ChatGPT与Codex负责人：给普通人的智能体已经到了

Tibo

会有剧烈的变化。每个人都会在自己的电脑上拥有一个小小的私人助理，让你能做的事超过三个月前、六个月前可能的范围。

There is going to be dramatic change. Everyone is going to get their own little personal assistant on their computer that allows you to do more than whatever was possible three months ago, six months ago.

Marina Mogilko

这是 Thibault。他在 OpenAI 负责 ChatGPT、Codex 和 API——你每天用的大多数 AI，背后的技术都跟他有关。他刚刚跟我说：再过几个月，完全不用 AI 的人，也能拿到过去两年一直在摸索的人同样的好处。

This is Thibault. He runs ChatGPT, Codex and the APIs at OpenAI — the tech powering most of the AI you already use every day. And he just told me that in a few months, people who don’t use AI at all will get the same benefits as the ones who’ve spent the last two years figuring it out.

Tibo

今天你必须主动写提示词，还得对要问什么有创意。未来就不是这样了。

Today, you have to actively prompt and be creative about what you’re asking. In the future, that’s not the case anymore.

如果一个人有创意、有好想法，现在是实验的好时候。

If you’re a creative person with good ideas, it’s a great time to experiment.

Marina Mogilko

我的观众里有一部分是开发者，但很多是知识工作者，他们对 AI 很兴奋。我们在软件工程里已经看到了这一点：Google 说现在 75% 的代码是 AI 写的，所以这一行已经被 AI 改过了。你说过，这种转变会在未来六个月扩展到所有知识工作。对知识工作者来说，你觉得会变的是什么？

My audience — some of them are developers, but a lot of them are knowledge workers. And they’re very excited about AI. And what we’ve been seeing with software engineering, right? Google says 75% of the code is now AI-written. So it has been really transformed by AI. And you said something that this transformation will extend to all knowledge work over the next six months. So what do you think is going to be changing for people who are knowledge workers?

Tibo

我觉得变的主要不是人，而是技术已经成熟了。现在智能体在长程任务上已经可靠。它很会用很多不同的工具，电脑操控是其中之一，还有浏览器。我们已经加了超过一百个插件，能接到你生活里已经在用的各种小工具。智能体，加上 GPT-5.5，在这上面非常可靠。所以更多是技术成熟了、准备好了。每个人都能从一个智能体里拿到好处。以前你得有点技术，得钻进去；如果它不可靠，五分钟就开始挣扎，你可能还得去改配置，那显然需要技术背景。现在不是那样了。所以我觉得它会变得非常普及。

I think it’s not that much that people are going to change as the technology has matured. And now agents are reliable over long horizons. It’s now very capable of using many different tools, computer use being one of them, browser use. We have added over like 100 different plugins that can tap into every little tool that you already use in your life. And the agent and GPT-5.5 is extremely reliable at it. So it’s more that the technology has matured and is ready. And so everyone will be able to get benefits from an agent. Whereas before, you have to be a little bit technical and get in there. If it wasn’t reliable, if it was struggling five minutes in, you could maybe have to go into the configuration. Obviously, that requires a technical background. That’s not the case anymore. So that’s why I think it’s going to become very widespread.

Marina Mogilko

你觉得变最大的会是什么？比如说一个做市场的人，智能体会怎么改他的日常？

What do you think is going to change the most? And say, if you take a marketer, what’s going to change their day-to-day with agents?

Tibo

你会去看哪些能自动化。也许我花一小时做市场调研，花一小时把大量进件和邮件摘要掉，再花两小时过潜在客户。六个月前还算进阶的概念，比如按 Cron 定时跑，现在就在应用里：你可以直接说，每 12 小时跑一次，做些市场调研，给我发一份 PDF。

So you’re going to look at what can you automate. Oh, maybe I spend like one hour doing market research. Maybe I spend one hour summarizing a whole bunch of inbound and emails. Maybe I spend two hours going through prospects. And so a lot of the concepts that were advanced concepts maybe six months ago, such as running something on a Cron schedule — nowadays, it’s just in the app. You can just say, run this every 12 hours, do some market research, send me a PDF.

Marina Mogilko

然后它会发到你邮箱？

And it’s going to send it to you over email?

Tibo

是的，可以发到邮箱，也可以在应用里看，也许还能打印。几周前我做过一件事：把 Slack 上的新闻全部摘要，然后每天实体打印出来。我就配着咖啡看。有点老派，我就是想要一份报纸。这种事马上会变成主流。

Yes, and I can send it to you over email, or you can just consume it in the app. Maybe you can print it. I did this a couple of weeks ago where I would summarize all the news from Slack and then print it on my printer physically like every day. So I would have it with the coffee. It’s getting maybe old school. I just kind of want my newspaper. This kind of thing is just going to be mainstream.

Marina Mogilko

我很受启发的一件事，是看你跟 Greg 的播客：早上起来喝咖啡，面前一块仪表盘，它问你「你能批准这个吗？我就要跑了」。你等于在读智能体睡觉时干完的活，批准一下，它继续。你觉得这什么时候会变成现实？

You know what I was really inspired by? I was watching one of your podcasts where you were talking with Greg about having this dashboard, basically when you wake up in the morning, you have your coffee, and it just tells you like, can you approve this and I’m going to run it? So you just basically read through whatever your AI agent did while you were sleeping and you were approving and it’s continuing its work. When do you think it’s going to be a reality?

Tibo

没那么远。技术已经存在，差的是包装。比如上周我们发布了 auto review，就是这个概念。做调研的时候，这件事确实让我很震撼。你有主智能体在做事，然后有第二个智能体核查第一个智能体的所有动作，确认它们不会对你造成伤害、风险很低。这是安全团队和 alignment 团队、主要是 alignment 研究里出来的创新。它让你能把智能体更长时间地自主跑下去，即使处理相当敏感的数据，也不至于比如给你通讯录以外的陌生人发一封带个人信息的邮件。

It’s not that far off. The technology already exists. It’s about packaging it. For example, last week we released auto review, which is the concept. It definitely blew my mind away when we did the research on that. So you have the main agent doing actions, and then you have a second agent that is verifying all the actions of the first agent and verifying that they are not doing anything that could be harmful to you and, like, in a low risk. And so that’s an innovation that came out of our safety team and alignment team, primarily alignment research, and it allows you to run an agent much more, for longer periods of time autonomously, even handling quite sensitive data without risking, for example, your agent sending an email to a stranger with some of your personal information in there.

Marina Mogilko

现在这些部件让它更安全，你也愿意把生活里很多东西交给它。数据该怎么组织？假设我们都准备部署第一个智能体，它需要好数据。我以前主要喂语气、个人档案，后来发现它给我做内容时，其实很需要知道我的策略。如果有人刚起步，你会对他们说：这些数据怎么组织，必须创建的文件有哪些？

Now that you have these pieces to make it more secure, more safe, and you’re willing to give access to a lot of things in your life. How do we organize our data? Imagine we’re all getting ready to deploy a first agent, right? And the thing is, agent needs good data. And sometimes, you know, I’ve been working with mostly my tone of voice, like personal dossier. But then I realized that my agent would really benefit from knowing my strategy when it creates content for me. So what would you say to someone who’s just starting out, how to organize this data, what are the must-have files that they have to create?

Tibo

我把所有东西组织在电脑的本地文件里。我有一个文件夹，笔记放在里面，保持相当整齐，也用智能体来整理，然后它会随时间变多。

I organize everything on local files on my computer. So I have a folder. I have my notes in there. I keep it fairly tidy, and I use my agent to organize it. And then it grows over time.

Marina Mogilko

这就是我的问题。大家是在本地电脑上工作的。我有一台旅行用的笔记本，工作室一台 Mac，办公室一台。

That’s my question. People work with local computers. I have a laptop that I travel with. I have two Macs, one in my studio, one in my office.

Tibo

未来三个月你会看到：这些都会上云。你不必再只在笔记本上管本地文件；然后你出门、拿起手机，突然就不是同一个智能体了。那很烦，因为你等于有两个分开的实体，要把生活映射到两套东西上。所以大量会到云上。它会自己管记忆，也会帮你管托管在某处的文件。目前还没有很好的方案，这其实挺令人惊讶。

So what we’re going to see over the next three months is all of this is going to come to the cloud. And you’re not going to have to manage local files on just your laptop. And then if you happen to travel and you’re on your phone, now suddenly it’s not the same agent. And that’s annoying because you have two separate entities that you need to map to different things in your life. So a lot of this is going to come to the cloud. It’s going to manage its own memory. It’s going to help you manage files that are just hosted somewhere. There’s no good solution yet, which is sort of surprising.

Marina Mogilko

我现在是全扔进 Google Drive，再把 Google Drive 接上。

Yeah, I’m just putting everything to my Google Drive and I’m connecting a Google Drive.

Tibo

那能用。那能用。

Yeah, that works. That works.

Marina Mogilko

如果谈知识工作者的生产力，每个人都该给智能体准备哪些文件？

What are the files that everyone should come up with for their agents? If we’re talking about productivity for knowledge workers.

Tibo

语气是很好的一份。但也许出乎意料：我不建议你真的去解释自己的语气。我建议直接放例子——你发表过的 newsletter、录音片段，或者你在不同场景、职业和私人场合发给朋友的消息。我有很多围绕项目的笔记，每个项目一个文件夹，里面有各种文件。还有联系人。但你不必把所有东西都维护成文件。你也可以直接依赖已经在用的那些生产力应用，然后比如 Codex 会去把该拉的信息拉出来。

Tone of voice is a good one. And for that, maybe surprisingly, I don’t recommend actually trying to explain your tone of voice. I recommend just including examples of past newsletters maybe that you published, or snippets from recordings, or messages that you sent to friends in different, maybe professional and personal settings. I have a lot of notes around projects that I have. Each project has its own folder with various files in it. And then contacts. But you don’t have to maintain everything in files. You can also just rely on all the productivity apps that you already have. And then Codex, for example, will be able to go and pull the right information.

Marina Mogilko

你怎么判断该停在一个项目里，还是让 Codex 真的去造一个工具或应用？

How do you know when you stay inside a project or you want Codex to actually build something like a tool or an app?

Tibo

有时候我觉得需要一个专用应用来覆盖新场景，就会建一个新文件夹，在里面试验。但现在越来越多，我感觉自己更少需要那种只会做一件事的静态应用，更多地就是让智能体什么都替我做。

Sometimes I feel like I need a dedicated app for a new use case, and then I go and create a new folder and then I just experiment in there. But nowadays more and more, I feel like I need less of static apps that just can do one thing, and I rely just more on my agent to do everything for me.

Marina Mogilko

如果有人开始用智能体，有人不用，一年或三年后他们的生产力差在哪？

If somebody starts using agents and somebody doesn’t, what’s the difference in their productivity in say one or three years?

Tibo

一到三年已经太远了，技术本身到那时会变很多。我们会看到：愿意适应、愿意去发现这些东西的人，会明显更高效，也能去做你现在大概会往后拖的那些事。每个人都会在电脑上拥有自己的小小私人助理，帮你报税、设邮件过滤器，提醒你、帮你跟亲人多联系。这件事会把很多人连在一起。

One to three years — that’s so far off. The technology itself will change so much by then. What we’re going to see is that people who are willing to adapt and discover these things are going to be quite a bit more productive, and it’s going to enable you to do all these things that you sort of now maybe put off. Everyone is going to get their own little personal assistant on their computer doing all of that — maybe filing your taxes, setting up email filters, telling you and helping you get more in touch with your loved ones. That is something that will connect a lot of people.

Marina Mogilko

我开始多用 AI 之后，有一种责任上的两难。你刚提到报税。AI 完全能替我报税。我有一套自动化，每个月告诉我要交多少税、可以上哪些税务策略。我愿不愿意为此负责？我不知道。还有，作为创业者我很清楚：如果今天才起步，你会高效得多；但如果你已经在经营，我不会因为一个 AI 智能体能跑这件事，就把团队里的人开掉。我会让那个人去用这个智能体。你觉得这会往哪走？我一跑很多智能体，就觉得必须去盯、去核验产出。然后我又想：还是让别人来管吧。

When I started using more AI, I felt this responsibility dilemma. You just mentioned taxes, right? AI can totally do taxes for me. And I have this automation that tells me every month how much tax I’m going to owe and what tax strategies I could be deploying. Do I want to be responsible for that? I don’t know. Like, when it comes to these tasks, also as an entrepreneur, I totally realize if you’re just starting out today, you’re much more productive, but if you’re an existing entrepreneur, I wouldn’t really fire anyone on my team because an AI agent can run it. I would just ask that person to use that AI agent. Where do you see this go? Because I feel like when I started running so many agents, I feel responsible that I need to check on them. I need to verify their output. I’m like, oh, I’ll just let somebody else handle it.

Tibo

这很有意思。说到底，人仍然要负责。我们的想法其实是增强你自己的能力，给你一个工具，让你能做的事超过三个月前、六个月前，并把工作里大量无聊的部分自动做掉。写代码这件事对我们很重要：如果你产出了一段代码，你要为它负责。它坏了，不是智能体的错，是你的错。代码审查也一样。你不能把「理解」外包出去。人仍然在控制之中，仍然是需要理解整个系统、理解事情怎么运转的人。所以如果你把它看成增强你作为人的生产力，那很显然，你仍然需要人。毕竟我们是为自己而建，为了让自己的生活更好。

That’s interesting. So at the end of the day, humans remain responsible. And then the way that we think about it — this is actually about augmenting your own capabilities and giving you a tool that allows you to do more than whatever was possible three months ago, six months ago, and take a lot of the boring parts of the work as well and just do that automatically for you. It is important as we see this for coding. For us, it’s like if you produce a piece of code, you are responsible for it. If it breaks, it’s not the agent’s fault. It’s your fault. Same for code review. And you cannot outsource understanding. At the end of the day, humans still remain in control and remain the people who need to understand the entire system and how things work. And so if you view it under the lens of augmenting your own productivity as a human, obviously you need humans. After all, we’re building for ourselves to better our own lives.

Marina Mogilko

我只是觉得自己先是高效了很多，然后因为想优化太多东西，脑子开始爆炸。

Yeah, it’s just I feel like I’ve become much more productive first, but then I’m like, because I want to optimize so many things, my brain just started exploding.

Tibo

有一个坑是：陷得太深，什么都用它，感觉自己什么都能做，但其实还稍微走在能力曲线前面。所以有些事也许要等未来的模型才可能。那是好事。说明你在往前推，在发现哪里可靠、哪里还要再打磨。也许三个月、六个月后你就能做这件事。

There’s a pitfall of falling too much into using it for everything and feeling like maybe you can do things, but you’re a little bit too early on the capability curve. And so maybe things will be possible with future models. That’s good. That means that you’re pushing and you’re discovering where it’s reliable, where maybe it needs a little bit more work. And maybe this will be something that you can do in three months, six months.

Marina Mogilko

我们来谈 vibe coding。播客前我跟你说过，在 Language Trip 我们 vibe coding 很多不同的应用。我们有一个真正会写代码、写得很好的技术的人，也有我们这种不会写的人。我们 vibe coding 出来的东西如果能跑就很好；然后技术的人进来说，我本来会用另一种结构，因为如果要长大——比如我们有一个「英语最有用的 300 词」应用，vibecode 出来完全能用；但如果我们想扩成 1000 个词，架构就有点不对。现在做 vibe coding，你会怎么处理？如果目标是做成一家大公司，你该和技术的人一起做，还是继续 vibe coding？

Okay, let’s talk about vibe coding in general. So I shared before the podcast that in Language Trip, we’re actually vibe coding a lot of different apps and we have a technical person who can actually write code and he’s really good at it, but then it’s also us who can’t. And when we vibe code something, if it works, great, but then the technical person comes in and says, oh, I would have structured it in a different way because if we wanted to grow it — like for example, we have this app that is 300 most useful words in English, right? And the way it was vibe-coded is in a perfect way, so it’s usable. But if we want to extend it and make it like a thousand useful words, then the architecture is a little bit off. What would you say, how would you approach vibe coding these days? If you’re thinking of building something like it’s going to be a big company, should you work with a technical person or still try and vibe code it?

Tibo

如果目标是分享给几个人、试一试、为了好玩而做，那就自己上手、让智能体帮忙切就完全没问题。如果目标是做大、做成能给几十万人或更多人用的成功产品，把技术的人放进组合里仍然有用。我确实预期这一点会随时间消失：智能体会理解长期维护、正确的结构，并能一路扶着你扩到一个非常大、非常成功的产品。

If the goal is to share it with a couple of people and try something out and build it for the joy of it, definitely just cutting it by yourself with the help of an agent — that’s perfectly fine. If the goal is to scale it and make something that is successful for hundreds of thousands of people or more, having that technical person in the mix is still useful. I do expect that over time to go away, where you will have agents which are able to understand the long-term maintenance aspects, the right structure, and be able to handhold you all the way to scaling to a very large and successful product.

Marina Mogilko

时间表你怎么看？因为变得太快了。

What do you think is the timeline? Because it’s been changing so fast.

Tibo

未来六到九个月，我们会看到代码长期可维护性方面的显著改善。至于完全不需要更懂技术的人帮忙，那感觉还相当远。

We will see significant improvements towards long-term maintainability of code over the next six to nine months. In order to not need the help of someone more technical at all, that feels like quite far off.

Marina Mogilko

你整体怎么看软件工程的未来？我刚主持过一场 DeepLearning.AI 的圆桌，六个人有一个共识：你仍然需要技术知识，但也需要变成通才。因为人人都在 vibe coding 应用。作为创作者，十年前我绝不会想去做一个应用，因为我知道有多贵。现在我会去做，然后看到几千人在用、碰到 bug，我又需要一个技术的人。我们到底会需要更多软件工程师，还是更少？

What do you think in general about the future of software engineering? I was just moderating a panel around it with DeepLearning.AI. And we’re talking about how we all had a consensus of six people on the panel that you still need technical knowledge, but you also need to become a generalist. And because everyone is vibe coding apps — as a creator, I would have never thought of building an app 10 years ago because I knew how expensive it was. Now I would build an app, but then I will see thousands of people using it and I will experience some bugs and I will need a technical person. Are we going to need more software engineers or less with this?

Tibo

我觉得我们会看到基础设施和应用的爆炸。现在很棒的一点是：你只要有一个想法，就能做出来，至少能做出某种形态。如果你是有好想法的创意人，现在是实验的好时候。然后你可以快速做原型、迭代，走到一个你觉得可能成功的东西。很难给软件设一个上限：世界上对更多软件的需求有多大？我们还能再解决多少问题？感觉我们还在最开始。

Yeah, I think we’re going to see an explosion in the amount of infrastructure and apps that we built. And nowadays, it’s just awesome because if you just have an idea, you can build it, or at least in some shape you can build it. If you’re a creative person with good ideas, it’s a great time to experiment. And then you can quickly prototype, iterate and get to something that you feel might be successful. And then it’s hard to put a limit on how much software is enough, how much demand is there for more software in the world? How many more problems can we solve? It feels like we’re at the very beginning.

Marina Mogilko

感觉我们一直在想出还能解决的问题。

It feels like we keep coming up with problems we can solve.

Tibo

对。只要这一点还成立，我们还能继续把技术往前推，就会有对大量技术人才的需求。

Exactly. So as long as that continues to be true, and we’re able to continue technological advancement, it feels like there will be demand for a lot of technical folks.

Marina Mogilko

你能不能给我看一套每个人今天就该部署、用来把生产力拉满的工作流？

Can you show me a workflow that everyone should be deploying today to maximize their productivity? Can you think of something?

Tibo

真的因人而异。我做的其中一件事，是用它跟上世界对 Codex 的看法，所以我会收到一份每日摘要，里面是要点。

It really varies. It depends. One of the things that I do is I use it to stay in tune with what the world thinks, for example, about Codex. And so I receive a daily summary of the highlights.

Marina Mogilko

我们能给我也做一套吗？

Can we build something for me? Something like that.

Tibo

可以。我们开一个新对话。比如：我在录一期关于 AI 和 Codex 的播客。在我的收件箱里找相关邮件，根据你从记忆里知道的我的优先级，准备回复草稿。你还没建立起记忆。但如果你经常用 Codex，它会了解你。它也会把 ChatGPT 里的记忆带过来。

Yes. So let’s do a new chat. For example: I am on a podcast talking about AI and Codex. Find relevant emails in my inbox and prepare draft replies based on what you know about my priorities from memory. So you haven’t built memories yet. But if you use Codex a lot, it will learn about yourself. But it’s going to put memory from ChatGPT as well.

另一个是：过一遍网上的热门来源，给我一份过去两周 Codex 发了什么的拆解。我们也可以回到邮件。我的 Gmail 收件箱很乱，给它设过滤器。我记得大概 2019 年，我花了几天整理邮件和文件夹，后来发现太浪费时间了。

Another one is: go through popular internet sources and give me a breakdown of what Codex shipped over the last two weeks. We can go back to email. I have a messy inbox for Gmail — set up filters for it. I remember, I think it was like 2019 or something, I spent a couple of days just organizing my emails and folders and then I realized such a waste of time because I spent so much time with it.

Tibo

我去规划一次旅行：我们该去哪？根据我日历上的空档。因为它能接到你的日历。一份行程计划，用你的日历空档来排。

I went to plan a trip — where should we go? Based on my calendar availability. Because it can connect to my calendar. A trip plan, and use my calendar availability to plan it.

比如你看，它已经过了你的邮件。这一条是「我在录一期关于 AI 和 Codex 的播客」。它已经把邮件过完了，找到了几条跟今天这件事相关的活线索。它过了日历，还在过邮件。所以找到了一堆东西。看起来你跟 Codex 有安排，就是今天。然后这边还有另一条。你可以看到我们在并行做很多事，你可以跑这些小小的智能体线索。

For example, here you can see it’s gone through your email. So this one is like I’m on a podcast to talk about AI and Codex. It’s already gone through your email, found several live threads related to today’s thing. It went through the calendar. It’s still going through email. So it’s found a bunch of things. Apparently you have something with Codex, which is today. And then here you have another one. So you can see we’re doing a lot of things in parallel. You can just run little agentic threads.

这里你可以说：我在做演示文稿，把这个放进 Google 幻灯片。它就会去，把全部内容做成一份 Google 幻灯片。

Here, you could say I am making a presentation, put this in Google Slides. And it will go and it will just prepare a Google Slide for all of the content.

Marina Mogilko

编辑是在应用里做，还是我得离开、去 Google 幻灯片？

The editing is going to be within the app or I will have to leave and go to Google Slides.

Tibo

应用里也有浏览器。我们还上线了一个挺可爱的小功能。现在你可以把这个移过去，看到哪些线索还在跑。比如它还在摘要 Codex 更新，目前在设一些邮件过滤器。我不想改你的收件箱，所以我把这一条停掉。你现在有一份去克里特岛的行程了。

So there is an in-app browser as well. We also shipped this cute little feature. So now you can move this across and you can see which threads it’s still working on. For example, it’s still summarizing Codex updates. It’s currently setting up some email filters. I don’t want to make changes to your inbox, so I’m just going to stop this one. You have a trip to Crete planned now.

Marina Mogilko

今天早上我真的问过 ChatGPT：根据我的提问，我该做什么应用？它给了五个想法。其中一个就是内容再分发。我给了它我的 Markdown 文件链接，它就做了这个应用。唯一的问题是，我想能对着应用口述，让它转成真正的邮件 newsletter，但我觉得没做成。

This morning I actually asked my ChatGPT, based on my queries, what app should I build? And it gave me five ideas. And this was one of the ideas where it’s content repurposing. I gave it a link to my MD files. It created this app. But the only thing, I wanted to be able to dictate into the app, so it can convert it into an actual email newsletter. But I don’t think it worked.

Tibo

这是 Content Repurposing Engine，从你所有的帖子来。然后它把这些都给你建好了。

So this was Content Repurposing Engine, from all the posts. Okay, and then it just built all of that for you.

Marina Mogilko

它建得有点太花。我说，咱们先做得很简单。

Well, it built something too fancy. I’m like, let’s just make it very simple. You were a little bit too ambitious here.

Tibo

然后它还有 A/B testing。已经有一份 newsletter 草稿。它没有等你的提示，自己就往前生成了。它自己判断：这大概是你需要的。

And then it has A/B testing. It’s already a newsletter draft. And actually I like that. It didn’t wait for my prompt. It just went ahead and generated. It just did a lot of these things by itself. It was like, this is probably what you need.

Marina Mogilko

唯一不工作的是语音输入。我想对着应用口述。再写一条提示能修好吗？

And then the only thing that doesn’t work is voice input. I want to be able to dictate into the app. Is it something that another prompt is going to fix?

Tibo

可以。应用里我们还没有听写。你能不能用 OpenAI 的 speech-to-text API 接进去？为此你需要一把 API key，但你现在可以先随便填，然后去网上的文档，看怎么把 OpenAI speech-to-text API 接到这个应用里。

Yes. So in the app we don’t have dictation working. Can you integrate it with the OpenAI speech-to-text API? For that you will need an API key, but you can just make it up for now and you can go through this documentation online to figure out how to integrate the OpenAI speech-to-text API into this app.

Marina Mogilko

那是一条很专业的提示。我怎么知道自己需要那条提示？我根本不会想到 API key。所以有时候你还是需要一个稍微懂技术的人。

That was a very sophisticated prompt. How do I know that I needed that prompt? Because I would never think about API keys. That’s why sometimes you still need someone who’s a little bit technical.

Tibo

但现在也许还停留在「你需要更多技术背景」的那些事，会变成主流。也许你今天还需要我，但三个月后它就能把这些都设好。它会直接连到你的 OpenAI 账号，你不必再设一把单独的 API key，它能接到所有东西。

But a lot of these things that right now maybe are still a little bit in the realm of, oh, you need more of a technical background, are going to come and become mainstream. So maybe you need me today, but in three months, it will be able to set all of this up. It will just connect it to your OpenAI account. And you don’t need to set up a separate API key. And it’s going to be able to just connect to everything.

Marina Mogilko

你能不能讲讲最复杂的用例，或者工作流看起来很复杂、但能极大改变日常生产力、每个人都能从中受启发的那种？

Can you talk about the most sophisticated use case, or maybe the use cases that are very sophisticated in terms of workflow, but that change productivity tremendously for people day to day, something that everyone could get inspired by?

Tibo

你可以标记很多不同的插件。你可以说 Gmail、日历，如果你有文档也可以。然后：做我的参谋长，给我一份一天的拆解、什么重要的摘要，并帮我准备好。你每天一开始就跑这个。然后你可以比我这里的示例提示更具体。我见过有些人，对「怎么让自己准备好」提出相当复杂的要求。

So you can say, go through — you can tag a lot of different plugins. So you can say Gmail, calendar, if you have docs. And be my chief of staff and give me a breakdown of my day, a summary of what is important, and prepare me. And then you just run this at the start of the day, and then you can be more specific than the example prompt that I gave here. Like some people that I’ve seen have fairly sophisticated requests for how to be prepared.

Marina Mogilko

还有：我把时间浪费在哪了？我是该雇人修某个我花最多小时的地方，还是做一个应用来优化？

Yeah, and like, where am I wasting my time? Should I be hiring someone to fix something where you see I’m spending most of my hours, or building an app that’s going to optimize?

Tibo

你真的可以跟 Codex 讨论，开始头脑风暴怎么把事情理顺。

You can really discuss with Codex and start to brainstorm about how you can streamline things.

Marina Mogilko

你自己用它做什么、按什么顺序、对应哪些任务？

What do you personally use, and in what order, for which tasks?

Tibo

我大量用来写代码。我也用它帮我规划我们准备发出去的不同部分：什么顺序、叙事怎么搭。它是很好的思考搭档。我用它整理自己一天里的笔记。现在我不再记到单独的笔记应用里，而是直接记进 Codex。

So I use it for coding a lot. I use it to help strategize for the different pieces that we’re planning to put out — in what order, the narrative to construct. So it’s a great thought partner. I use it to organize all my own notes throughout the day. So instead of taking notes in a separate notes app, now I just take them straight into Codex.

Marina Mogilko

有意思。

Oh, interesting.

Tibo

它就在堆记忆。你想说什么就新开一个对话。我就说：嘿，我在想这个。

And it just builds up memories. You just start a new chat for anything you want to say. And I’m just like, hey, this is what I’m thinking.

Marina Mogilko

到一天结束，它会自动摘要，还是你得提示它？

And then at the end of the day, does it automatically summarize it or you have to prompt it?

Tibo

我会提示它，把所有东西倒进一份文档，同时它也在建记忆。我还经常用它跟上并回复重要的未回邮件或 Slack 消息。

I prompt it to then dump everything into a doc, but also it builds up memories. I use it to often stay on top of and answer important unanswered emails or Slack messages.

Marina Mogilko

你有没有看到从更多代码工作转向更多生产力工作？还是一直差不多？

Are you seeing this shift from more code work being done with AI to more productivity stuff? Or has it been equal?

Tibo

想想工程师、程序员一天到底在干什么，其实挺有意思。即使在那里，大部分时间也已经不是花在写代码上。所以我们看到了一种转变，连我们的技术用户群里也是：今天 Codex 上超过 50% 的任务已经是非技术任务。

So it is interesting to think about what is an engineer, what does a programmer do all day? And already there, the majority of the time is not spent on coding, actually. So we saw a shift over time, even including in our technical user base — way over 50% of the tasks done on Codex are non-technical tasks today.

Marina Mogilko

已经？应用才上线多久？

Already? And it’s been — the app has only been three months?

Tibo

是的。我们上线了应用。面向程序员的 Codex CLI 是一年前。

Yes. So we launched the apps. The Codex CLI, which was definitely for programmers, that was a year ago.

Marina Mogilko

那人们拿它做什么？你看到的用例是什么？

So what are people using it for? What do you see? What are the use cases?

Tibo

很多是：帮我计划、帮我组织、把旅行想清楚。现在有了电脑操控和浏览器，它可以做比如帮你在 DoorDash 下单、帮你购物。

There’s a lot of like, help me plan, help me organize, thinking through trips. Now with computer use and browsers, it can do things such as order on DoorDash for you, do your shopping.

Marina Mogilko

会不会很慢？我还没在浏览上试过，有时候智能体浏览器……

Does it take long? I haven’t tried it on browse yet, but sometimes the agentic browsers is like—

Tibo

我们有目前最快的电脑操控实现。快得让人意外。你会看到它在点击。

No, we have the fastest computer-use implementation out there. It’s surprisingly quick. So you will see it click around.

Marina Mogilko

我们能不能让它去下载我的 LinkedIn 分析？

Can we ask it to go and download my LinkedIn analytics?

Tibo

可以。你加上 computer，然后去 LinkedIn，下载我的分析。格式我们说 Excel 表格，再做一份 spreadsheet。它会用桌面控件。ChatGPT 的差别在于：它可以真正用你的电脑。它是一个完整的智能体，能用浏览器，也能在你的应用上点击。你看，它已经在访问了。

Okay, so let’s do — add computer, and then go to LinkedIn and download my analytics. And then the format we said, Excel spreadsheet, and create a spreadsheet. I’ll use the desktop controls. So the difference from ChatGPT is that it can use your computer. It’s a full agent that works and has access to your browser, can click around on your apps as well. And you can look at it here. So it’s already visiting.

Marina Mogilko

它已经在我的 LinkedIn 页面上了。它在导出东西。已经在存了。太神奇了。

It is already on my LinkedIn page. Oh, it’s exporting something. It is already saving stuff. That’s amazing.

Marina Mogilko

等它跑完，我想问你一件事。你从博士里退学了，对吧？两周之后？去创业？如果现在有人在读博、本科或硕士，觉得自己很讨厌，你会建议他们退学吗？现在是退学的好时机吗？

While we wait for him to finish, I wanted to ask you something. You dropped out of your PhD, right? After two weeks? To start a company? Would you recommend to someone who’s doing their PhD or bachelor’s and master’s now and feel that they’re just hating it? Is it a good time to quit?

Tibo

那是很久以前了。差不多 15 年前。

This was a long time ago. This was almost 15 years ago.

Marina Mogilko

但现在更相关。这 15 年里，教育的含义已经变了。你在 OpenAI、DeepMind 内部看到这么多创新，你觉得人们还该追求很深的教育，还是该出去直接做？

But now it’s even more relevant. It’s interesting how the meaning of education has changed in these 15 years. What do you think from seeing all the innovation inside OpenAI, DeepMind — should people still be pursuing very deep education, or should they just go out and start building?

Tibo

我从博士退学，是因为刚开始之后，我觉得把四年人生押在那个具体课题上，其实不是我想做的。我有更多想法、更多想试的东西。所以我觉得创业环境适合我。我一次次在自己的生活里意识到：跟着直觉走、做给你能量的事，非常重要。

The reason I dropped out of my PhD is I just actually, after starting it, I felt like that committing four years of my life to that specific subject was actually not what I wanted to do. And I had more ideas and more things that I wanted to try. And so I felt like a startup environment was right for me. I think it’s very important to, time and time again in my own life, I’ve realized that it’s important to follow your instincts and do things that give you energy.

Marina Mogilko

对你来说那是对的决定吗？

Was it the right decision for you?

Tibo

绝对是。我过得很开心。我把那家公司做了大概一年，然后去了 Google。一开始做 Google Maps，还做过广告的不同部分，后来到了 DeepMind——那是 DeepMind 的黄金年代，一个大挑战接着一个大挑战。后来没那么有意思了。大概在所有人都在规模化、OpenAI 已经证明你可以规模化 transformer、做出非常有吸引力的东西、而那可能就是通向 AGI 的路的时候，我就想：好，去 OpenAI 工作吧。一次次如此：逼自己去追求新事物。

Oh, absolutely. I had such a great time. I built that company for like a year and then I went on, worked for Google. Initially I was working on Google Maps and different parts, ads, and then I ended up working at DeepMind, which was during the golden ages of DeepMind, when it was a grand challenge after grand challenge. And then it became a little bit less interesting. And around the time where everyone was scaling and OpenAI had proven that you could scale transformers and create something very compelling, and this was probably the road to building AGI — that’s when I was like, okay, let me go work for OpenAI. And time and time again, it’s challenging myself to pursue new things.

Marina Mogilko

看结果之前最后一个问题。以你看到的这些创新，三到五年后我们的生活会怎样？会不会出现很多人在讲的那种剧烈变化，还是他们夸张了？

So before we look at what it’s created, one final question: what do you think is going to happen to our lives in three to five years from all the innovation that you’ve seen? Do you think we’re going to see this dramatic change that a lot of people are talking about, or are they exaggerating?

Tibo

我觉得会有剧烈的变化。对我们、对我个人来说，重要的是真的把好处带给每一个人。我认为这意味着：无论你是不是在主动使用这项技术，你都会得到好处。今天你必须主动写提示词，对要问什么有创意；你拿到的好处，几乎跟提示词写得好不好成正比。未来不会是这样。对我来说，那会非常像去找一个好裁缝：他一眼看你、懂你，然后说，这种衣服会让你发光，正好适合你。

I think there is going to be dramatic change. I think it’s important for us and for me personally to really bring the benefits to everyone. And one thing that I think this will mean is that you will have the benefits whether you’re actively engaging with this technology or not. Today, you have to actively prompt and be creative about what you’re asking. And the benefits that you get are definitely proportional to how good you are at prompting. In the future, that will not be true. To me, it will be very similar to going to a nice tailor. Instantly looks at you and gets you, and it’s like, this is the kind of clothes that would make you shine and that is just right for you.

Marina Mogilko

那它将取决于什么？如果不是提示词，什么会让人变得出色？

So what will it depend on then? If it’s not your prompting, what’s going to make people brilliant, I guess.

Tibo

会更像从朋友那里得到好建议，或者像我们现在这样自然地聊天。所以是提出正确问题的能力，而不一定是去「提示」它们。它会是以你真实的自己进入一段对话，然后在对的时间得到对的帮助，并从这种支撑社会的环境智能里受益。

Yes, it will be much more like benefiting from good advice from a friend, or having a natural conversation, like the conversation that we have right now. So the ability to ask the right questions, not to necessarily prompt them. It will be about engaging as your authentic self in a conversation and then getting the appropriate help at the right time. And benefiting from this ambient intelligence that is just supporting the society.

Marina Mogilko

它做出了一份 spreadsheet。它把分析都从 LinkedIn 下载下来了。如果我们问得更具体，因为它等于做了一张截图。我需要更多数据，比如每篇帖子的曝光。

It has created a spreadsheet. So it has downloaded all the analytics from — oh, that’s amazing. Like if I ask it to do more specific, because it did like one screenshot. I need more data, for example, impressions per post.

Tibo

我现在用 Codex 已经很懒了，能不打字就不打字。

Okay, so I am very lazy now with Codex and I just do everything to avoid typing.

Marina Mogilko

一样。我到处都用 Wispr Flow。

Yeah, same. I just use Wispr Flow across all my—

Tibo

如果你喜欢某个工作流，你可以用 skill creator——它本身就是一个 skill。你可以说：创建一个 skill 来捕捉这个工作流，让我每天都能跑。然后它会给你做一个专属 skill。我们可以就这样收集分析。

If there is a workflow that you like, then you can use a skill creator. This is a skill by itself. You can say, create a skill to capture this workflow, such that I can run it every day. And then it will create a bespoke skill for you. So we can just collect analytics.

Marina Mogilko

这太迷人了。谢谢你。我今晚回家大概有活要干了。谢谢你们把它做出来。

Okay, this is fascinating. Thank you so much. I feel like I have some work to do when I come back home tonight. This is really fascinating. Thank you for building it.

Tibo

当然。很高兴来。谢谢。

Of course, yeah. It was a pleasure. Thank you.