How I'm Actually Using AI Right Now (Including Claude Duet) — 文稿

F10:00

Claude Duet 这周发布了，是个人代理领域的最新产品。今天我会带你看看我实际上是怎么用的，但当我深入研究时，发现我得先给你一个我整体上如何使用 AI 的概述。

Claude Duet is out this week, the latest in the personal agent space, and today I am going to walk you through how I'm actually using it, which when I dug in kind of required me to give you an overview of how I'm using AI overall.

那么，我们开始吧。

So let's dive in.

AI Daily Brief 是一个每日播客和视频，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，在我们开始之前，先快速宣布几件事。

All right, friends, quick announcements before we dive in.

F10:44

还有，再宣布一件事。

Also, one more announcement.

F11:01

所以在本期节目中，我想深入聊聊刚刚发布的 Claude Duet。

So for this episode, I wanted to go a little bit deeper on the just announced Claude Duet.

更广泛地说，我在准备这期节目时意识到，我有一段时间没有做一期关于我实际如何使用 AI 的节目了，包括我目前的技术栈是什么，我用哪些工具做什么，哪些用例带来了最大的价值。

And more broadly, I realized as I was preparing for this, I haven't done an episode for a while around how I'm actually using AI, what my current stack is, which tools I'm using for what purposes, what use cases are getting the most value.

结果发现，在分享我如何使用（或者说至少是尝试使用）这一代新的个人代理时，提供一些背景信息是必要的。

And it turns out that in sharing how I'm using this new generation of personal agents, or at least experimenting with them, some amount of that background is necessary.

有趣的是，我坚信我们必须将这些个人代理的形态视为仍在实验阶段。

What's interesting to me is that I believe pretty firmly that we have to treat the form factor of these personal agents as still experimental.

是的，我们确实看到了早期的吸引力和使用率，尤其是在 Muse 上。而且，自从 Claude 今年早些时候爆发以来，我们一直在尝试这种形态，这说明确实有一些认可的声音。

Yes, we are absolutely seeing early traction and uptake, especially with Muse, and certainly the fact that we've been playing around with this form factor since Claude exploded earlier this year suggests that there is some hear, hear.

不过我发现，先稍微透露一下，我还在摸索这些个人代理到底应该是我的参谋长，整理我做的所有事情，还是一种非常具体的主动替身型员工，能在我没有要求的情况下主动去想办法提供帮助。

What I found though, to give a bit of a preview is that I'm still trying to figure out how much these personal agents are supposed to be my chief of staff organizing everything I do versus a very specific proactive proxy me type of employee that goes out and figures out how to be helpful without me asking.

但我有点操之过急了。为了了解我使用这些工具的背景，我先大致介绍一下我主要的 AI 用例。

But I'm getting ahead of myself and to understand the background of how I'm using these tools, let me situate you more broadly in my major AI use cases.

我会尽量让这个内容对尽可能多的人有价值。

I'll try to make this as valuable to a wide cross-section of people as I can.

我的主要工作，贯穿 AI Daily Brief 和 Superintelligent，就是思考下一步要做什么或创造什么。

My main job, cutting across both the AI Daily Brief and Superintelligent, is thinking about what to do or what to create next.

在 AIDB 这边，这主要是在内容领域；而在 Superintelligent 那边，则更多是关于商业策略，关于试图了解 AI 用户存在哪些学习差距。

On the AIDB side, this is primarily in the content domain, whereas on the Superintelligent side, it's more about business strategy, about trying to understand what learning gaps there are for AI users.

而且因为我的工作很大一部分是策略，这涉及到很多外部化。

And because a big part of my job is strategy, that involves a lot of externalization.

我不是那种只是默默思考的人，我喜欢说出来。

I'm not a person who just quietly thinks to myself, I like talking it out.

事实上，我在 Notion 里有大量的笔记，我称之为“散步笔记”，这些是我在走路、开车或坐着时思考想法和下一步该做什么的记录。

In fact, I have reams and reams of notes in Notion that I call walk notes that are the times when I'm either walking or driving or sitting and thinking through ideas and what I'm going to do next.

这个用例一直是我的头号用例，至少在纯粹的时间投入上是如此。

This particular use case has always been my number one, at least in terms of sheer volume of time spent.

如果你浏览一下我与 AI 的所有对话和会话，大概有 60% 可能属于这个策略领域，但不一定是从消耗的 token 量来看。

If you look across every thread and conversation and session I've ever had with AI, probably 60% maybe are in this strategy realm, not necessarily in terms of volumes of token consumed.

当然，构建方面消耗的 token 更多，但就纯粹投入的时间而言，策略绝对是第一位的。

That of course goes to building, but just in terms of the sheer amount of time I've spent, it's absolutely tops.

这是一个模型差异影响巨大的领域。

This is one area where model differences have huge impacts.

我常说，当有新模型出现时，现在的问题不是问它们是否会是你现有工具的 1 对 1 替代品，而是要理解它们适合你技术栈的哪个位置。

I always say when there's a new model that at this point, it's not about asking if they're going to be a 1-to-1 replacement for what you're using, but understanding where they fit into your stack.

但我总是用每一个新发布的主要模型来测试这种策略性外部化，看它是否真的能 1 对 1 替代我现在使用的工具。

But I am always with every single new major model testing it against this sort of strategic externalization to see if it will in fact be a 1-to-1 replacement for what I'm using now.

说到什么样的模型对我来说是好的策略模型，有许多因素。

When it comes to what makes for a good model for me when it comes to strategy, there's a whole bunch of factors.

最重要的是在很多方面也是最难的一点，是它对反驳和奉承的态度。

The most important and hardest in a lot of ways is its approach to pushback and sycophancy.

在很长一段时间里，坦白说这些模型并不比在纸上写下东西好多少，因为它们永远不会反驳你。

For a long time, these models were frankly not all that much better than just writing things down on paper because they would never push you.

一切想法都是最好的，这其实没什么帮助，因为你想让你的想法变得真正好，并且只追求那些真正好的想法。

Everything was the best idea ever, and that's actually not that helpful if you're trying to make ideas really good and only pursue the ones that are really good.

在这种情况下，你不需要一个总是说每个想法都闪闪发光的应声虫。

In that circumstance, you don't want a yes person who's saying that every idea you have shines like gold.

你想要的是能进行批判性思考的人，而且重要的是，这种思考是有依据的，而不仅仅是基于被训练成反驳就是好的。

You want someone who can critically engage and who importantly is doing so based on something, not just because it's been trained that pushback is good.

这是一条非常非常难把握的界限。

This is a really, really hard line.

模型必须足够动态、足够有创造性，同时还要足够适应、足够自信。

Models have to be dynamic enough, creative enough, but also adaptable enough, but also confident enough.

是的，我用了所有这些人类学术语，尽管我并不认同将AI拟人化的观点，但因为在描述我这个使用场景中想找的东西时，这些是唯一真实有效的方式。

And yes, I'm using all these anthropological terms even though I don't ascribe to the anthropomorphic view of AI because they're the only real way to describe what I'm looking for when it comes to this use case.

不管怎样，Opus 5.5 是我很长时间以来在这个方面最喜欢使用的模型。

Anyway, Opus 5.5 is my favorite model that I've used in a very long time for this.

在那之前我用的是 Fable 5.1，还算可以；再往前一段时间我用的是 OpenAI 的模型，尽管今年大部分时间，我觉得 GPT 模型对于这类工作有点平淡、不够动态，这一点我们稍后会在 DOTS 中看到。

I was using Fable 5.1 before that, which was okay, and before that for a while had been using OpenAI models, although for most of this year, I found the GPT models to be a little bit flat and not dynamic for this sort of work, which as we'll see follows into DOTS.

我的下一个使用场景是研究。

My next use case is research.

你可以想象，对于《AI Daily Brief》和我即将告诉你的这个新项目——我们是怎么走到这一步的，研究也占据了我工作的一大部分。

As you might imagine with the AI Daily Brief, and with this new upcoming project that I'm about to tell you about how we got here, Research also represents a big chunk of what I do.

我还会经常为我妻子制作的真实犯罪播客《Love Murder》做研究。

We also often have research for my wife's true crime podcast, Love Murder, that I produce.

因为所有这些研究最终都会由我或我妻子公开表达，所以我们非常需要模型足够好、来源可靠、不胡说八道、能够理解来源、并且能够恰当地强调不同类型来源的价值。

And because all of this research is resulting in either me or my wife saying things publicly, we really need the models to be good, to be well-sourced, to not hallucinate stuff, to be able to understand the sourcing, to be able to put proper emphasis on different types of sources versus others.

对于这个使用场景，我实际上差不多同等地使用 Astra 和 Opus。

And for this use case, I actually use Astra and Opus about equally.

而且这种使用场景在特别重要的情况下，还能让它们互相协作带来好处。

And it's also the type of use case that can, especially in really important circumstances, benefit from them interacting with one another.

如果我在研究某个话题，我经常会让 Astra 和 Opus 都去处理，然后互相分享结果，让 Astra 审核 Opus，Opus 审核 Astra，增加一层额外的信心，然后再转化为内容，无论我最后用什么方式转化。

If I'm researching a topic, I will very frequently have both Astra and Opus go at it and then share the results across so that Astra is reviewing Opus and Opus is reviewing Astra to add that additional layer of confidence before it then turns into content, however it is that I happen to go turn it into content.

下一个我每天都会用到的场景是文案写作。

The next use case that is a daily one for me is copywriting.

我不使用 AI 来撰写任何播客，因为它们不是有脚本的播客。

I don't use AI to write any of my podcasts because they're not scripted podcasts.

稍微透露一下幕后情况：我们制作《AI Daily Brief》的方式是，每天晚上我会对当天 AI 领域发生的一切进行一个大调查。

For a little behind the scenes, the way that we produce the AI Daily Brief is that every evening I do a big survey of everything that has happened in AI that day.

很多时候我已经跟踪了一整天，但如果没有，我会花一两个小时深入挖掘新闻以及相关的讨论。

A lot of times I've been tracking it all day, but if I haven't been, I'm gonna take an hour or two to go deep on both the news but also the discourse.

与此同时，我在澳大利亚的研究员——顺便说一句，这是一种让我们能24小时工作的聪明做法——他在他的早晨也做同样的事情。

Meanwhile, my researcher in Australia, which is a hack that allows us to be working 24 hours a day, by the way, does the same during his morning.

然后大约美国东部时间晚上八九点，我们定下第二天节目要涵盖的具体内容。

And at about 8 or 9 PM Eastern time, We lay out exactly what the show the next day is going to cover.

我的研究员 Scott 会在一夜之间准备一份资料，包括我将要讨论的关键来源，尤其是大量的关键评论，比如社交媒体上的帖子，这些构成了节目的大量元叙事。

My researcher Scott then overnight prepares a dossier that includes key sources that I'm going to talk over, and especially a lot of the key commentary, things like posts from social media that form a lot of the meta-narrative of the show.

当我醒来，我会用那份资料来安排我想讨论的屏幕以及脑海中大致的顺序，然后就开始即兴发挥。

When I wake up, I use that dossier to lay out the screens that I wanna talk over in the rough sequence that's in my head, and then I just let it rip.

实际上，当我收到评论说我是“AI 在谈论 AI”时，我总是觉得好笑，因为在这个过程中真正用到的 AI 少得惊人，而且说实话，可能还有一些地方我们可以更高效，但我们就是这么做的。

I always think it's funny actually when I get comments that I'm AI talking about AI, 'Cause there's actually shockingly little AI used in this process, and honestly, probably some ways that we could be more efficient, but that's how we do it.

不过反过来，当一集节目完成后，文案写作是我每天都会使用 AI 的事情。

On the flip side though, when the episode is done, copywriting is something I use AI for every day.

节目描述显然是一个用 AI 的地方，社交媒体帖子也是，不过这个流程我稍后会讲到。

Episode descriptions are an obvious place for that, as well as social posts, although that's a process that I'll get into in just a moment.

标题则有一点来回商讨。

And titles are a bit of a back and forth.

我总会有一个自己带来的标题。

I always have a title that I'm coming in with.

我总会让 AI 有机会尝试说服我用不同的标题。

I always give the AI a chance to try to convince me of something different.

我得说大概50%的时候我会完全坚持原有标题，另外50%的时候，我和 AI 之间来回商讨后会产生一个不同的标题。

And I would say about 50% of the time, I stick with exactly what I had, with the other 50% of the time, some back and forth between me and the AI producing a different title.

在这方面，我实际上用的是 Astra。

For that, I actually use Astra.

我觉得这有点关乎记忆和上下文。

I think this one is a little bit about memory and context.

我使用 GPT 模型来做这个已经很长时间了，所以有很长一段记录了我喜欢什么和不喜欢什么。

I've been using GPT models for so long for this that there is a very long track record of what I do and don't like.

所以即使Opus或者Stable在文案写作上一样好甚至更好，花那么多时间调参我觉得不划算。

And so even if Opus or Stable were just as good or even better at copywriting, the amount of time to tune it just doesn't strike me as worth it.

我还觉得现在很多人觉得OpenAI的模型在文案写作的简洁性上更好。

I also think that the concision of copywriting is something that I've heard lots of people like OpenAI's models better for right now.

这当然也影响了文案写作的价值。

And that certainly plays into the value for copywriting as well.

跟文案紧密相关的是我使用图像生成的方式。

Closely related to the copywriting is the way I use image generation.

图像生成其实每天在我的工作中占很大一部分。

Image generation actually comes into my work a lot on a daily basis.

我经常用它来做内景图，就像我现在这样。

I will very frequently use it for inside shots as I'm doing right now.

你可以看到我背景里这些图，而且无论如何，我每天至少用AI生成节目的封面图。

You can see these images that I'm talking over, and no matter what, every day I'm creating the cover image at least for the show using AI as well.

目前图像生成基本上就是GPT的图像模型了。

At this point, image generation has pretty much just become the GPT image models.

这倒不一定是因为我觉得它们更好。

That's not necessarily because I am convinced they're better.

我还在续费Ideogram和Midjourney。

I still maintain subscriptions with Ideogram and Midjourney.

Ideogram我真的很喜欢用来迭代，因为它不像ChatGPT一次只生成一张，而是一次生成四张，还能调节它们的差异程度。

Ideogram I really like as a way to iterate, because as opposed to creating a single image at a time like you do with ChatGPT, Ideogram is creating 4 at a time and gives you toggles for how widely varied you want them to be.

而Midjourney就是个怪胎，有很奇特的艺术品味，在某些特定情况下可能好得多。

And Midjourney is just its own weird beast with a lot of strange taste in artistry that, depending on the particular use case, can sometimes just be way better.

尤其是当你不太确定想要什么图像，只希望它很酷、有趣、视觉上吸睛，想让模型自由发挥时，Midjourney就特别有价值。

Especially if you're not exactly sure what you want out of an image, you just want it to be cool or interesting or visually arresting, and you want to give the model some latitude, that's where Midjourney is really valuable.

对我来说，主要的图像生成就是那些封面，我在确定标题后马上生成，所以全部在一个线程里搞定最合理。

For my purposes, the main image generation is going to be those covers, and I'm producing them right after I've finished locking in the headline, so it makes sense all to just keep in that single thread.

另一个大的用例是数据分析，这实际上超出了我作为内容创作者的角色。

Another big use case, which is one that actually extends and expands outside of my role as a content creator, is data analysis.

今年那些延期报税的兄弟姐妹们可能刚经历过这种事。

My brothers and sisters in arms who filed their taxes on an extension this year probably just went through this experience.

就是倒进一大堆财务数据，让模型整理、提取支出等等。

Of dumping a whole bunch of financial data in and having it organize it, extract your expenses, et cetera.

几乎所有数据分析项目，我都在Codex里用Astra。

And for almost every sort of data analysis project, I'm using Astra inside of Codex.

对我来说，它提供最好的结果，而且有那种简洁的思路，我认为对这种用例特别有价值。

For me, it provides the best results and has that sort of concision of thought that I think is really valuable for this type of use case.

然后就是开发。

And then we come to building.

这当然是个大类。

And this of course is a huge category.

和你们很多人一样，今年我用过很多不同的工具、框架、模型和技术栈来开发。

I, like many of you, have used lots and lots of different tools and harnesses and models and stacks for building this year.

我们用过一阵OpenCLAW，当然还有Codex和Claude Code的应用程序和命令行版本，还有Cursor之类的第三方工具。

We did OpenCLAW for a while, and of course Codex and Claude Code in both their application as well as the CLI versions, third-party tools like Cursor.

但对我来说，最稳定的选择是Claude Code，默认模型是Opus 55，难度设置通常在高或极高。

But for me, where things have landed pretty consistently is Claude Code with Opus 55 being the default model and the effort settings usually on high or extra.

我经常也在Codex里用Astra进行开发，主要是为了原生调用图像生成模型。

Now I will frequently build inside Codex using Astra as well, specifically to get native access to the image generation models.

所以很多节目的配套体验，如果特别视觉化，就会在Astra里构建。

So a lot of times the companion experiences that go with the show, if they're particularly visual, will be built in Astra.

但最终我大部分组织、叙事架构和开发协调都是在Claude Code里完成的。

But ultimately I do most of my organizing, narrative architecture, and orchestrating all the building in Claude Code.

另外，我也给Claude Code通过API接入GPT图像模型，不过我发现在Codex里用图像模型和通过Claude Code API调用有些不同。

I also, I should note, give Claude Code access to GPT image models via the API, although I have found a difference using the image models inside Codex as opposed to via the API through Claude Code.

至于你们看到的具体内容，AI Daily Brief网站全部由Claude构建和维护。

In terms of specific assets that you guys see, all of the AI Daily Brief site was built and is maintained by Claude.

实际上，我认为这部分原因说明了今年一次关键模型更新的故事。

In fact, part of the reason for this actually I think tells the story of one of the key model updates of this year.

当我第一次获得 Fable 的使用权限时，它让我感觉跟其他模型不同的地方在于：虽然有一段时间，开始构建东西已经变得很容易了，但 Fable 像是把这种轻松也带到了把事情完成上。

When I first got access to Fable, what made it feel different from other models was that while it had been easy for a while to start building things, Fable, it felt like, brought that ease to just getting them done.

不像以前那样，项目会卡在80%或90%完成的状态，启动能量已经足够低，但完成能量仍然太高。Fable 就是把完成能量大幅降下来，让它和启动能量匹配。

As opposed to having projects hang at 80 or 90% complete with the activation energy sufficiently low but the completion energy still too high, Fable just brought that completion energy way down and matched the activation energy.

具体来说，关于 AI Daily Brief 的网站，其实我已经知道好几个月了，我得把我那个旧的、可爱又复古的90年代风格网站换掉。那个网站对我来说有趣、复古、也很有感觉，但完全没什么实际功能。

Now, specifically with the AI Daily Brief website, I had known for a couple of months that I needed to switch off the old cutesy 1990s aesthetic website that I had that was fun and retro and evocative for me, but totally nonfunctional.

而我有一个明确的任务，我知道自己想做的是什么。

And I had a specific mandate that I knew I wanted to achieve.

AI Daily Brief 是一个信息密度很高的节目，我觉得，而且大家似乎也这么认为，它的重要价值之一就是你每分钟都能获取到尽可能多的信息。

The AI Daily Brief is a very information-dense show, which I think, and it seems, is a big part of the value proposition that you get as much information per minute as you do.

但这也，说到激活能量，就带来了相当高的进入门槛。

But that also, speaking of activation energy, creates a pretty high barrier to entry.

我听到很多人说，他们非常想要的一个重要东西，就是能有更简单的方式把节目的特定部分分享给同行和同事。

I had heard from lots and lots of folks that a very important thing that they wanted was an easier way to share specific parts of the show with their peers and colleagues.

所以我知道，这个网站不能只是个网站，它实际上要成为一条生产流水线，可以把节目的原始内容或文字稿转化成一种非常不同的网页内容。

So I knew that the website needed to not just be a website, but actually needed to be a production pipeline that could take the raw content or transcript of the episode and turn it into a very different type of web content.

这就是我和 Fable 一起设计和构建的东西。

That's what I designed and built with Fable.

而且我实际上在获得权限的第一个下午就做到了，整个初稿就在那个下午完成。这其实是件好事，因为第二天 Fable 就下线了，原因是和 White House 在出口管制问题上起了争执。

And I actually did it on the first afternoon I got access, completing the entire first draft in that afternoon, which was a good thing because the next day was when Fable got taken offline because of the export control dustup with the White House.

构建那条流水线的第一阶段，是构建一个系统，让我可以上传文字稿，然后它从文字稿中提取相关信息，整理成这些可分享的素材，再放到网上。

The first stage of building that pipeline was to build a system by which I can upload a transcript and it can extract the relevant information from that transcript and organize it into these shareable assets that then go up on the web.

使用 Fable 和 Claude Design，我们能够为这个系统构建一种不使用任何图像生成的美学风格，这当然是有局限的。

Using Fable and Claude Design, we were able to build an aesthetic for this that doesn't use any image generation, which of course has limits.

但对我们现在要做的事情来说，它是有效的。

But it works for what we're trying to do here.

它在视觉上很统一，清晰易读，而且很多品牌标识都是用文字和颜色元素来做的。

It's visually consistent, it's clear, it's readable, and it uses text and color-based elements for a lot of the brand identity.

下一步，也是用 Claude 做的，是把这条流水线扩展到社交媒体。

The next step, which was also with Claude, was expanding that pipeline to social.

说实话，我从来没有给社交媒体它应得的时间。

Truth be told, I have never given social the time it deserves.

而且说白了，要在社交媒体上成功，就要真的坐在那里跟人互动，在上面花时间。

And to be clear, the way to be successful on social is to actually sit there and engage with people and spend time on it.

但我至少希望有一些内容能发上去。

But I at least wanted some amount of content going up.

因为那是在 Opus 5.5 之前，我又用了 Fable，加了一条次级流水线：节目内容提取完以后，那些卡片会经过一个二次处理过程，生成一组推文和一篇 LinkedIn 帖子。

Using Fable again, 'cause this was pre-Opus 5.5, I added a secondary pipeline where once the episode is finished extracting, those cards then go through a secondary process generating a set of tweets and a LinkedIn post.

然后这些内容会通过第三方服务 Typefully 来安排发布。

Those are then scheduled with a third-party service Typefully.

我确实尝试过折腾 API 来直接连接这些服务，但像 Typefully 这样的第三方已经把那些工作都做完了，直接接入那边要容易得多。

I did explore messing around with the APIs to connect directly to the services, but a third party like Typefully has already done all that work and it was way easier to just plug in there.

最近的一步是视频，而在这里，原理和社交媒体一样。

The most recent step has been video, and here it's got the same principle as social.

更好的做法是给这些平台创作原生视频。但在没有条件的情况下，我希望每集至少有一个片段能放到 Spotify 上。

It's better to create net-native video for the channels. But in the absence of that, I wanted at least one clip per episode to go with Spotify.

最近，尤其是 Opus 5.5 之后，Claude 里的模型在视频剪辑方面变得超级擅长。

Recently, and especially with Opus 5.5, the models in Claude have gotten enormously good at video editing.

以至于我甚至觉得，即使你现在觉得自己没有理由用视频，你可能也还是想去试试。

So much so that I actually think that even if you don't think you have a reason to be using video right now, you may still want to go and experiment.

但不管怎样，我让 Claude Code 帮我建了一条视频制作流水线，让它和网站的美学风格保持一致。

But in any case, I asked Claude Code to build me a video production pipeline that matches the aesthetic of the website.

所以它每天做的事情是，我把文字稿喂进去，它看一遍，然后自己判断选出最好、最吸引人、最自成一体的一段60到90秒内容。

And so what it does each day is I feed it the transcript, it reviews and makes a judgment call around the best, most compelling, most self-contained 60 to 90 seconds.

然后它提取那段片段，围绕它构建其他视觉素材，然后把整包东西打包成可下载的文件，我就可以上传到任何地方去。

It then extracts that clip, builds other visual assets around it, and packages the whole thing up for download that I can then upload wherever it goes.

现在，剧透警告——其他听众明天就会听到这件事。当我开始做一个叫 How We Got Here 的新节目时，这套流程已经完全到位了。

Now, spoiler alert for something that the rest of the audience will hear about tomorrow, this process was all in place when I started working on a new show called How We Got Here.

How We Got Here 这个节目的理念，其实就在名字里了。

The idea of How We Got Here is kind of right there in the name.

这是一个探讨导致当今最大故事、现象和事件的具体社会、文化、技术和经济因素的节目。

It's a show that looks at the specific social, cultural, technological, and economic factors that led to today's biggest stories, phenomena, and events.

核心理念是，我们现在经历的一切都源于过去做出的一系列特定决定。要重塑或重新想象这些现象，我们需要理解我们是如何走到今天的。

The idea is that everything that we experience now comes from some specific set of decisions that were made in the past, and in order to remake or reimagine those phenomena, we need to understand how we got here.

这个想法的产生，是因为在主持这个节目时多次意识到，我没有足够空间深入探讨某个特定议题。所以这个新节目时长45分钟到一小时，每周一期。给你一点概念：第一集是关于美国是如何不再热爱科技产业的。

It came out of a lot of times recognizing on this show that I just didn't have the space to go as deep as I wanted to into a particular issue, and so it's 45 minutes to an hour, it'll be once a week, and to give you a little bit of a flavor, the first episode is about how America fell out of love with the tech industry.

第二集是关于为什么物质商品变便宜了，而生活中所有重要的事物却变得更贵。

The second is about how it was that stuff got cheap while all the important things in life got more expensive.

第三集是关于预测市场，以及我们是如何开始对一切进行押注的。

And the third is about prediction markets and how we started betting on everything.

第一集将于10月26日星期一发布，但其实我已经筹备了一段时间。幸运的是，我已经有了完善的流程。

The first episode comes out on Monday, October 26th, but I've been working on this for a while now, and luckily I had all these processes in place.

Claude是我迭代想法的地方，无论是从战略和分发的角度，还是内容创意本身。

Claude is where I iterate on the ideas, both from a strategic and distribution standpoint, as well as the content ideas.

在此基础上，我会同时使用Claude和Atlas来创建丰富的研究档案。

From there, I'm going to use both Claude and Atlas to create rich research dossiers.

然后我会进行一轮反馈，让Claude根据我想要阐述的论点列出关键要点。

I then do a round of feedback, have Claude lay out the key beats based on the arguments I'm trying to make.

我去找视觉素材，像在AI Daily Brief中那样安排它们，然后对着它们讲解。

I go source visuals, lay them out just like I do for the AI Daily Brief, and then talk over them.

这次会持续较长时间，最终形成40分钟到一小时的节目。

This time for a long time, resulting in a 40-minute to hour-long show.

但这里我们真正开始拓展，甚至推进了在AI Daily Brief中的流程。

But here's where we really started to expand and even push on the process from AI Daily Brief.

录制结束后，我会提取自己的原始转录文本，连同最初的研究材料一起交给Opus 4.5。

After I record, I rip out the raw transcript of myself and hand that plus the original research back to Opus 4.5.

我使用的是Opus 4.5。

I'm using Opus 4.5.

让它完成配套文章的初稿。

To have it do the first draft of a companion essay.

配套文章的目标是提供一个空间，能够更丰富地呈现我在节目中提出的论点，并以适合阅读的格式呈现，方便读者获取更多链接和节目背后的来源。

The goal of the companion essay is to be a place that makes the same argument I'm making on the show, but with a lot more visual richness, and that is presented in a format for people who like to read, with the easy ability to get more links and the sources behind the show.

但这要处理一小时的素材，对应5000到6000字的文章。

But we're talking about an hour of material, 5,000 to 6,000 words of essay.

然后，我把文章放入结合了Atlas的Codex，利用GPT Image来创造整体的美感和视觉风格。

So from there, I take the essay, drop it into Codex with Atlas, and leverage GPT Image to create a whole aesthetic and look and feel.

顺便提一下，我会对那篇文章进行彻底且耗神费力的编辑，在初稿基础上重写大约一半内容。

For those wondering, by the way, I then do an exhaustive, an exhausting edit of that essay where based on the first draft, I rewrite about half of it.

但此时我们还没有结束与Claude Code的合作。

But we're still not done with Claude Code at that point.

因为如我所说，最新一代的模型在视频编辑方面有了重大飞跃。

Because like I said, this latest round of models have made a major jump in video editing.

现在我有一个视频编辑团队，但我们的做法略有不同：他们先做第一轮剪辑，充分利用我们多年来在AIDB中建立的流程。

Now I have a team of video editors, but we're doing things a little bit differently where they do the first pass, taking advantage of a lot of the processes that we built over the years with AIDB.

然后我们引入AI来添加动画，并直接接入剪辑管线。

And then we integrate AI to add animations and to plug it directly into the clip pipeline.

KPMG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.

F119:10

网址是B-L-I-T-Z-Y点com。

That's B-L-I-T-Z-Y dot com.

好了，以上就是我日常使用AI的相关背景。

Okay, so this is all the relevant background on how I use AI on a daily basis.

显然，这主要集中在内容创作和围绕内容构建基础设施上。

It's obviously super closely focused on content creation and building the infrastructure around content.

你可能会注意到，其他人在AI中获得大量价值的很多方面在这里并没有提到。

And you'll probably notice that a lot of the things that other people get lots of value out of AI with are not here.

例如，我没有提到收件箱监控、对某些邮件的自动回复、Slack监控、通用更新等主动型工作。

For example, I didn't mention inbox monitoring, automated responses to certain types of emails, Slack monitoring, general updates, all that sort of proactive stuff.

而且我还没有花时间真正去组织这类AI工作，因为到目前为止，对我个人而言，不值得费力去做。

And I haven't taken the time to really organize that sort of AI work because up until now, for me personally, the juice wasn't worth the squeeze.

我用 OpenClaw 试过这个。

I did experiment with this with OpenClaw.

我让独立的 Claw 分别负责我工作里的不同部分，用心跳和定时任务来监控，并在特定的时间节点做特定的事。

I had individual Claws managing specific pieces of what I did, using the heartbeats and cron job setup to monitor and do specific things at specific time intervals.

我还设了一个‘参谋长’智能体，负责协调所有这些。

I also had a chief of staff agent that was meant to coordinate across all of those.

当时，我在 AIDB 和 Superintelligent 那边有一个持续的研究任务，是在监控 AI 应用方面的研究和调查。

And at the time, there was a persistent research job that I was doing as part of AIDB and Superintelligent that was monitoring studies and surveys in AI adoption.

所以，这就是我对主动性做的两个实验。

So those were my 2 experiments with proactivity.

一个是主动且始终在线的研究智能体，另一个是参谋长风格的监控智能体。

The proactive always-on research agent and the chief of staff style monitoring agent.

后来我不再需要那个研究智能体了，因为手头项目的方向变了。

Now eventually I stopped having need for the research agent because that just wasn't a project that I was working on in the same way.

至于那个参谋长，坦白说，它带来的价值不值得我花时间去维护和打理。

And when it came to the chief of staff, it candidly just wasn't adding enough value to deal with the maintenance and upkeep.

不过得说清楚，这很大程度上可能跟我本人有关。

Now to be clear, that might have a lot to do with me.

我对控制和管理自己的日程非常强势。

I am incredibly assertive about limiting and managing my calendar.

我接的电话 90% 都不是预约的。

90% of the calls I do are not scheduled.

想让我真正预约一个电话，那是极其困难的事，这点但凡尝试通过电话跟我谈 AIDB 广告投放的人应该都深有体会。

And it is extremely hard to get me to actually schedule a call, as anyone who's ever tried to discuss an ad buy for AIDB on the phone will have found out.

我不知道是不是因为我属于网络时代‘老古董’，但处理邮件时，我通常就是收到重要的就加星标，然后每隔几天清一次收件箱。这个方法我用了很久，一直很管用。

And I don't know if it's just being an internet boomer, but when it comes to email, I just star important things as they come in and clear out the inbox every couple of days, and that's worked for me for forever.

这倒不是说主动型智能体没有用。

Which is not to say that proactive agents are not useful.

而是在我们当时能接触到的版本里，它们给我个人带来的价值还不足以让我投入那些搭建成本。

It's that in the version that we had access to, they did not add a sufficient amount of value to me personally to be worth the setup cost.

这就是为什么你从来没听我提过 Hermes 智能体，虽然我觉得它是个很棒的产品，但就是跟我的工作方式和内容不太匹配。

It's why, for example, you haven't heard me talk about the Hermes agent, even though I think it's an excellent product, because it just hasn't fit specifically with how I work and what I work on.

这就把我们带到了个人智能体的新阶段。

Which brings us to this new phase of personal agents.

对我来说最有意思的问题是：它们能否把搭建和维护的门槛降得足够低，让它们能提供的主动性真正变得值得？

The interesting question for me has been, will they lower the cost of setup and maintenance sufficiently that the type of proactivity that they can offer actually feels worth it?

我自己呢，至少目前还属于那类认为——当然将来也可能被自己打脸——我基本上不太可能把这些智能体用在个人事务上的人。

Now, I personally am in the category of people who, at least for now, believe, and of course I could be eating my words in the future, that I was very unlikely to use these sort of agents for personal uses.

你可能还听我吐槽过这些公司宣传的那些用例，比如订机票、自动化购物、订餐厅等等。

You might have even heard me denigrate all of the use cases that these companies pitch, like flight booking and agentic shopping and booking restaurants and things like that.

再说一次，我不是看不到它们对某些人的价值，只是它们不适合我。

Again, it's not that I don't see how they could be valuable for some people, it's just that they're not for me.

就拿订机票来说，我几乎总是订我有里程的那家航空公司，除非实在没办法。

To take just one example, when I'm booking a flight, I'm pretty much always booking the airline where I have my miles unless I absolutely can't for some reason.

那种情况下，通常也会换另一家也有我里程的航空公司，飞那些航线。

And in that case, it's usually one other airline that does those other routes where I also have miles.

这意味着我基本只在一家航空公司的订票系统里操作，而向一个智能体解释各种变量和意外情况所花的时间，跟我直接看那个网站界面也差不多了。

Meaning that I'm working within the ecosystem of a single airline's booking system, and it would take absolutely as much time to explain to an agent the variables and contingencies as it does to just look at their specific web interface.

所以回到个人智能体这个话题，我始终会偏向专业用途那一块。

So coming back to personal agents, I was always going to be on the professional use case side of those personal agents.

那么问题就变成了：对我而言，个人智能体的价值，是不是指那些全新的东西，比如我还没搭建起来的这类主动式工作？

So then the question becomes, is the value of a personal agent for me net new things like this proactive work of the type that I haven't set up yet.

或者是一种能取代我与 AI 日常交互的协调机制？

Or is it some type of coordination that replaces my normal interactions with AI?

那我们就更直截了当地看看这两种可能性。

So let's look at these two possibilities a little more directly.

所谓‘全新的东西’，我指的是那种主动功能，比如监控我的邮件，当有事情需要处理时给我发通知，然后草拟回复让我批准。

By net new, I mean that proactive stuff like watching my email, sending me notifications about something that needs to be done, and drafting responses that I can approve.

再说一遍，目前我没有让任何智能体在做这些事。

Again, that's not a thing that I have agents doing right now.

说到更好的协调，我指的是有点像 Chief of Staff 这个角色，但我觉得在某些方面，它实际上更接近我们过去几个月在这里讨论过的 monothread 范式。

By better coordination, I mean a bit like this chief of staff role, but I think in some ways it's actually closer to the monothread paradigm that we've discussed here over the past couple of months.

Monothread 范式就是说，不是有一大堆不同的聊天，分散在很多不同的项目里，每个聊天只有那个特定聊天或项目的上下文；而是有一个单一线程，里面有你所有的上下文，需要做什么的时候它就把需要的东西拉出来，还能切换来切换去，处理不同的事情，还能按需启动子代理去做不同的事情。

The monothread paradigm is the idea that instead of a slew of different chats spread across a ton of different projects that each only have the context of that particular chat or that particular project, you instead have a single thread that has all of your context and pulls up what it needs to do when it needs to do it and can shift around and behave and work on different things and spin up subagents to do different things as they are required.

把东西组织到单独的聊天和单独的项目里，确实对整理自己的思路很有用，就像你在电脑上用文件夹一样。

Organizing things into individual chats and individual projects can be really useful for organizing one's own brain in the same way you use folders on a computer.

Monothread 范式的好处在于，对用户来说，你不需要承担做那种组织的认知负担。

The benefit of the monothread paradigm is that for the user, you don't have the cognitive load of doing that organization.

你就直接顺着意识流走就行了。

You just get to go stream of consciousness.

这种范式之所以能实现，是因为后台在压缩和上下文窗口管理方面取得了进展。

This has only been possible as a paradigm with advances in compression and context window management going on behind the scenes.

换句话说，以前到某个时候，你的 AI 会因为上下文窗口满了而变得非常疲惫。

In other words, it used to be that at some point your AI would get very tired because its context window was full.

然后你就只能换一个新聊天。

And you just had to move to a new chat.

事实上，我们在 2026 年做的早期教育项目里，有很多课程都是关于怎么最好地写交接文档的，但各家实验室在后台压缩上下文和向前传递方面已经做得越来越好，所以你其实不用离开当前这个单一的聊天。

In fact, a bunch of the lessons in the early education programs we did in 2026 were about the best ways to do handoff documents, but the labs have all gotten much better on the backend about compressing the context and carrying it forward so that you don't actually have to leave the single chat that you're in.

说实话，这种 monothread 范式比那种结构化的层级组织更贴合我的工作方式和我大脑的组织方式。

This monothread paradigm frankly fits my way of working and my brain zone organization a lot better than structured hierarchical organization.

我已经在推动 Claude Code 和 Codex 往这个方向发展，让事情不要分得那么细，而是围绕一个主导性的单一线程来工作。

I've already been pushing Claude Code and Codex in this direction, having things much less divided and working off a single dominant thread.

所以我对这些个人代理的问题是，它们会更多地采用这种方式吗？

So my question for these personal agents would, will it be more of that?

接下来我们来看看不同的工具。

So then we come to the different tools.

有一类优先级比较低的工具，是像 Instinct 和 Town 这样的第三方新工具。

One category that was a lower priority for me were third-party new tools like Instinct and Town.

虽然人们对这些工具赞不绝口，但它们对我来说一直都是比较低的优先级，因为它们擅长的东西和我想做的事情不太匹配。

Even though people rave about these tools, they were always in that lower priority for me because of the mismatch in terms of what they were good at and what I wanted to do.

而且从根本上说，我也不愿意把所有的专业和工作上下文，从我已经在做这些工作的地方转移过来。

And fundamentally, my unwillingness to move all of my professional and work context over from the places I do that work already.

就像你听到的，就是 ChatGPT 和 Claude。

Which, as you've heard, is ChatGPT and Claude.

然后还有 GrokBot 和 Muse。

Then we have GrokBot and Muse.

Muse 同样，我对其兴趣稍低一些，因为它偏向个人事务，不过很明显，那不是 Mark Zuckerberg 和 Alex Wang 野心的终点。

Muse again, a little bit less interesting to me because of its bias towards personal stuff, although it's very clear that that is not where Mark Zuckerberg and Alex Wang's ambition end.

对于 GrokBot，我确实订阅了所有 Ultra 套餐，但我真的不想非得搬出 OpenAI 和 Anthropic 的生态系统，因为维护这两个已经够我忙的了。

And with GrokBot, I do have all of the Ultra subscriptions, but I would really prefer not to have to move out of the OpenAI and Anthropic ecosystems because it's already enough to maintain those two.

我觉得 GrokBot 很有价值，是因为它和 X 的整合，从内容生产的角度来看真的非常有价值。

GrokBot I find valuable because of its integration with X, which is really valuable from a content production standpoint.

基本上，我现在对 GrokBot 的态度是保持恰到好处的参与度，这样万一将来有足够的理由去切换，我也不用从零开始。

And basically my approach right now with GrokBot is to stay just enough engaged so that if any point there were compelling reasons to switch, I wouldn't be starting from zero.

说到这里，我应该提一下 Google 和 Microsoft。

I should mention Google and Microsoft at this point.

Google，很抱歉，目前我还是觉得投入大量精力不太值得。

Google, I still at the moment, I'm sorry to say, I don't think it makes sense to invest a lot in.

这完全可能会改变。

That could absolutely change.

事实上，我乐观地认为这会改变，因为他们会重新振作起来。

In fact, I am optimistic that it will change as they get back up on the horse.

但就目前而言，他们在这个领域落后，对我来说反而是少了一件需要投入的事情。

But for now, the fact that they are behind in this area is one less thing for me to invest in.

对于 Microsoft，我会在专业层面密切关注他们的动向，因为播客和 Superintelligence 的用户主要都在企业领域；不过由于我完全是单打独斗，我总会偏向那些更灵活、迭代更快、不那么偏重企业级的版本。

With Microsoft, I keep close professional track of what they're doing because of both the podcast and Superintelligence users, which are largely in the enterprise, but being totally solo, I'm always going to bias towards the much more nimble, fast-moving versions that aren't heavily enterprise-focused.

总而言之，关于 Microsoft，我现在并不是要对他们的工具集做价值判断。

All of which is to say that when it comes to Microsoft, I'm specifically not making any value judgments about their toolset right now.

只是那不是我参与的生态系统。

It's just not an ecosystem that I'm playing in.

那么剩下的就是 Dots 和现在的 Duet。

So that leaves us with Dots and now Duet.

到目前为止，我使用我的 Dot 的方式和感受，很大程度上反映了我更广泛地使用 ChatGPT 的方式。

So far, how I use my dot and my feelings about it are pretty reflective of the way that I use ChatGPT more broadly.

对我来说，它基本上就是 ChatGPT 中我做重要专业工作时的一种新版本的单线程组织方式。

It's basically right now for me, a new version of the monothread organization for any of what I would consider important professional work that I do in ChatGPT.

换句话说，如果我在做重要的研究，或者对我的播客统计数据做数据分析，我现在都是通过 Quasar 来管理的，他既是《Dungeon Crawler Carl》中的 Nullian 律师，也是我的 Dot。

In other words, if I'm doing important research or doing data analysis on my podcast statistics, that I am now managing through Quasar, who is both the Nullian lawyer of Dungeon Crawler Carl and my Dot.

另一方面，对于简单快速的事情，比如以前我会用谷歌搜索的随机问题，甚至是日常播客集数的文案工作，这些都在和 Quasar 不同的空间里进行，和以前一样。

On the other hand, for simple fast things like random queries that I would've Googled before, or even the copywriting for the daily podcast episodes, that's happening in the same space away from Quasar as it always has.

我得说，即使是那些专业相关的工作，比如对过去播客表现做一堆数据分析，我也不能完全确定在 Codex 里做是不是会更好。

I will say that even with that professionally relevant work, like doing a bunch of data analysis on past podcast performance, I'm not 100% sure that it wouldn't have been better served being done in Codex.

至于像那样的策略性工作，我当然没有感觉到更多用我的 Dot 来做的动力。事实上，我发现——而且我看到其他很多人也反映这一点——目前 Dot 的性格非常平淡，几乎阻碍了那种策略性的互动。

And when it comes to other things like that strategy work, I'm certainly not finding any more compulsion to do it with my Dot. In fact, I have found, and I've seen a number of other people reflect this as well, that the Dot's personality at this point is so flat that it almost stonewalls that sort of strategic engagement.

我有时会给 Quasar 倾注一大堆背景信息，感觉就像要费力才能让它参与进来。

I will sometimes dump a load of context to Quasar, and it almost feels like pulling teeth to get it to engage.

前几天我有一个很有启发性的经历，我一整天一边徒步，一边和 Claude Opus 3.5 进行策略规划和策划，然后之后把整个对话分享给了 Quasar，这样它就能拥有最新的信息，而不需要我再分享一遍。

I had a telling experience the other day where I spent all day while walking and hiking strategizing and planning with Claude Opus 3.5, and then shared the whole conversation after with Quasar so that it had the up-to-date information without me having to share it again.

但它没有接起那场对话中的任何一个话题——那场对话大概有六个小时——我觉得它的回复基本上就是“很好”。

Instead of picking up on any of the threads from that conversation, which are again probably six hours of talking, I think its response was literally great.

这条信息已经保存以备将来使用。

This information has been saved for the future.

我发现我的 Dot 并不是特别主动，坦率地说，没过多久我基本上就不再觉得有理由与它互动了。

My dot I have found not to be particularly proactive, and frankly, it took very little time before I basically just stopped really seeing a reason to engage with it.

到目前为止，如果我在 OpenAI 里，我要么在做那些基本的快速的事情，要么在 Codex 里深度使用。

So far, if I'm in OpenAI, I'm either doing that basic fast stuff or I'm deep in Codex.

所以总结一下。

So summing up.

我对 Dots 的初步体验是——当然这完全可能改变，也不让我对未来悲观——但我的初步体验是，作为一个功能，它并没有真正增加什么，当涉及到 ChatGPT 成为我被动做事情的地方时。

My initial experience with Dots, and of course this is completely subject to change and does not make me pessimistic for the future, but my initial experience is that as a feature, it doesn't really add anything when it comes to ChatGPT being the place for me to go reactively do things.

它在主动工作方面很弱，但它作为背景信息的主要持有者似乎很有价值。

It's very weak on proactive work, but it does seem like it could be valuable as a master holder of context.

换句话说，我可以把所有相关的背景信息都倾注给 Quasar，让它同步并处理事情，而不是有很多个聊天，之后还得重复那些背景信息。

In other words, I can just dump all the relevant context to Quasar and have that sync and do things rather than having a bunch of chats where I have to repeat that context later.

然后我们来到 Duet。

Then we come to Duet.

在主要的个人代理中，Duet 是最不关心个性和性格的。

Duet is, of the major personal agents, the one that's least concerned with a personality and character.

它没有像 Muse 那样可爱的模糊 logo，也没有像 Dot 那样你可以选择的名字。

It doesn't have a cute fuzzy logo like Muse, and it doesn't have a name you choose like Dot.

它非常明显，遵循 Anthropic 的大体模式，专注于工作，这对我来说似乎很适合。

It is very clearly, following the larger pattern of Anthropic, focused on work, which seems like it could be a good fit for me.

当我让 Duet 启动并运行起来时，它做的第一件事就是让我连接 Slack、Gmail、Drive 等。

When I got Duet up and running, the first thing it asked me to do was to connect Slack, Gmail, Drive, etc.

马上。

Right away.

在我做任何其他事情之前，它就给了我一堆主动项目的选项。

And before I had done anything else, it gave me a stack of options for proactive projects.

事实上，Duet 非常偏向主动，我发现它可能高估了那类工作的价值，因为它可以主动去做。

In fact, Duet is so biased towards proactivity that I found that it maybe overestimates how valuable that set of work is because it can be proactive about it.

我举个例子。

I'll give you an example.

它基于对我的收件箱的了解想要帮忙的主动项目之一，就是管理播客赞助商库存，特别是确保我们不会把同一个广告时间段承诺给多个赞助商。

One of the proactive projects that it wanted to help with based on being in my inbox was managing podcast sponsor inventory, specifically making sure that we didn't commit the same ad slot to multiple sponsors.

它之所以把这个当作问题，是因为在两封不同的邮件里，我给了两个不同的赞助商同一个可用日期，而 Duet 当时还不知道其实我那天有一套时间段，所以这不一定是个问题。

This it picked up on as a problem because in 2 separate emails, I had given 2 separate sponsors the same date as available, and Duet did not yet know that I actually have a set of slots for those days, so that wasn't necessarily a problem.

它基本上对这件事激动了一下，提醒了我大概四次，后来我不得不告诉它这个不碍事，事实上整个工作流程都不是我关心的。

It basically had a spasm about this thing, reminding me like 4 times before I had to tell it that that didn't matter, and in fact that that entire work stream was not one that I cared about.

然而，也有其他一些主动的事情，我发现它对那些更有用。

And yet there are other proactive things that I found it much more valuable for.

有几次，我收到了那种我会加星标然后过几天再回复的邮件，每次Duet都建议了一个回复，我可以选择编辑或者授权它直接从我的聊天中发送。

A couple of times now there's been an email of exactly the type that I would star and go back to a couple days later, and in each of those cases, Duet has proposed a response that I could either edit or authorize it to send directly from my chat.

有几次我就让它直接发送了，还有一次，是一个最实质性和最有创意的建议，我没有立即发送，但它帮我完成了大约90%，我不需要再回头思考。

A couple of times I've just let it send, and one time on the most substantive and creative proposal, I didn't send it right away, but it got me about 90% of the way there without me having to go back and think about it.

这让我对Duet的这种主动性的价值更加乐观。

This makes me more optimistic for the value of Duet for this proactivity.

我还要指出，虽然Duet是作为iOS应用推出的，但我其实很喜欢它的网页界面。

I would also note that while Duet is pushed as an iOS app, I actually quite like its web interface.

除了你的主要综合信息流，你还可以为Duet创建单独的频道，这样如果你想要一定程度的持续分层组织，你就可以做到。

In addition to your main everything stream, you can also create separate channels for Duet so that to the extent that you want some amount of that continued hierarchical organization, you can do it.

而且Duet利用了Claude的artifact基础设施，所以它可以实际创建你可以互动和编辑的东西，而无需进入单独的界面。

And Duet takes advantage of Claude's artifact infrastructure so that it can actually create things that you can interact with and edit without having to go into some separate interface.

它可以自动将你正在做的事情组织成任务，并分成活动、下一步、预定或已解决等组，你可以通过主聊天或直接添加任务来修改。

It can automatically organize things that you're doing into tasks that it groups as active, up next, scheduled, or resolved, which you can modify either through the main chat or by directly adding a task.

当然，我现在只用了几天，但我已经对这种做法更加乐观了。

Now, of course, I am only a few days in, but I'm already much more optimistic about this approach.

我得说，我不认为你会想在Duet中做所有在Claude中能做的事情。

I will say that I don't think you're going to want to do everything in Claude with Duet.

我有一个UI和品牌视觉设计的任务，在Duet里面做比在Claude的原生设计体验中做差得多，我认为这个原生设计体验今年晚些时候会被整合到Artifacts中，但它仍然有自己设计的用户体验。

I had a UI and brand visual design task, and doing it inside Duet was much worse than doing it in Claude's native design experience, which I believe is being folded into Artifacts later this year, but still is its own designed UX.

所以对我来说，关键还是在于那种主动性。

So for me, it really is going to be about that proactivity.

我所有这些的目的并不是要给这些工具一个具体的排名，或者就你应该如何使用它们、我认为它们会如何发展做出任何定论。

My goal with all of this is not to provide a particular ranking of these tools or to make any definitive statements about how you might want to use them or where I see them going.

坦率地说，我觉得你其实不必担心你投资的是哪个生态系统，因为一旦某个功能在一个系统中奏效，几周甚至几天内，它就会成为所有系统的一部分。

I think frankly, you kind of don't have to worry about which ecosystem of these that you're investing in because the moment that some feature works in one, within weeks if not days, it's going to become part of all of them.

比如说，如果我的Dots不够主动的体验是更普遍的现象，那你放心，OpenAI一定会调整这点。

If my experience, for example, of Dots not being proactive enough is something that is more commonly experienced, you better believe OpenAI is going to tweak that.

如果人们喜欢Duet或其他某个工具的某些UI元素，其他实验室迟早也会模仿这些UI功能。

If there are some UI elements that people like about Duet or about one of the others better, at some point the other labs are going to copy those UI features as well.

更广泛的问题仍然是这些个人代理的定位。

The broader question remains where these personal agents fit.

对我来说，到目前为止，它远非是我与AI互动的主要方式的重大转变，而更像是一个容易设置的、缩小版的自己，帮我做一堆我不想做的事情。

For me, so far, it is much less a big shift towards it being the main way I interact with AI, and much more an easy-to-set-up little baby version of myself that does a bunch of stuff that I don't want to do.

这很有价值，但它是行业未来那样的价值吗？

That's valuable, but is it future-of-the-industry valuable?

还有待观察。

Remains to be seen.

希望这次是幕后窥探的一次有用分享。

Hopefully this was a useful peek behind the curtain.

现在，今天的AI Daily Brief就到这里。

For now, that's going to do it for today's AI Daily Brief.

一如既往，感谢你的收听或收看。

Appreciate you listening or watching as always.

下次再见，祝好。

Until next time, peace.

已剔除 3 处广告（点击展开查看）

F10:29广告 · 已剔除

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

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

To learn more about sponsoring the show, send us a note at [email protected].

F10:45广告 · 已剔除

We recently launched at Superintelligent the new AI Champions Program.

It's a way to learn not just how to use AI well, but also how to bring that AI to the rest of your organization.

There's a link to that you can find at the top of the AI Daily Brief website, or you can just go directly to besuper.ai.

F116:53广告 · 已剔除

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.

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

Learn more about what separates AI Amplifiers from everyone else at kpmg.com/us/aiamplifiers.

The best teams don't have a single star carrying everyone else.

They know their own strengths and each other's weaknesses and play to both.

That's the team Robots and Pencils has built on purpose.

Nobody there is grinding through busywork to pad a headcount number.

People come for the hard problems and they stay because everyone around them is leveling up at the same time.

In a market full of companies that are just trying to hire fast, that's worth a look.

Check out robotsandpencils.com/careers.

This episode is brought to you by CData.

Companies rolling out AI keep hitting the same wall.

Token spend is climbing, security is holding agents back, and no one knows how AI is truly being used.

The root cause: AI is cut off from the systems and context your business runs on.

That's why CData built Connect AI Gateway, one control point between your AI and your systems.

Built on the connectivity layer powering Palantir, Google, Salesforce, and hundreds more, each agent gets exactly the data and tools it needs.

It governs down to the record and lets you finally see your org's complete AI usage in one place.

Accurate answers, a fraction of the token cost, and a gateway that learns your business with every interaction.

See how at cdata.ai.

Every AI coding tool on the market does the same thing first: it starts writing code.

Blitzy does the opposite.

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

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

The result is a dynamic knowledge graph that understands your software the way a principal engineer would after 30 years in the building.

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

Blitzy never guesses.

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

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

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

See for yourself at blitzy.com.