大小，或者阅读大量文档找特定内容，AI可以帮你手动操作，

So filling in the same templates over and over, doing the same thing to a lot of different files like renaming, converting, resizing, reading a lot of documents to find specific things, AI could help you manually, I.

也就是

E.

你每次把东西交给AI处理，或者如果你开发软件，它就能持续自动帮你处理。

You put those things into AI each individual time, or it could be helping you in an automated ongoing way if you build a software to do so.

收件箱工作。

Inbox work.

你会不会收集别人提交的东西，比如申请、注册请求、投稿之类的？

Do you collect things from people like applications, sign up requests, submissions?

很多时候，可能已经有现成的软件能帮你解决这个问题，但也不是说完全不可能，你有一些具体的、零散的需求，跟那些供应商的产品不完全匹配，这时候就可以考虑自己建一个接收系统。

In a lot of cases, there's probably existing software that solves that for you, but it's not at all inconceivable that there's some specific discrete need that you have that doesn't perfectly fit with one of those vendors now, and that would be a reason to consider building some intake system.

顺便说一句，这又引出了另一个我觉得很重要的观点。

And this, by the way, gets to another great point that I think is important.

能建不代表就一定要建。

Just because you can build something, doesn't mean that you always need to.

一旦你开始用AI编程，你几乎肯定会发现，你盯着某个付费产品，心里想，这个我自己就能做。

One of the things that you will almost definitely find once you start your building an AI coding journey is that you'll be squinting at something that you pay for and think to yourself, I could just build that.

为什么还要花钱买呢？

Why am I paying for it?

但往往不自己做是有充分理由的。

But there will often be good reasons not to.

一个团队，他们的全部工作和使命就是围绕某个产品响应客户需求，他们做软件的能力和资源，比你把它当成待办事项里第六十八件事来做，要强得多。

A team whose whole job and mission is to respond to the needs of their customers around a particular product has a lot more raw capacity to do software well than you do as the sixty eighth thing on your to do list.

我几乎总是先看看有没有现成的东西能帮我做这件事，然后再决定要不要完全自己动手建。

Almost always, I'm checking to see if there's anything that exists out there that could be doing the thing for me before I'm committing to entirely building it myself.

举个例子，最近我在搭建社交管道的时候，本来可以直接通过X和LinkedIn的API来做自动发布，但我们发现了一个叫TypeFully的服务，它本身就具备这个功能，而且能和我们建好的管道很好地配合。

An example that came up recently when I was building the social pipeline is we could have done the automated posting directly via the X and LinkedIn APIs, but we found a service TypeFully that just had that capability natively and could interact really well with the pipeline that we had built.

这帮我省去了大量的烦恼和痛苦，也省了不少token。所以即使是在我个人的软件里，这个个人软件也能和别人的非个人软件很好地互动，形成一个完整的解决方案。

That saved me a huge amount of anguish and agony and tokens, So even in the context of my personal software, that personal software was able to interact with very much non personal software that someone else had built to be a complete solution.

那么，最后我们试着用六个理论项目来把这一切整合起来。

So let's close by trying to put this all together with six theoretical projects.

再次强调，这些只是作为启发性的想法，供你参考，并不是说这就是知识工作者最佳构建项目的典范。

And once again, these are humbly submitted just as thought starters for you, not as the paragon of the best type of build projects for knowledge workers or anything like that.

三个构建模式类别，每个类别各两个项目。

Two projects each from each of the three different build pattern categories.

首先是自动化，第一个项目我称之为“周五导出”。

First up is automation, with the first project being something I'll call the Friday export.

这个项目就是把那个你闭着眼睛都能做的电子表格例行公事，变成一个小的、可检查的转换管道。

This is turning that spreadsheet ritual that you can do with your eyes closed into a small, inspectable transformation pipeline.

所以你有一个系统导出的CSV或电子表格，你需要重命名、筛选、拆分、合并、计算、重新排序、调整格式、分析，而你要构建的是一个本地页面，你可以在那里拖入原始导出文件，预览转换过程，查看需要注意的地方，然后下载完成后的文件，格式和原来一模一样。

So you've got a CSV or a spreadsheet from one system that you rename, filter, split, join, calculate, reorder, restyle, analyze, and what you're going to build is a local page where you drop the raw export, preview the transformation, see anything that needs attention, and download the finished file in the exact old format.

交付的成果还是那个可靠的成果，但你不用再牺牲周五下午的时间了。

It's the same trusted deliverable, but you don't have to give up your Friday afternoon anymore.

类似的自动化还有发票堆积处理。

A similar type of automation is the invoice pile.

你会收到发票、收据、账单，它们以PDF或照片的形式到达，还有一个跟踪表，里面需要手动输入供应商、日期、金额、类别和参考编号。

You've got invoices, receipts, statements arriving as PDFs or photos, plus a tracker where vendor, date, amount, category, and reference number are typed by hand.

你要构建的是一个监控文件夹或拖放区域，它能读取每份文档，标准化字段，标记低置信度的值，捕捉重复项，并生成那个老式关键电子表格，但你只需要做审核，而不是手动输入。

What you're gonna build is a watched folder or drop zone that reads each document, normalizes its field, flags low confidence values, catches duplicates, and produces that same old key spreadsheet, but where you're just doing the review rather than the manual input.

你可以看到，自动化这种构建模式确实是为了节省你的时间和精力，让你有空间去做其他事情，而构建软件来实现这一点，只是你工具箱里另一个赢回时间的工具。

You can see here that the build pattern of automation really is about saving you time and agony and leaving you space to do other things, and that building software to do so is just another tool in your toolkit to win back your time.

你前期投入一点时间来构建软件，之后就能获得巨大的时间回报。

You invest a little upfront to build the software, and you get back a big time ROI on the other side.

接下来我们要讨论的项目属于升级这种构建模式。

Now the next projects we'll talk about fit into the build pattern of upgrade.

第一个想法在这期节目里已经出现过好几次了，我们叫它“实时报告”。

And the first one is an idea that's come across a number of different times in this episode, which we'll call the live report.

只要你需要定期给别人提供某些数据或分析，就可以考虑不再发快照，而是给他们一个地方，让他们看到持续或定期更新的数据流，还能自己提问、查数据，不用你当中间人。

Anytime you owe someone some set of numbers or analysis at some specific regular interval, you could consider no longer sending them snapshots, but instead giving them one place to see a continuously or regularly updated stream of data with the ability to ask questions of and interrogate that information without you having to be the interlocutor.

我的赞助商就是一个例子。也许你每周或每月要给客户、老板、董事会、资助方或赞助商发数据邮件、幻灯片或PDF，然后他们还会要求不同日期范围、不同维度的数据。

So my sponsors are an example of this, but maybe you have a weekly or monthly numbers email, a deck, a PDF for a client, a boss, a board, a funder, a sponsor, followed by requests for different date ranges, breakdowns.

你要做的就是建一个专门的页面，直接从数据源刷新。

What you're going to build is a focused page that refreshes from the source of the data.

页面会显示数据上次更新的时间。

It's going to show the user when the data was last updated.

它会自动回答最重要的问题。

It's going to answer the most important questions automatically.

它还会提供一定程度的自动分析。

It's going to provide some amount of automated analysis.

如果你想更进一步，甚至可以让他们用AI来互动，自己找答案，不用先来找你。

If And you really want to push yourself, maybe you even allow them to use AI to interact with it in some way, and try to get answers to their questions without having to go to you first.

这不仅是升级的一个例子，工作内容相同但产出更好，也是生产软件交付类的一个例子，你正在构建的东西会被别人使用，但使用者是明确且可了解的，你可以根据这个受众来决定合适的权衡。

This is an example not only of an upgrade where the job is the same but the output is better, it's also an example of the production software delivery class, where you are building something that is going to be used by someone else, but a very specific and knowable someone else, where you can still figure out based on that audience what the right trade offs can be.

第二个升级项目，我们称之为“假设滑块”。

A second upgrade project we'll call the what if slider.

我相信你们中有些人有某种预测、人员配置计划、报价、情景模型和演示文稿，最终都会遇到这样的问题：如果我们改变价格、数量、时间或人数会怎么样？

I'm sure some of you have some sort of projection, staffing plan, quote, scenario model, and deck that inevitably comes to a question of, well, what if we changed price, volume, timing, headcount?

也许你只需要用电子表格就能解决这个问题。

Now maybe you can just use a spreadsheet for this.

再说一次，我们不是为了建软件而建软件。

Again, we're not trying to build software just for the sake of building software.

Excel和Google Sheets确实很擅长让你修改数字并查看结果。

And Excel and Google Sheets are really good at allowing you to change the numbers and see what comes out.

但Excel也有它的局限性。

But Excel has its limits.

而且可能有很多额外的变量无法直接转化为数字，个人软件风格的“假设滑块”——也就是一个页面，展示变量并允许人们互动修改它们，看看另一端输出会如何变化——可能更适合这种假设情景规划。

And there might be a lot of additional variables that don't translate cleanly into numbers that a personal software style what if slider, I e, a page that exposes the variables and allows people to interact and change them to see what outputs would change on the other end, could be a better fit for that sort of what if scenario planning.

最后，还有两个偏发明创造类的理论项目。

Finally, two theoretical projects on the invention side.

第一个我们叫它“观察者”，基本上就是你的个人智能研究助手。

The first we'll call the watcher, and it's basically your personal agentic researcher.

想象一下，你有一些信息或数据会随着时间变化，而了解这些变化对你的工作至关重要。

Let's imagine that you have some type of information or data that changes over time that knowing the changes about are integral to your work in some way.

这些可能是竞争对手的定价、招聘信息、资助页面、提及、库存，或者监管指南，这些都可能随时变化。

That could be competitor pricing, job posts, grant pages, mentions, inventory, regulator guidance that changes unpredictably.

手动跟踪所有这些信息是可行的，但尤其是当这些变化不可预测时，会耗费大量时间和精力。

Trying to keep track of all of that is something that can be done by hand, but especially if it's at all unpredictable when those things are going to change, that can take a lot of time and energy.

你可以构建一个检查器，监控这些数据源，过滤掉无关的噪音，记录历史和变化，并在重要时自动发送更新。

You could build some checker that watches those data sources, cleans up for irrelevant noise, keeps track of history and changes, and automatically sends updates when it matters.

显然，这是一个以前不存在的监控任务，但现在可以帮助你以更根本的方式提升工作。

Now, this is obviously a monitoring job that didn't exist before, but which can now help you do your work in a fundamentally better way.

常听节目的听众可能会想，这听起来很像用个人代理软件（比如OpenClar，最近还有GrockBot）能做的事情，你们这么想是对的。

Now regular listeners might be thinking to themselves, gosh, that sounds kind of a lot like the type of thing you can do with personal agent software like OpenClar, more recently, GrockBot, and you would be right in that.

我觉得在接下来的几个月甚至几年里，我们需要关注的一个问题是，现在很多所谓的“构建项目”——就是需要定制开发软件的那种——有多少会被那些结合了预设功能和可定制性的智能体给解决掉。

One of the things that I think we will have to watch in the coming months and years is how many of what we might call build projects right now, where you would build custom software, get solved by agents with the right combination of preprogramming and customizability.

虽然搭建东西本身很有趣，但如果有更简单的方法能解决问题，不用费那么多劲，我们当然应该为此感到高兴。

As fun as building stuff is, we should obviously be cheering when simpler approaches allow us to solve that problem without spending all that effort.

还有一个发明项目，说实话可能最终会成为智能体的领域，我们叫它“模式阅读器”。

Another invention project which honestly might end up the domain of agents, we'll call the pattern reader.

想象一下，你有一大堆信息，没人有时间去读。

Imagine that you have some big pile of information that nobody has the time to read.

比如客服工单、销售记录、评论、申请材料、调查问卷、面试笔记、事故报告等等。

Support tickets, sales transcripts, reviews, applications, survey answers, interview notes, incident reports.

你可以做一个本地分析工具，把所有这些数据清洗一遍，把重复出现的主题归类，比较不同群体或时间段，把相关说法链接到有代表性的原始段落，并且持续提供更新后的分析。

You can build a local analysis tool that cleans it all, groups recurring themes, compares segments or time periods, links claims back to representative source passages, and provides some ongoing and updated analysis.

因为这个模式阅读器是一个持续运行的软件，它会定期自我更新，所以你随时可以跟它互动，不用费劲去准备它来回答你的问题。

Because that pattern reader is a persistent piece of software that is regularly updating itself, you can intersect with it at any given point without having to do a bunch of work to get it ready to answer the questions that you have.

需要特别指出的是，虽然我很容易就能举出一些自动化或升级型构建模式的例子，但说到发明创造，基本上只有在你开始动手摸索之后，你才会知道自己会发明出什么东西。

Now it's really important to note that while it's fairly easy for me to give you some examples of automation or upgrade style build patterns, when it comes to invention, there's pretty much no way to know what stuff you're going to invent until you start messing around.

我觉得这最终就是我想推荐的核心点。

And I think this is ultimately the point in the recommendation.

现在真的没有理由不开始尝试，看看AI编程怎么帮你干活。

There is no reason anymore for you not to dive in and start experimenting with how AI coding could support your work.

如果你想从最省事的工具开始，可以试试Lovable或者Replit。

If you want to start with the most helpful training wheels, you can do Lovable or Replit.

如果你想留在自己已经熟悉的系统里，那就试试Codex或者Cloud Code。

If you want to stay in the ecosystems that you're already operating in, try Codex or Cloud Code.

不管选哪个，从我刚才说的那些里挑一个你觉得最有点意思的，直接去试试看要怎么做出来。

In either case, take whatever seemed most vaguely interesting from all of what I just said, and just go see what it would take to build that thing.

可能最后什么都不是。

Maybe it amounts to nothing.

可能你马上就放弃了。

Maybe you abandon it right away.

也可能经过一段时间和尝试，你发现现有软件或者智能体其实什么都能帮你搞定。

Maybe after time and experimentation you decide that there's actually nothing that existing software or agents can't do for you.

但我坚信，现在做软件不是为了发布给别人用，而是为了把自己的工作做得更好，这已经成为知识工作者必须具备的一项基础能力。

But my strong belief is that building software not for the sake of releasing software for other people to use, but for the sake of doing your own work better, is now just a foundational capacity that knowledge workers need to have.

希望听完这期节目，你会觉得开始尝试没那么吓人。但今天的人工智能每日简报就到这里了。

Hopefully it feels less intimidating to start up to this episode, but for now, that is going do it for today's AI Daily Brief.

一如既往，感谢你的收听或收看，我们下次再见，祝一切顺利。

Appreciate you listening or watching, as always, and until next time, peace.