不怕 AI 垃圾内容，更怕故事无人讲述：WorkOS 的 Zack Proser 谈创作工具

简要描述Brief Description

我不怕 AI 垃圾内容，我怕的是那些未被讲述的故事——Zack Proser，WorkOSI Don't Fear AI Slop. I Fear Untold Stories - Zack Proser， WorkOS

目录Table of Contents

• 简介
  Intro
• 15年孜孜不倦的写作生涯
  15 years of obsessive writing
• 比 AI 垃圾内容更令人担忧的是
  The bigger worry than AI slop
• 在 WorkOS 构建 Blogbot
  Building Blogbot at WorkOS
• 不对称杠杆效应
  Asymmetric leverage
• 速度会扼杀匠心吗？
  Does speed kill craft?
• 每一句话都让我一惊。
  "Every sentence makes me flinch"
• 火花、风箱与淬火
  Spark, bellows and quench
• 它是真的吗、有用吗，而且美吗？
  Is it true, useful and beautiful?
• 两个人的故事工厂：睡前故事
  A factory for two: bedtime stories
• 应对 AI 焦虑的解药
  An antidote to AI anxiety
• 你要为谁建造工厂？
  Who will you build a factory for?

简介Intro

非常感谢大家来到这里。在这次演讲中，我想试着说服你们：如果你关心某个人，并且经常和他们一起工作——即使你并不经常和他们一起工作——你也应该为那个人建造一座工厂。我们会聊聊这是什么意思，以及为什么要这么做。Thank you all so much for being here. In this talk, I'm going to try to convince you that if you care about somebody and if you work with them regularly, even if you don't work with them regularly, you should build that person a factory. And we're going to talk about what that means and why.

15年如痴如醉地写作15 years of obsessive writing

那么，首先，我为什么这么说？嗯，我是一名开源开发者，至今已经15年了。不过从十几岁刚出头起，我就一直如饥似渴地、不停地写作。最开始是用铅笔、纸、钢笔和笔记本。大约16岁时，我开始使用文字处理软件。在过去15年的职业生涯中，我在不少初创公司工作过，也曾以工程师的身份在任职期间为它们的博客发表文章。此外，我也一直在自己的网站上发布内容。So, first, why do I say this? Um so, I'm an open-source developer, have been for 15 years now. But since my early teens, I was writing uh voraciously and constantly. It started off with pencil paper, pen, and notebooks. And then around 16, I was onto word processors. And in the course of my career in the last 15 years, I've worked at a bunch of startups and I've published stuff on on their blogs as an engineer while working there. And then I've constantly been publishing on my own site.

所以，我写了很多文章、教程之类的东西，都是为了满足自己的兴趣。这个过程里，只要满足了自己的兴趣，我就喜欢把它发表出来，分享给大家。所以总的来说，我写东西有点着迷，甚至可以说近乎狂热，而且已经坚持了相当长一段时间。So, I have a ton of essays and tutorials and things that I find interesting to kind of scratch my own itch. And then as part of that cycle, as soon as I scratch that itch, I like to just publish it and kind of share it with the world. And so, that is all just to say that I write sort of obsessively, kind of fanatically, and have been doing so for for quite some time.

接下来我们会聊聊我写的其中一篇帖子，它一直表现最好，而我只花了23分钟就写完了。我们也会谈谈我是怎么做到的。And we'll get into one of the posts that I I wrote here that has done consistently the best and that I wrote in 23 minutes. And we'll talk about uh how I did that, too.

比 AI 垃圾内容更令人担忧的事The bigger worry than AI slop

但我相信你们当中有些人已经在想：呃，这不是……你知道，这不是一场 AI 会议，也不是一场关于 AI 的演讲。当然，这里面确实涉及 AI 垃圾内容。不过，我要告诉你们，有件事比 AI 垃圾内容更让我担忧。并且我相信，只要我们在塑造作品时秉持正确的意图，评判最终成果，并让自己和彼此承担责任，那么实际上，我们完全可以借助 AI 创作出比不借助它时更好的故事，也可以改进流程，让更多人更有效、更稳定地讲述故事。好了，回到我刚才提到的那篇帖子：这是我写的一篇文章，讲述了我在过去十五年左右运营并自主出版一个科技博客的亲身经历。But I'm sure that some of you are already thinking uh this isn't, you know, this isn't an AI conference, isn't an AI talk. Uh certainly there is slop involved here. And uh I'm going to tell you that there is something that I'm far more concerned about than AI slop in particular. And I believe that if we uh bring the right intention to shaping the work and we judge the result and we hold ourselves and each other accountable, that it is actually possible to use AI to produce better stories than we can without it and to improve processes so that more of us can tell stories more effectively and more consistently. So, to get back to that post I was talking about, uh this is a post that I wrote about my own experience over the course of, you know, decade and a half running and self-publishing a tech blog.

我也分享了一些自己的体验，比如运营这件事是什么感受，以及如何坚持下去、保持连贯。在大型语言模型出现之前，我把这篇文章从无到有写出来，整理成 Markdown，并在 23 分钟内完整发布了出来。那是在我经历了一段特别折腾的睡前流程、把两个幼儿哄睡之后。所以，我的同事和一些朋友总会问我：你怎么写得这么快？And I made some, you know, shared kind of what the experience was like and what it what it's like running that and keeping up the consistency. And I published this in I wrote the entire thing from didn't exist to written into markdown and and fully published in 23 minutes before LLMs. And it was after a particularly brutal bedtime routine putting down my two toddlers. And so inevitably what my colleagues and some of my friends would would constantly ask me is how do you write so fast?

你会想：“你到底在做什么？这怎么可能？你一天的时间并不比我多啊。”当我思考这个问题时，我意识到答案是：我一直都在写作。所以在某种程度上，我近乎痴迷地不断尝试新的标题、想法或句子，琢磨自己可以讲什么故事，或者该如何展开那个故事，才能让它尽可能引人入胜、产生最大的影响。Like what are you doing and how how is this possible? You don't have more time in the day than I do. And when I thought about this, I realized that the answer is that I am always writing. And so to some degree, I'm kind of obsessively trying out new titles or ideas or sentences or how what stories might I tell or how might I develop that story so that it is the most compelling and impactful that it could possibly be.

因此，我基本上曾是我个人所知道的唯一一个内容工厂。你知道，我就是做自己的事，在初创公司工作、当开发者，同时又不断发布内容。所以我个人倒没那么担心 AI 垃圾内容，因为我认为我们可以运用大量技巧来改善它，也有办法解决这个问题。我更担心的是那些始终无人讲述的故事。And as a result, I was essentially the once the only content factory that I knew personally. You know, just kind of, you know, doing my thing, working at in startups, being a developer, but then constantly publishing. And so I personally am not as worried about AI slop because I think there's a tremendous number of techniques that we can apply to to fix that and I think there's ways to solve that problem. I'm I'm significantly more concerned about all the stories that go untold.

所以，我在职业生涯中以及与许多优秀、有才华的人共事时注意到，很多人会对自己说：“哦，我不是写作者，我做不到。”很多人会因为各种原因感到恐惧和羞耻；无论他们有过怎样的经历，或者他们的自我认知如何限制了自己，他们都因此无法分享自己最有影响力的作品，也无法以最能影响自己和未来职业发展的方式分享这些作品。And so what I've noticed over the course of my career and working with a bunch of excellent and talented folks is that a lot of folks tell themselves, oh, I'm not a writer, I can't do that. A lot of folks feel fear and shame for various reasons, whatever the their experience might be or or their self-concept limits them from actually sharing the most impactful work and sharing it in a way that would be most impactful to them and their their future career.

所以，这就是为什么我说，现在是时候考虑建造充满爱与恩典的工厂，并把它们赠予他人了。And so this is why I say that it's it's time to consider building factories of love and grace and to give them away.

在 WorkOS 构建 BlogbotBuilding Blogbot at WorkOS

所以我们要进一步探讨这实际上意味着什么。我是 WorkOS 应用 AI 团队的一名工程师，已经在那里工作两年了。大约一年前，我们决定需要再次提高内容发布的速度——不是为了往互联网上疯狂倾倒低质内容，而是因为我们有多个团队和许多成员，他们一直在做出色且富有创新性的工作，但我们并没有持续地讲述这些故事，也没有把我们的洞见以及正在做的事情带给市场。于是我搭建了最初的系统，我们称之为 Blog Bot，对吧？这是一个基于 Cloudflare 构建、运行在云端的系统。因为我有着近乎执着的写作背景，所以我能够思考：在这门技艺中，我认为什么样的作品才称得上优秀，对吧？So we're going to develop what that actually means. So I am a engineer on the Applied AI team at WorkOS. I've been there for 2 years. About a year or so ago, we decided that we needed to increase publishing velocity again, not to slop cannon in the internet, but because we had multiple teams and folks that were doing excellent and innovative work constantly, and we were not consistently telling all those stories and kind of bringing, you know, our insight and stuff that we were doing to the marketplace. And so I built the initial what we call Blog Bot, right? And this is a system that was built on Cloudflare, and it runs in the cloud, and because of this sort of obsessive writing background that I had, what I was able to do was to think about what do I believe makes a good artifact in in this in this craft, if you will, right?

那么，随着时间推移，经过一次又一次的尝试，我个人逐渐认为，哪些东西能让内容更有趣、更吸引人，嗯，也就是更具教学价值？我就把这些东西全都塞进一个盒子里，让它自动化，然后把这个盒子交给了同事们。And so what are all the things that over time and many, many repetitions I have come to believe personally make something more interesting, more engaging, you know, um to have better pedagogical value. And I just kind of stuffed those all into a box that made it automated, and then I handed that box to my colleagues.

不对称杠杆作用Asymmetric leverage

而最终为他们带来的，就是我现在所说的“非对称杠杆效应”。同事可以在 Slack 里打开一个非常简单的界面——这是他们早已熟悉、每天都在使用的工具——然后说：“Blog Bot，我们这里有一份活动的文字记录，我想请你根据它写一篇符合品牌调性、切合主题、达到 WorkOS 博客质量标准的活动回顾文章。”他们得到的会是一份初稿，完成度大概已经有 85% 到 90%。And what that ended up producing for them was this what I call asymmetric leverage now. So a colleague can come into a very simple interface in Slack, something that they already understand and use every day, and say, "At Blog Bot, we've got this transcript from an event, and I want you to produce an on-brand, you know, on-theme, you know, reaching the quality bar WorkOS blog post about it recapping it." And what they get out is, you know, a draft that is 85 to 90% of the way there.

这意味着，他们不必再手动、费时地把所有背景信息拼凑起来——无论是 Granola 录音、活动图片、大家在 Slack 上的相关讨论，还是我们希望采用的叙述角度。所有这些信息都会自动为他们收集整理好。最终产出的是一篇基本上已经准备就绪、几乎可以发布的博客，但还需要再迭代几轮，并由人从头到尾读一遍、署上自己的名字，然后发布。It means that they haven't had to manually and tediously assemble all the context from the Granola recordings or the images of the event or what folks said about it in Slack to prepare or the framing that we wanted to use. All of that is automatically sourced for them. And what they arrive at is a blog that is essentially ready to almost ready to go, but needs a couple more iterations and for a human to read all the way through and to put their name on it and to publish it.

因此，非对称杠杆效应的妙处在于，你可以用一个非常简单的界面作为门面，背后却是一个极其强大、甚至复杂的分布式系统。这个系统可以通过数据连接器接入公司里你关心的每一个信息源，还可以使用自定义工具、请求人工审批以确认事实，等等。我们甚至还有一个专门用于生成图像的端点，嗯，它生成的结果和我们优秀且才华横溢的设计团队做出来的作品简直一模一样。And so the nice thing about asymmetric leverage is that you can hide behind a very simple interface an incredibly powerful and even complex, you know, distributed system that has a data connector to every source of information that you care about in your company, custom tools, the ability to ask a human for approval to confirm facts, etc. We even have a special endpoint that has that does image generation that is um the outputs resemble exactly what our excellent and very talented design team would produce.

所以，你知道，持续这样做，并让组织内的其他人也能执行这一流程，确实能提升整个组织的内容发布速度。比如，最初的草稿或提示词只是我同事说：“嘿，我们刚办完一场活动，想写篇回顾文章。我手头还有些别的事，要不你先起草一下？”And so that, you know, consistently doing this and allowing other people to run it does across the org increase publishing velocity. And so with just that initial draft or just that initial prompt where my colleague said, "Hey, we just had an event. We want to do a recap post about it. I have some other things on my plate right now, so why don't you start the draft, right?"

而他们得到的回报——我所说的非对称杠杆，就是他们能拿到这样的回报：有实质内容的东西。它还没到可以一口气直接上生产环境的程度。需要有人为它负责，把所有内容都读一遍；不过，我们已经完成了，或者说系统已经替他们完成了大量工作，把最初的素材拼装起来。更重要的是，之后完全由他们自己来调整和打磨，让它符合自己的喜好，我完全不必参与。所以他们不需要——你知道的——来找我帮忙，也不需要找任何有写作背景的人。他们只要用非常简单的方式做出自己想要的修改，就能把工作完成。你知道，我发布之后一开始看到这一切还挺有意思的：这些东西开始运转起来，那边的人也开始产出内容。And what they get back, what I mean by asymmetric leverage is this is what they get back, something substantial. It is not ready to one shot all the way to prod. Somebody has to take responsibility for it and read it all, but we have done or the system has done a significant amount of the work for them to assemble the the initial pieces. And then it is, more importantly, something that is solely in their power to adjust and tune to their liking without me being involved at all. So they don't need to, you know, ask me to do anything or anyone else that that might have a writing background. They can just make the changes that they want in a very simple way and kind of get their work done. And so, you know, this was fun to initially see after I published that this stuff started working and folks there were producing things.

速度会扼杀工艺吗？Does speed kill craft?

我记得大约在那段时间，我和 WorkOS 的创始人 Michael Grinich 聊过。我们谈到当时公共舆论场上那场激烈的争论：大家在讨论所谓的“垃圾内容加农炮”，以及 AI 写作全是垃圾之类的话题。与此同时，人们又渴望提高效率。对我们这些经验丰富的开发者来说，很明显，我们可以利用这些强大的工具，在几天内构建出过去要花几个月才能完成的东西。And I remember around this time I had a conversation with Michael Grinich, the founder of Work OS. We were talking about, you know, the pretty the debate that was happening kind of in the public square about, you know, slop canonning and and, you know, AI writing is all slop, etc. And at the same time the desire to move faster and for us as experienced developers, we were seeing it was very obvious that you could use these powerful tools to build things in days that used to take us months at a time.

于是迈克尔用了一个比喻，给我看了一个 YouTube 视频。视频里，一家公司在生产线上大规模组装符号，你知道，生产速度非常非常快，却又对每一个都进行检查。起初，他想把这个类比引到我们开始尝试的事情上来：这有点像我们正在用这个博客机器人和其他工具做的实验。And so Michael used a metaphor and he showed me a YouTube video where a company was mass assembling symbols on a production line and, you know, producing them very, very rapidly and yet inspecting all of them. And initially, and he was trying to, you know, draw the the parallel to this is kind of what we're starting to experiment with with these this blog bot and other tools as well.

迈克尔说：“这在我看来简直就是工艺精神的体现。”我记得我们最初一起看那段视频时，我有点退缩，没法完全坦然地接受“是啊，我想我可以更快地写出文章，或者更快地创作内容”这个说法。但迈克尔的意思是，工艺精神贯穿整个生产流程。所以，尽管机器往往承担了大量、甚至某些环节里全部的繁重工作，以人类无法企及的速度生产出一个个产品，但那家公司并没有丢掉对工艺精神全心全意、深入骨髓的坚持：每一台设备都要经过检查，由一位在公司工作了很久、明白质量标准是什么的音乐家亲自演奏。他会演奏，你大概能从他的口型看出他在说“真漂亮”，然后他把设备交出去，这台就算验收通过了。他还会写上：“我，这个人，已经为这个符号签字认可。”And Michael said, "This screams craft to me." And I remember the initial time that we were kind of looking at that video together, I sort of flinched and didn't fully feel comfortable to accept that, "Yeah, I guess I can produce an articles even faster or content even faster." But Michael's point was that craft runs through the entire line. So, even though machines are often doing must much of the heavy lifting or even all the heavy lifting in some parts and producing units at a speed that humans could not approach, what has not left that company is a complete and profound dedication to craft and inspecting every single device as played by a musician that has been with the company for a long time and understands what the quality bar is and plays and he you can kind of see if you read his lips he's saying it's beautiful and then he hands it off and that one's good to go and he's putting, "I, this person, signed off on this symbol.

它已经可以用这个品牌名称来制作了。”所以，他们先试用、聆听，然后做出决定。它们或许以极快的速度制作出来，但质量并没有因此打折。这就是为什么迈克尔告诉我：“这在我看来就是匠心。”起初我对此感到不太自在，但后来我回过头来，想了想自己写作的历程，意识到我并不认同他。于是，在博客文章发布到第二或第三个版本之后，我们发布了一篇回顾文章。那时，我们已经看到整个组织的发布率上升；更重要的是，从我个人的观察来看，一些工作出色、却不总是分享成果的同事，如今开始定期撰写文章，告诉大家：“这是我们做的工作。这是它的运作方式。这是它的作用。It is ready to be produced under this brand name." So, they play, they listen, and they decide. They might be being produced at extreme speed, but the quality has not left the process. And this is the reason why Michael told me that this screams craft to me. And so, I was initially uncomfortable with that, but I went went back and kind of thought about my own journey in in writing and I I realized that I didn't disagree with him. And so, we published a recap post after the second or third version of blog posts was out and we had seen publication rates rise across the org and I had anecdotally, more importantly, seen colleagues that were doing excellent work but didn't always share that work were now regularly producing articles to say, "This is what we worked on. This is how it works. This is what it does."

于是，我知道它开始起作用了。And so, I knew that it was starting to work.

每句话都让我瑟缩。"Every sentence makes me flinch"

不过，我们在网上收到的早期评论中，有一条是有人说：“你们做这件事很酷，但现在我读网上的任何东西时都会心里一颤。我读的时候总会心里一颤。我会在脑子里盘问每一句话：‘这是 AI 写的吗？那条是 AI 写的吗？这句是人写的吗？那句呢？’”某种程度上，我起初理解这种抱怨，但它也让我感到困扰。再加上围绕流水线和手艺的讨论，我觉得自己得把对这个问题的想法理清楚、想明白。But we got one of the the first comments that we got online was from someone saying that this is cool that you did this, but now every single thing I read online, I flinch when I read it. I read it with a flinch. And I'm interrogating in my mind every sentence, "Was this AI? Was that one AI? Was this one human-written? Was that one?" And at a certain level, I understood this complaint initially, but it it also bothered me and and taken in conjunction with the conversation around the assembly line and craft, I decided that I kind of had to get my own thinking on this issue clear and straight.

火花、风箱与淬火Spark, bellows and quench

所以，当然，我做到这一点的方式就是写作。于是我决定回头想想：我怎么看待自己过去的写作方式？作为一个人去写作意味着什么？而现在，我可以借助 LLM 来写作，并以快 6 倍的速度、经过更多轮迭代，达到我想要的最终目标。嗯，你知道，我决定借用一个来自锻造领域的延伸隐喻：在这个例子里，我就是那颗火花，依然保有意识，依然与世间的人打交道，感受摩擦、痛苦、苦难、喜悦等等。于是，作为一个开发者，或者一个有品位的人，我会判断这件事是好的，还是不好；我喜欢它，还是不喜欢它；或者，实际上，这是一个重要而有趣、值得讲述和分享的故事。And so, of course the way that I do that is to write. And so I decided to look back and think about what do I think about the way I used to write and what it means to write as a person and now the fact that I can do it with an LLM and get to the the end goal that I want um you know, 6x faster with many more iterations. And I decided to borrow an extended metaphor from the blacksmithing world and say that in this case I am the spark who is still conscious, who's still dealing with people in the world experiencing friction and pain um and suffering and joy etc. And so I decide as a developer or a person with taste uh that this is something that's good or that I don't it's not good or I like it or I don't like it or actually this is an important and interesting story that is worth telling and sharing.

然后我同时也像风箱一样在推动它。即便到了流程的这个阶段，大语言模型或机器可能已经在替我处理那些真正繁琐的细枝末节，我仍然会观察进展，然后说：“这边这个可以；这一部分完全，怎么说呢，毫不相关，直接删掉。呃，这些都需要展开，但必须严格按照这种方式展开，而这个不对，对吧？”所以我一直在不断调整这项工作，让它越来越接近我想要的方向。And then I'm simultaneously the bellows. Now even if at this point in the process the LLM or the machinery might be doing the actual tedious um minutia for me I'm still watching what develops and saying this over here is is okay, this section is completely you know, um irrelevant just drop it. Uh all of these need to be developed but they need to be developed in this exact way and this is wrong, right? And so I'm continuously shaping the work closer and closer to where I want it to go.

最后，呃，你知道，总得做点什么，至少先把它发布到一个 URL 上。所以我也是那个淬火的东西。对不起，如果这里真有铁匠的话，我把这个延伸的比喻越说越离谱了。但我就是你把烧红的铁块丢进去的那个东西——你知道，丢进水里，它就把铁块淬硬、定型，让一切停下来，然后说：“发布吧，扎克·普罗瑟说了这些话，他为这些话、这些主张、这些链接、这些规格以及这些性能数据负责。”And then finally uh you know, something has to be done enough to at least initially publish it at a URL and so I am also the quench. I am the thing that you you know, drop into I'm so sorry if there's actual blacksmiths in this I'm as I torture this extended metaphor. But I am the thing that you drop your hot iron into the you know, into the water and it and it seals it and stops it and says publish, Zack Prosser said this and he stands behind all these words and these claims and these links and these specs and and this performance data.

所以，最终完成的作品仍然得值得署上我的名字。越是思考这件事，我越觉得自己现在有了一个框架，可以大致理解我们接下来该如何推进，并且即使速度越来越快，未来仍能产出高质量的成果。And so the finished work still has to earn my name and so the more that I thought about this the more that I felt like now I had a framework for kind of understanding how we're going to move forward and still produce quality in the future even if the velocity is increasing.

这是真的吗、有用吗，也美吗？Is it true, useful and beautiful?

而且，而且进一步说，我越是思考这件事，就越意识到：由于我一直大量产出并不断迭代，我觉得，如果最终用户看不出左边是我亲手在文档里逐字逐项写完再打印出来的，右边是我花了两个半小时或三个小时，和一个 LLM 来回迭代了 14 轮，然后说“不，不是这样，改一下这个词，再改一下那句话”之后弄出来的，这两者之间有什么区别的话……And and furthermore the more I thought about this the more I realized that because of my background in producing a lot all the time and iterating constantly I feel that if the end user can't tell the difference between on the left me writing every single element by hand in the document and then printing it, and on the right me spending two and a half or three hours going through 14 iterations with an LLM and then saying no, not that, change this word, change that sentence like that.

好吧，这已经很接近了。然后我自己在最后再手动编辑几个，再把它发布出去，对最终用户来说实际上没有任何区别。你知道，你可以说扎克·普罗斯尔做出来的那东西就是垃圾，我要再读一遍。没关系。呃，或者你也可以说，这还行，也许下周我会回来，再给那个人一次机会。Okay, that's pretty close. And then hand editing a few more at the end myself, and then publishing it, there's effectively no no difference for the end user. You know, you either say that that thing that Zach Prosser produced is garbage, I'm going to read them again. That's fine. Uh or you say like that's okay and maybe next week I'll come back and give that person another try.

所以我意识到，我真正关心的、以及我认为我们应该关心的是：这里真正的评判标准是，它是真的吗？有用吗？美吗？它能帮助其他人吗？因为如果我们制作的东西是要交给人来审核的，那这才是我们真正追求的。所以，你知道，我们在场的所有人，不管有没有意识到这一点，不管是否这样看待自己或这样理解自己，都有类似这样的东西——某种自己绝对是专家的成果或工作流程。And so I I realized that what I actually care about and what I think I would suggest we care about is that uh the real the real rubric here is is it true? Is it useful? Is it beautiful? And does it help anybody else? Because that's what we're actually going for if we're producing things that are for humans to review at all. And so uh you know, all of us in this room, whether we realize it or think of it or conceive of ourselves in that way or not, have something like this, some artifact or workflow that they are um absolutely an expert in.

它可能是一个内部流程，也可能是某种极其晦涩或复杂的东西。总的思路是，无论你在哪里工作、身处哪个领域或行业，或者想要实现什么，都要先把它做成一个工具，让它能够运转起来，直到你开始看到一些熟悉的、可以产出的东西。It could be an internal process, it could be um something extremely arcane or complex. And the the overall concept, regardless of where you work or the field and industry or what you're trying to do, is to create that into a tool initially, kind of get it working where you start to see something that you recognize and can produce.

然后你让其他人试试看，并问他们：“如果你试试这个，把你的东西放进去，你知道，你能达到自己想要实现的最终目标吗？你能更完整、更高效地完成自己的工作吗？”所以我认为，这是一种适用范围很广的模式，我们今后会越来越常见地看到它。And then you let other folks try it and say uh if you try this and put your stuff through it, you know, uh are you able to get to the end goal that you're trying to get to? Are you able to get to your work uh your work done more completely and more effectively? And so I think that this is a broadly applicable pattern that we're going to see increasingly more and more.

双人制造厂：睡前故事A factory for two: bedtime stories

嗯，你知道，我在这个故事里建的第一家工厂，本质上是为我的同事们建的。这样我们就能触达更多人，人们也会更多地发表自己所做的出色工作。当然，作为一名软件开发者，我在使用 LLM 时获得的体验，以及它带来的效率提升，让我开始思考：在这个全新的世界里，如果受众更小一些，是否也值得为他们建一家工厂？And uh you know, so the first factory that I built in the story essentially is for my colleagues. So more of where we can reach someone, people are publishing more about the excellent work that they're doing. But the experience, of course, with working with LLMs and the acceleration that I get from that as a software developer, then had me questioning uh in this new world, what if an audience that's even smaller is also worth building a factory for.

如果说，呃，两个人就足以成为打造某个特定工厂的受众呢？于是我又试了一遍同样的想法，呃，用 Opus 55 这款超高端模型，花了 4 个小时就把它完整实现了。但这一次，我的工厂是专门为两个人打造的。呃，正如我提到过的，我是两个幼儿的父亲，所以我经常负责给他们讲睡前故事。于是我做了这个应用：它会查看他们一天中的照片，大致判断我们都做了些什么，然后自动把这些内容编成故事，准备好在睡前讲给他们听，而且也会让他们成为故事里的角色。What if uh two people were enough of an audience to build a particular factory? And so I applied the same idea again and uh got this fully working with uh Opus 55 extra high end in 4 hours. But this time my factory was for specifically two people. So uh I do a I've as I mentioned I have I'm a father to two toddlers and so I do a ton of bedtime story duties and uh I built this app so that it looks at the photos of their day and kind of finds what we were doing and then automatically sort of suggest them into a story that can be ready for bedtime and that cast them in it as well.

于是，他们的一天就变成了一个故事。他们会再次看到我们一起学过的内容，或一起做过的事情，也能在故事里看到自己的影子。里面还有动画之类的东西，还会给他们讲故事。呃，这次体验相当奇妙，因为我可以很有把握地说，这是我整个职业生涯中最快的一次成功试玩：从零到能用，而且在 4 小时里一遍又一遍地重复。所以我接下来添加的第一项功能是实时语音控制。这样，他们在最后说“再来一次、再来一次、再来一次”时，故事就会重新播放。所以，这依然是同一种模式。这是我搭建的另一个完全可用的工厂。我把自己认为一则优秀睡前故事应有的要素，以及我对这方面的一些看法，都编码进去了；毕竟，我作为一名睡前故事实践者，干这行的时间够久了，也积累了一些自己的看法。And so their day becomes a story. Lessons or things that we did together they see again and can kind of see reflected in them. There's like animations and stuff and it'll kind of narrate to them. And uh this was a pretty trippy experience because I can say with confidence that this is the fastest successful playtest I've ever had in my entire career um from zero to working and again again again in 4 hours. So the first thing I added next was uh real-time voice control. So when they say again again again at the end it just plays it again. So again this is the same pattern though. This is another factory that I built that's fully working. It's codified with what I believe makes a good bedtime story what I have you know opinions about and have as a practitioner of bedtime stories for having served long enough to have opinions.

而生成出来的内容，正是他们当天的内容。现在，他们真的可以走到它面前说：“我想听一个关于美国队长的故事，还想听一个关于我和美国队长在动物园里的故事。”然后就有了，短短一分钟半，你就得到了完整的故事。他们读完故事，看到自己映照在其中。所以，你知道，我分享这些，是因为这是一个充满巨大潜力与进步，同时也伴随着焦虑、忧心忡忡、不确定、恐惧和怀疑的时刻。And what comes out is exactly their content in their day and now they can literally go up to it and say I want a story about Captain America and I want a story about me and Captain America at the zoo and and then there you go and in a minute and a half like you have that full story. They go through it and they see themselves reflected in it. And so you know I I share all this because it's a moment of like incredible potential and advancement and anxiety and hand-wringing and uncertainty and fear and doubt.

应对 AI 焦虑的解药An antidote to AI anxiety

正如你所知，作为一名视觉艺术家，我经历过这样的变化：从“哦，我会画画，而且我喜欢画画”，到“哦，我干吗还要再画画呢？”——写作也是如此，软件也是如此，然后又回到另一边。所以我只是想分享一下：如今，在某种程度上，这成了抵御那种恐惧、不确定和怀疑的良方，因为我知道自己喜欢创作这些东西，也喜欢帮助别人创作这些东西。看到那些工作出色的同事——他们可能从没觉得自己是创作者或作家——如今因为自己的作品以及他们发现的规律而获得认可，并能与世界分享这些成果，我会感到无比喜悦和满足。And I've experienced those things as you know as a visual artist going from oh I draw and I like to draw to oh why would I ever draw again um to the same thing for writing, same thing for software and then back to the other side. And so I just wanted to share that this is now the in some ways an antidote to that kind of fear and certainty doubt because I know that I like to produce these things, and I like to help other people produce those things, and I get immense joy and satisfaction out of seeing my colleagues who are doing excellent work but might not think of themselves as creators or writers now getting credit for and sharing their work with and the patterns that they've discovered with the world.

看到我的同事们越来越多地通过第一家工厂推出故事、技术深度解析和公告，真的让我感到无比欣慰。And so, seeing my colleagues put increasingly more and more stories and technical deep dives and announcements through the first factory is incredibly satisfying.

你知道，看着我的孩子们创作自己的故事，故事里会讲到那天我们做了什么、学到了什么，还有为什么要轻轻地动手、不能打妹妹之类的，真的很棒。不过话说回来，在我做过的所有试玩中，最成功的那些平均每个故事都会被要求再读三遍左右。你知道，大家最常给出的反馈就是：“再来一次，再来一次，再来一次。”所以现在，我也能享受他们创作出来的内容了；这两家工厂都是如此。You know, seeing my kids produce their own stories that that literally talk through what we did in that day and what we learned, and you know, why we need to have soft hands and not slap our sis you know, sister etc. Um But again, most successful play tests I've ever done uh the the average uh request for book repeat is like three per story, and it's you know, the primary feedback is again again again. Uh so, now I get to enjoy what they make, and that's true for for both these factories.

所以，这对我和同事一起合作的工厂来说是成立的，在家里也是如此。这只是因为我长期以来一直在做一件事、制作这一类作品，所以对什么能让它变得有趣、什么能让它变得出色有了自己的看法。现在，我让那些我在乎的人通过它来呈现他们自己的内容和故事，这就是我获得满足感的来源。我也会听取他们的反馈，比如他们说：“嘿，如果它还能做到某某事，那就更酷了。”然后你就会想：“好吧，你说得对。”So, it's true for the factory that I work with with my colleagues with and then also at home. So, it's just because that I've done this one thing and made this type of artifact long enough to have opinions about what makes it interesting what makes it good, and now I allow the people that I care about to bring their own content and their own stories through it, and then that is where I'm getting my contentment and getting feedback from them about saying like hey, it would be even cooler if it did XYZ, and you're like okay, you're right.

你要为谁建造工厂？Who will you build a factory for?

所以，我想把这个问题抛回给在座的各位：你们要为谁打造一座充满爱与恩典的工厂？有没有某个你关心的人，或者某个你在乎的团队？有没有什么事情是你特别熟稔于心的，或者同事、朋友总是对你说：“天哪，你在某某方面真是太厉害了”，又或者你对某件事怀有真正的热情？你能为它打造一座工厂吗？如果你是开发者，那就尽情发挥；如果不是，就找个智能体帮你实现。把你在实践和构建过程中学到的一切、所有你深信不疑的观点，都倾注到那座工厂里，然后把它交给一个平常不会制作这类东西的人，再看看他们能创造出什么。这就是为什么我希望自己已经说服了你：如果你在乎某个人，就应该为他们打造一座工厂。And so, the question that I would turn back to all of you in this room is who will you build a factory of loving grace for? So, who is somebody that you care about or a team that you care about? What is something that you specifically know by heart or are constantly told by colleagues or friends man, or you are so good at XYZ, or you have a real passion for XYZ. Can you Can you build a factory for it? If you're a developer, you know, go to town, and if if you're not, have an agent help you do it, and uh pour into that factory everything that you've learned uh from doing and from building, all of your strong uh strongly held opinions, and then hand it off to somebody else that doesn't normally produce that kind of stuff, and then see what they create, and uh that is why I hope I've convinced you that if you care about somebody, you should build them a factory.

非常感谢。Thank you very much.