Pickful: Your Shared Crypto Community!

· 1d

Basecamp 现已通过全新的、功能全面的命令行界面（CLI）向客服代表全面开放，该界面由一款出色的技能所封装，并依托经过全面升级且大幅扩充的 API。这是一种绝佳的方式，既能让客服代表访问 #Basecamp 中的所有内容，又能将其集成到任何地方。 #cli #ai https://x.com/dhh/status/2036860598785356219

中文 English

0:00 有一整批消费者已经把人工智能等同于产品

0:07 攻击，跟扯淡一样。

0:09 人们并不是讨厌人工智能。

0:11 他们讨厌的是因为你想留住你的

0:16 产品而搞出的糟糕人工智能。

0:17 欢迎收听 Rework，这是 37signals 关于更好工作方式和企业管理的播客。

0:21 你的

0:21 业务。

0:21 我是 Kimberly Rhodes，来自 37signals 团队，与我一同的是 Jason Frieden 和 David

0:26 Heinemayer Hanson。

0:28 我们将谈论科技和人工智能相关的内容。

0:31 Basecamp 最近已支持智能代理。

0:35 这样你的 AI 代理就可以在 Basecamp 内工作了。

0:38 我不是专家。

0:39 接下来由你们来说。

0:40 David，你想先说吗？

0:41 当然。

0:43 我先挑剔一下这个词，就像我们刚开录之前讨论的那样。

0:47 “代理友好”这个词不错，不过对我来说更

0:53 关乎无障碍性。

0:54 在传统网页设计中，这就是我们对无障碍性的争论，意味着

0:58 让视障或

1:05 视力有限、色盲等人群更容易使用网站

1:05 那些特殊因素可能让他们难以使用未考虑这些的应用程序。

1:11 所以我们做无障碍工作。

1:15 进行对比测试。

1:20 如果某两种颜色放在一起，效果不佳。

1:22 色弱者看低对比度内容会很困难。

1:24 所以需要调整。

1:28 引入不同的颜色，增加对比度，

1:31 针对完全失明的用户做这些优化。

1:32 确保键盘访问性很高，能完全用键盘操作。

1:36 在不同元素间切换时，有合适的流程和节奏，

1:39 不会跳来跳去让人摸不着头脑。

1:43 我就是这么看待我们为代理无障碍做的工作。

1:44 这些 AI 代理在许多事情上非常聪明，

1:50 但在使用网站时却还会笨拙。

1:51 它们勉强能用，但速度很慢。

1:55 一个月前我们开始做这项工作时，我做了个大测试，

1:55 想着我们是不是根本不用改进。

1:59 目前的代理、现成模型，云端代码和开源代码等，

2:00 它们能不能直接做到？

2:07 它们到底需不需要帮助？

2:10 我惊讶于这些代理仅用浏览器操作竟然如此成功。

2:15 我能让其中一个代理注册 Basecamp，

2:21 在 Campfire 自我介绍，

2:23 Vizzy 和 Hey 代理也能做到，尽管速度非常慢。

2:29 那种感觉是，我能看到未来，但不知道未来何时到来。

2:33 看起来至少还有一年。

2:33 可能是两年，五年也说不准。

2:35 如果我们今天想让 Basecamp 成为使用代理的好地方，

2:42 得让它速度快起来。

2:46 没人会有耐心等代理在聊天界面慢吞吞地处理任务。

2:47 它们只是机械地输出信息，对吧？

2:52 然而这个速度必须适合在 Basecamp 中使用它们。

2:58 这就是所有代理无障碍工作的意义。

2:59 就像是铺了条小斜坡一样，

3:02 轮椅无障碍，你本可以用别的方法上去，

3:05 但很麻烦甚至有点危险，

3:09 有了斜坡就能轻松滑上去。

3:12 这就是我们给 Basecamp 做的事，

3:15 创建了命令行界面（CLI），

3:21 AI 代理可以用这个工具。

3:24 过去六到九个月中，我们发现给 AI 这些终端工具时，

3:26 它们变得超级强大。

3:29 这就是最近三四个月代理加速开发热潮的原因，

3:31 程序员和设计师突然能做更多事了，

3:34 不仅仅是向训练有素的 LLM 提问，

3:37 然后得到答案。

3:40 而是让代理去执行操作，代理会尝试完成任务。

3:44 就像人一样，有时不会做，

3:48 调用错误工具，犯各种错，

3:49 但如果能持续反馈，反复尝试调整，

3:52 不断试错，最终成功，

3:58 就能快速前进。

4:04 但这需要工具使用快速。

4:09 虽然我很佩服代理能用浏览器，且用得不错，

4:14 但了解它们为何这么慢后就明白了，

4:18 现在它们实际上是在截图，

4:22 通过图像分析分解界面元素和字段，尝试理解，

4:23 非常厉害，但非常繁琐且慢，

4:30 相比之下如果用命令行界面。

4:30 只需要文本。

4:35 这正是这些大语言模型被训练的内容，数万亿的文本数据。

4:39 它们读文本，预测下一个命令，

4:43 下一段文本。

4:43 and then succeed, it can really quickly move on.

4:47 But that loop requires that the tools are fast to use.

4:51 And as impressed as I was that the agents could use a browser and could use a

4:56 browser really well, you also realize that when you know how they do it, why it

5:02 's so

5:02 slow, right now the agents are literally taking like a screenshot of the screen

5:08 and then running it through this image analyze to break down what are all the

5:13 elements, what are all the fields and then trying to reason about it.

5:16 Very impressive, as I said, but also very cumbersome and very slow versus if

5:22 they

5:22 do all this work through a CLI, a command line interface, that's just text.

5:26 Literally what these LLMs have been trained, like trillions of tokens.

5:32 They've gone through text, text, text, what's the next command?

5:35 What's the next token?

5:36 他们在这方面又快又好。

5:39 所以如果它们能保持在那个小循环里，你就能得到每秒的标记数，

5:43 对吧？

5:44 这很接近就像是在写你的傻故事时的速度。

5:47 而这些之间的差别就是一切，对吧？

5:52 速度，正如我们常说，是一个特性。

5:56 当代理能为你做事，而你又有一些

5:59 耐心去等待时，速度就是一切。

6:02 这是“我懒得做”和

6:04 “让我让代理去做更容易”之间的差别。

6:07 我一直在试验我们新代理在 REMC 或 CLI 上的可访问性。

6:14 尤其是最近用的最快的代理之一，

6:20 Kimmy K25，一个超级快的开放式等待模型，真的让我震惊，

6:26 如果你让它写故事或解决逻辑问题，

6:30 可以达到每秒200个标记的速度。

6:32 也就是每秒100多个词。

6:36 超级快，对吧？

6:38 然后我出于好玩，让它帮我设计一个基地营项目，

6:43 规划基地营五号的发布活动。

6:47 当然，我并没有给它所有背景资料。

6:49 所以它不会给我完整的发布计划。

6:53 但它列出待办事项的速度，拆解得很细致，

6:59 加了备注，加了信息，还添加了日程项目。

7:04 比如说如果你四周后要发布，你得提前一周开始做这个。

7:07 你得在前一周做那个。

7:09 我当时简直惊呆了，这太不可思议了。

7:13 很有趣的是，当你想为什么这感觉特别时，

7:19 如果我18个月前问 ChatGPT 3 给我出一个基地营发布计划的文本，

7:25 它也能做出来。

7:29 我当时可能也会觉得挺不错的。

7:32 但我拿到它后，接下来该怎么办呢？

7:34 这就是代理可访问性的魔力。

7:36 你把所有的智慧、洞察、总结，还有我们

7:42 喜欢的大型语言模型的特点，

7:46 变成可用的东西。

7:49 它不仅仅是一堆文本块。

7:51 不，它是一个完整的项目。

7:54 这里有一些待办事项，有些分配给你，

7:56 有些分配给代理，

8:00 有些分配给 Jason 或者其他参与这项工作的团队成员。

8:05 突然间，所有的智能都变得可执行了。

8:08 说这些话的时候真的得小心，别听起来像是 Salesforce 的机场广告。

8:13 智能变得可执行，砰！但有时候这些

8:18 惊奇的发现确实让你感叹，“哇，真是太棒了”。

8:24 就像我用这些代理进行编程一样。

8:30 我曾经很长时间非常好奇，

8:33 也非常着迷。

8:35 我喜欢问它各种问题。

8:36 然后我又自己动手写了点代码。

8:39 就是用我这两只小手，突然一切都变了，因为

8:44 代理开始能做事了。

8:45 它们能用终端，

8:46 能运行代码，

8:47 能运行测试，

8:49 能重写测试失败的代码，

8:51 能进入那个循环。

8:53 我从“哦，这挺不错”

8:56 变成了“这真是太疯狂了”。

9:00 你去做，我需要时会介入。

9:03 如果我们能把这种能力推广到其他一切上，比如项目设置，

9:09 分工，进度检查

9:13 和回访，

9:14 当这些超能力触手可及时，

9:19 因为所有内容都在基地营共享，

9:23 这不仅仅是我和代理的私人对话。

9:26 整个公司，整个项目，每个人都能围绕这些工作

9:30 协作，且不止用一个代理，

9:34 而是多个代理。我们已经在基地营大量实践了，

9:40 它们驱动着一些内部流程。

9:42 我们有很多不同的代理。

9:44 有些是个人人工代理，代表他们行动，

9:48 还有一些自动代理也做这些事情，并进行跟进和提醒。

9:52 我知道这种爆炸式发展在许多先行公司的

9:53 领域内正在发生，

9:57 但还有剩下98%的世界，

10:01 他们或许用过 ChatGPT，但未用过代理。

10:07 他们没用过命令行界面（CLI）。

10:09 如果你很活跃在 X、推特等平台，看到大家高速发现、分享这些，

10:15 你可能会觉得整个世界已经这样在运作了，

10:20 其实不是，完全不是。

10:22 我们现在所做的工作，比如代理可访问版的

10:25 基地营，使用 CLI、技能等，

10:29 甚至还

10:29 没能覆盖

10:33 广大群众。

10:34 我们还差一步，让它像用 ChatGPT 那样简单，

10:35 而 ChatGPT 几亿人都使用了，

10:42 并很快变得主流。

10:44 我们得跑向冰球会去的方向。

10:46 我觉得这就是这项工作令人兴奋的地方，

10:49 近两年来我们内部做了不少 AI 混合特性实验，

10:55 就是那些把 AI 融入产品

11:02 本身的尝试，比如说，它可能帮你总结，

11:06 给你建议，或以其他方式辅助你。

11:06 大多数公司的这类工作

11:10 成绩可以说是不太稳定。

11:11 如果不那么宽容的话，可以说是完全失败了。

11:18 事实上，情况糟糕到一部分消费者

11:22 已经把 AI 等同于产品退化和胡扯。

11:28 这是事实。

11:34 微软上周刚不得不公开道歉，说抱歉，

11:39 我们把AI乱塞进了画图、记事本，还有Windows的各个角落。

11:46 我们听到了，你们不想要那个。

11:50 当然你们不想要，因为这只是附加上去的，实际上

11:54 并不

11:54 够有用。你把它和消费者对明显有用的东西的兴奋感对比一下，

11:59 比如ChatGPT和其他基于聊天的界面，

12:04 几亿人在用它。

12:07 他们认为它是日常生活不可或缺的一部分，并且为此付费，

12:12 这些东西都说明人们不是讨厌AI。

12:15 他们讨厌的是被乱塞进来的糟糕AI，只因为你想把它

12:20 套进你的产品里，对吧？当然有好的方法。

12:24 有技术可以把AI嵌入产品，让它

12:29 完全

12:30 原生且不可或缺，人们不会拒绝，但这很难。

12:35 正如我说的，我们试了几年，看能不能找到很多

12:40 切入点，尝试了很多方法，但几乎没发布任何成果。

12:45 因为没达到最终标准，我们不想像记事本、画图那样发出烂产品遭到反弹。

12:49 所以我们继续努力，我相信我们会成功。

12:53 我们会找到它真正合适的位置，且非常合理的方式。但在那之前，

12:56 我们可以给大家提供一个简约且易用的Basecamp版本，

12:59 一个他们可以用现有喜爱工具操作的友好版Basecamp。

13:06 比如没有人在每天用Plot代码或Open代码时会说我不想要那个。

13:10 没人会说我不想能用指尖控制Basecamp，

13:14 不想把它连接到GitHub或Sentry或者其他任何东西。

13:17 他们会说想，因为这是显而易见的胜利。

13:21 这也是一种建议。

13:24 我想说的是，任何想搞清楚AI在产品中作用的人，

13:28 但你知道吗？

13:31 在你弄明白之前，如果还没弄明白，就先让它易用。

13:36 让代理更容易使用它。

13:38 这就是解锁我们向客户承诺了二十年的API所有潜能的粘合剂。

13:42 但99.9%的人从未使用我们的API，因为那需要程序员，

13:44 还得做各种准备，太贵了。

13:49 让代理易用，CLI，技能，这一整套把所有承诺带了过来，

13:53 虽然不能完全端到桌上，

14:00 但我们差不多了，不那么麻烦

14:03 的一盒子，很多人都能打开。

14:05 我猜年底前

14:11 这实际上会成为主流，因为会以大家都用的界面批量发出。

14:14 好了，现在代理可以用Basecamp了。

14:17 其他产品有什么打算？

14:18 嘿，Fizzy，那些会推出吗，还是只限Basecamp？

14:20 哦，全部都会推出。

14:23 实际上Fizzy的无障碍做得挺好，因为我们的朋友Rob发布了一个开源CLI。

14:27 其实我们还雇了Rob Salkas来帮我们做Basecamp CLI，

14:27 因为他做Fizzy CLI做得很棒。

14:31 我们会应用很多经验，继续打磨Basecamp CLI。

14:35 这是个AI的启发时刻，我们想让Basecamp更易用，

14:37 于是我们做了CLI，

14:42 而代理实际上写了大部分CLI代码。

14:42 CLI绝大多数代码都是代理写的，

14:43 他们很快就完成了65%。

14:51 然后我们花了几周时间把完成度提高到97%，虽然不是100%。

14:55 现在我们可以把学到的经验，应用到Rob做的Fizzy上，

15:01 推出官方完整打磨的Fizzy CLI和技能。

15:04 接着，百分之百我要这个，

15:08 我要让它支持我的邮箱。

15:09 当我用Fizzy或Basecamp时，把邮箱和它们连接起来，

15:14 把所有东西串联，配一个可以听我指令的执行代理。

15:17 比如我经常用的旅行，就是让代理直接去查信息，

15:20 我只想拿邮件里的一个信息，

15:24 不想翻邮件。

15:25 不想看邮件内容，

15:31 只想要邮件里的事实。

15:35 我很期待给邮箱和日历都全面无障碍，

15:36 把它们串联起来。

15:39 我们会全部做到。

15:42 今后这都会是默认配置。

15:47 代理的无障碍不仅适用于直接使用应用，

15:52 也适用于连接更大的生态系统。

15:57 很多成功应用，比如Slack，一个很好的例子。

15:57 Slack之所以成功，是因为它有一个封闭的生态系统和集成。

16:04 代理无障碍正在让这一切变得开放给所有人。

16:07 所有壁垒都被打破了，

16:11 只在一个应用里有什么优势都不存在了。

16:13 实际上，游戏的关键是你的代理能和你用的任何东西对话，

16:17 访问任何数据，

16:18 不管数据在哪里，都能把它调回来或散布到各处，

16:19 把所有东西连接起来。

16:21 I just want the fact that's in the email.

16:23 I'm really excited for having full accessibility for, hey, both on the email

16:29 side

16:29 but also on the calendar side and tying all these things together.

16:32 So we'll do it for all of it.

16:33 And I think anything going forward, this is going to be baked in.

16:36 This is going to be table stakes that your application is, agent accessibility

16:41 accessible,

16:42 both for the direct use with that application, but just as much because it

16:47 kind of plugs in to this broader ecosystem.

16:50 So many successful applications over the year Slack is a good example.

16:54 We're successful because they ended up with this ecosystem that was kind of

16:58 proprietary to Slack and integrations with it.

17:00 What the agent accessibility is doing is basically bringing that to everyone.

17:03 Like all those moats just come tumbling down because there's no specific

17:08 advantage

17:08 to just having something inside of one application.

17:11 In fact, the whole game here is that your agent can talk to anything you use,

17:17 can access anything you use, wherever your data is, it can move it back here or

17:23 everywhere and tie it all together.

17:24 这真令人兴奋。

17:25 好的，你可以在 Basecamp.com/agents 上了解我们正在做的事情。

17:31 这是 37 Signals 的一部作品。

17:33 你可以在我们的网站 37signals.com/podcast 找到单元内容和文字记录。

17:38 视频

17:38 剧集在 YouTube 上。

17:39 如果你有关于更好的工作方式和管理的提问给 Jason 或 David，

17:43 台词是什么？

17:47 正要说那个。

17:48 我想，等等，我需要代理帮我说这句话。

17:52 如果你有关于更好的工作方式和管理的提问给 Jason 或 David，

17:56 业务。

17:57 给我们留言语音，网址是 37signals.com/podcast question。

18:01 或者你可以发邮件到 [email protected]。

18:05 那不是。

18:05 是这样吗？

18:06 你们，这就结束了。

18:08 是邮箱地址，对吧？

18:09 我想是的。

18:10 哦，天哪。

18:11 让代理检查一下。

18:12 真的，我需要代理来做结尾。

18:17 (欢快的音乐)

0:00 An entire contingency of consumers have come to equate AI with product

0:07 aggression, with bullshit.

0:09 It's not that people hate AI.

0:11 What they hate is shitty AI glob done because you want to stick around your

0:16 product.

0:17 Welcome to rework a podcast by 37 signals about the better way to work and run

0:21 your

0:21 business.

0:21 I'm Kimberly Rhodes from 37 Silver Hills team joined by Jason Frieden, David

0:26 Heinemayer Hanson.

0:28 We are talking about tech things and AI things.

0:31 And Basecamp has recently been made agent friendly.

0:35 So your AI agents can work within Basecamp.

0:38 I'm not an expert.

0:39 I will let you guys talk about it.

0:40 David, do you want to kick us off?

0:41 Sure.

0:43 I'll start by quibbling with the term as we did just before hitting record.

0:47 Agent friendly, I think is a fine term, but I think it's actually to me more

0:53 about accessibility.

0:54 And this was the contention we had about what does that mean traditionally in

0:58 web design, accessibility means making it easier for folks who might be blind

1:05 or

1:05 might have limited vision, might be color blind, have all of these factors

1:11 that make it difficult for them to use a website or an application that has not

1:15 been designed within any of those factors in play.

1:20 So then you do accessibility work.

1:22 You do contrast testing.

1:24 Oh, if you have this color next to this color, that doesn't work very well.

1:28 If someone's kind of blinder, they can't see low contrast well.

1:31 So you change it.

1:32 So you get some different colors introduced, you increase the contrast,

1:36 you do all those things for full on blind users.

1:39 You make sure that keyboard accessibility is really high, that you can do

1:43 everything with a keyboard.

1:44 When you tap from one element to the other, it goes in a flow and a rhythm

1:50 that makes sense.

1:51 And it doesn't just jump all over the place in something that doesn't make

1:55 sense.

1:55 So that's actually how I think about the work we've been doing for

1:59 agent accessibility.

2:00 You have these AI agents that are incredibly smart at a ton of things.

2:07 And then they still kind of stumble when they have to use a website.

2:10 They can barely just do it, but they're really slow.

2:15 I did a big test a while back about a month ago when we set off to do this

2:21 work, where it was like, I wonder if we even need to do anything.

2:23 Can the agents we have right now, the models that are out there, the harnesses

2:29 that people run, cloud code and open code and all the other ones, can they

2:33 actually just do it?

2:33 Do they even need any help?

2:35 And I was shocked by how successful the agents were at using just a browser.

2:42 I could tell one of these agents to sign up for Basecamp, to introduce

2:46 itself in campfire.

2:47 The same thing with Vizzy, the same thing with, Hey, but it was really slow.

2:52 It was one of those things where like, I can see the future, but I can't see

2:58 when it's going to arrive.

2:59 This looks like something that might be at least a year out.

3:02 It could be two, it could be five.

3:05 Who knows if we want to make Basecamp a great place to work with

3:09 agents today, we got to make it fast.

3:12 No one's going to have the patience to sit around and wait for agents,

3:15 take minutes and minutes to do work when you ask them in a chatbot interface.

3:21 And they just, they're spitting out facts, right?

3:24 If that kind of pace needs to be captured.

3:26 When you're working with them in Basecamp.

3:29 So that's what all this agent accessibility work is for.

3:31 It's sort of like a little, little ramps, right?

3:34 Like the wheelchair accessibility, like maybe you could get up with your

3:37 wheelchair some other way, but be very cumbersome and maybe even a little

3:40 dangerous, but if we just make it a little ramp, you can just roll right in.

3:44 So that's what we've done for Basecamp here by creating a command line

3:48 interface,

3:49 a CLI tool that the agents can use.

3:52 Because what we found over just the last six to nine months is that AI

3:58 becomes super powerful when you give them these tools inside of a terminal.

4:04 That's what all this explosion of productivity has been about, especially

4:09 the last three or four months on agent accelerated development work,

4:14 like programmers and designers suddenly being able to do way more stuff

4:18 because they're not just asking an LLM that's been trained on the whole

4:22 internet and getting an answer back.

4:23 No, they're asking the agent to do stuff and the agent will try to do something

4:30 .

4:30 And just like a human will realize that often they don't know how to do it.

4:35 They call the tool wrong, they do all these things, but if it can stay in a

4:39 feedback loop where it can try something, adjust its approach and then try

4:43 again,

4:43 and then succeed, it can really quickly move on.

4:47 But that loop requires that the tools are fast to use.

4:51 And as impressed as I was that the agents could use a browser and could use a

4:56 browser really well, you also realize that when you know how they do it, why it

5:02 's so

5:02 slow, right now the agents are literally taking like a screenshot of the screen

5:08 and then running it through this image analyze to break down what are all the

5:13 elements, what are all the fields and then trying to reason about it.

5:16 Very impressive, as I said, but also very cumbersome and very slow versus if

5:22 they

5:22 do all this work through a CLI, a command line interface, that's just text.

5:26 Literally what these LLMs have been trained, like trillions of tokens.

5:32 They've gone through text, text, text, what's the next command?

5:35 What's the next token?

5:36 They're so good and so fast at that.

5:39 So if they can stay in that little loop, you can get the tokens per second,

5:43 right?

5:44 To be quite close to when it's just writing your silly story.

5:47 And the difference between those things is everything, right?

5:52 The speed, as we often say, is a feature.

5:56 And when it comes to agents being able to do things for you and you having some

5:59 patience to wait for it, speed is everything.

6:02 It's the difference between I can't be bothered to.

6:04 It's easier to ask my agent to do it.

6:07 And I've been experimenting with our new agent accessibility on REMC or CLI.

6:14 And I've been mind blown how quickly, especially the fastest agents like

6:20 Kimmy K25 that I've been using recently, which is one of these super fast, open

6:26 wait models that if you just ask it to write a story or solve a problem, logic,

6:30 you can do 200 tokens a seconds.

6:32 That's whatever, 100 plus words a second.

6:36 Super fast, right?

6:38 And then I asked it to actually, just for the heck of it, design me a base

6:43 camp project that spells out the launch campaign for base camp five.

6:47 And of course, I didn't even give it all the context.

6:49 So it wasn't going to give me the launch campaign we're going to ship with.

6:53 But the pace by which it filled out the to-do list, it broke it all down.

6:59 It added comments, it added messages, it added items on the schedule.

7:04 Well, if you want to launch in four weeks, you got to start doing this

7:07 the week before you got to do this.

7:09 I was just like, holy, smoly, this is incredible.

7:13 And it's so funny because when you think about it, why does that feel special?

7:19 If I had asked chat GPT three 18 months ago about just creating a text

7:25 document with a launch plan for base camp, it would have done that.

7:29 And I would probably also been surprised like that's neat.

7:32 But then what am I going to do with it?

7:34 That's the magic of this agent accessibility stuff.

7:36 You take all the wisdom, the insight, the summarization, all the things we

7:42 like about LLMs and then you make it usable.

7:46 It's not just a block of text.

7:49 No, it's an entire project.

7:51 And here's some to do is some of them are assigned to you.

7:54 Some of them are assigned to the agent.

7:56 Some of them are assigned to Jason or whoever is working on this stuff.

8:00 And suddenly all that intelligence becomes actionable.

8:05 I mean, it's so funny when you talk about these things, you really got to be

8:08 careful not to sound like an airport advertisement for Salesforce or something.

8:13 Intelligence becomes actionable, boom, but sometimes some of these

8:18 revelations actually you sit with and you go like, Oh, wow.

8:24 Yes, much the same way as I've had it programming with these agents.

8:30 Like for a long time, I was very curious.

8:33 I was very fascinated.

8:35 I loved asking it stuff.

8:36 And then I went off and I wrote my little code by myself.

8:39 By my two little hands here and then suddenly things flipped because the

8:44 agents could do stuff.

8:45 They could use the terminal.

8:46 They could run code.

8:47 They could run tests.

8:49 They could rewrite code that failed the test.

8:51 They could get into that whole loop.

8:53 And suddenly I went from like, Oh, this is neat.

8:56 But like I'll write it myself to this is freaking incredible.

9:00 You go ahead, I'll intervene if I need to.

9:03 And if we can get to that for everything else, for setting up a project,

9:09 for for figuring out how to divide the work, for checking in on things and

9:13 checking up on things.

9:14 And we can have those kinds of superpowers at our fingertips because it's

9:19 all in base camp, because it's all shared in base camp.

9:23 It's not just like I have a personal little conversation here with an agent.

9:26 No, the whole company, the whole project, everyone can suddenly

9:30 collaborate around this stuff and not necessarily even with one agent, but

9:34 with multiple, we've started doing this extensively already at base camp, where

9:40 you're driving some of these internal processes that we have.

9:42 And we have a bunch of different agents.

9:44 Some have a personal agent that they're just using to act on their behalf.

9:48 And then we have some automated agents that do all of this stuff too and chime

9:52 in and follow up.

9:53 And I know this kind of explosion is going on at a fair number of companies

9:57 sort of on the leading edge, but then there's the rest of the 98% of the world

10:01 who who may have used chat GPT, but we haven't done anything with agents.

10:07 We're not running into CLI.

10:09 And if you're very plugged into X and Twitter and wherever else that people

10:15 are discovering and sharing all this stuff at high velocity, you think that

10:20 this is how the entire world is already working.

10:22 No, they're not, absolutely not.

10:25 And all this work that we're doing right now, the agent accessible version of

10:29 base

10:29 camp that uses the CLI and the skills and so on, even that is not going to

10:33 reach

10:34 the broad masses.

10:35 We are missing a step yet where this becomes as easy as using chat GPT, which

10:42 hundreds of millions of people have used.

10:44 Like that has actually become very mainstream very quickly.

10:46 But we got a skate to where the puck is going.

10:49 And I think that that's what's exciting about this work, that over the last

10:55 almost two years, we've had a bunch of experiments internally with AI infused

11:02 features, like these are the things where you try to bake the AI into the

11:06 product

11:06 itself and like, well, maybe it can summarize some things or can suggest

11:10 some things or it can help you in other ways.

11:11 And the track record for most companies on that work is let's say mixed.

11:18 And if you're less charitable, say completely fucked, right?

11:22 Like in fact, it has been so bad that an entire contingency of consumers

11:28 have come to equate AI with product degradation, with bullshit.

11:34 Microsoft literally last week had to come out with a mea culpa saying, sorry,

11:39 we shoved AI crap into paint, into notepad, into all these crevices of windows.

11:46 We hear you, you don't want that.

11:50 And of course, you don't because it was tacked on and it wasn't actually

11:54 helpful

11:54 enough. And you got contrast that with the consumer excitement for something

11:59 that's obviously good, like chat to BT and the other chat based interfaces,

12:04 like hundreds of millions of people are using it.

12:07 They're considering it integral to their daily lives, they're paying for it,

12:12 all these things. So it's not that people hate AI.

12:15 What they hate is shitty AI globbed on because you want to stick around your

12:20 product, right? Now, there are ways to do this well.

12:24 There are ways to put AI into a product and have it be something that feels

12:29 fully

12:30 native and integral to it and people wouldn't reject, but that's quite hard.

12:35 We've tried, as I said, for a couple of years to see if we could find a bunch

12:40 of angles on this and we tried many things and we shipped virtually none of it.

12:45 Because it didn't pass that final muster because we didn't want the notepad

12:49 paint backlash of shipping something crappy.

12:53 So we continue to work on that. And I'm sure we're going to nail it.

12:56 We're going to find some ways with this really fits and it really makes a lot

12:59 of sense. But until then, we can give everyone the age and accessible version

13:06 of Basecamp, the in friendly version of Basecamp that they can use with these

13:10 tools they already love. Like no one who's using plot code on a daily basis or

13:14 open code are going to tell you like, well, I don't want that.

13:17 I don't want to be able to just command Basecamp with my fingertips and tie

13:21 it together with GitHub or Sentry or anything else.

13:24 They're going to say, yes, please, because this is such an obvious win.

13:28 So that's also a bit of a recommendation.

13:31 I'd actually say for anyone else who's trying to figure out how AI plays a

13:36 role in the product, but you know what?

13:38 Until you figure that out, if you haven't already, just make it accessible.

13:42 Just make it easier for agents to use this.

13:44 This is that glue that unlocks all the promise that we told customers for

13:49 literally 20 years was going to be there with APIs.

13:53 And 99.9% of them never touched our APIs because it required a programmer.

14:00 It required all sorts of stuff to do it.

14:03 It was just too expensive to do.

14:05 Aging, accessibility, CLIs, skills, this whole bucket takes all of that promise

14:11 and then delivers it not quite on a silver platter.

14:14 We're not quite there yet, but like, I don't know, in a slightly less

14:17 cumbersome

14:18 box, quite a few people can open that.

14:20 And then by the end of the year would be my guess.

14:23 This is actually going to go mainstream because it's going to be shipped in

14:27 bulk

14:27 through these interfaces that everyone uses.

14:31 OK, so base camp is now accessible to agents.

14:35 What are we thinking for other products?

14:37 Hey, Fizzy, are those on the horizon or it's just a base camp solution right

14:42 now?

14:42 Oh, it's coming for everything.

14:43 In fact, we already have some pretty good accessibility for Fizzy because our

14:51 friend Rob put out an open source CLI for it.

14:55 In fact, we ended up hiring a Rob Salkas to work with us on the base camp CLI

15:01 because he did such a great job at the Fizzy CLI.

15:04 We're going to apply a bunch of those lessons that we've now taken really

15:08 polishing the base camp CLI.

15:09 This was one of those AI inception moments where like we're trying to make

15:14 base camp more accessible to the agents and we're making the CLI.

15:17 And the agent is actually making the bulk of the CLI.

15:20 Like the vast majority of the code that goes into the CLI was written by an

15:24 agent.

15:25 And it got like 65% of their of that done in no time at all.

15:31 Then we spend weeks and weeks and weeks and weeks getting it to, if not 100%,

15:35 then 97%.

15:36 Now we can take all of those lessons.

15:39 We can apply it to the work that Rob already did on Fizzy.

15:42 And then we can put out an official fully polished Fizzy CLI and skill.

15:47 And then after that, 100% I want this for, hey, I want this for my email.

15:52 I want my email to be tied together with my Fizzy when I'm using that or my

15:57 base camp

15:57 when I'm using that, bring all these things together and having this executive

16:04 agent that I can just tell to do stuff.

16:07 I mean, one of the things I use, hey, for a lot, for example, is travel and

16:11 having an agent

16:13 to be able to just go in and look these things up when I just want a piece of

16:17 information out of my email.

16:18 I don't want to draw through it.

16:19 I don't want the email.

16:21 I just want the fact that's in the email.

16:23 I'm really excited for having full accessibility for, hey, both on the email

16:29 side

16:29 but also on the calendar side and tying all these things together.

16:32 So we'll do it for all of it.

16:33 And I think anything going forward, this is going to be baked in.

16:36 This is going to be table stakes that your application is, agent accessibility

16:41 accessible,

16:42 both for the direct use with that application, but just as much because it

16:47 kind of plugs in to this broader ecosystem.

16:50 So many successful applications over the year Slack is a good example.

16:54 We're successful because they ended up with this ecosystem that was kind of

16:58 proprietary to Slack and integrations with it.

17:00 What the agent accessibility is doing is basically bringing that to everyone.

17:03 Like all those moats just come tumbling down because there's no specific

17:08 advantage

17:08 to just having something inside of one application.

17:11 In fact, the whole game here is that your agent can talk to anything you use,

17:17 can access anything you use, wherever your data is, it can move it back here or

17:23 everywhere and tie it all together.

17:24 That's super exciting.

17:25 OK, well, you can read more about what we're doing at Basecamp.com/agents.

17:31 This has been a production of 37 Signals.

17:33 You can find units and transcripts on our website at 37signals.com/podcast full

17:38 video

17:38 episodes on YouTube.

17:39 And if you question for Jason or David about a better way to work and run your.

17:43 What is the line?

17:47 Literally about to say that.

17:48 I was like, wait, I need an agent to say this for me.

17:52 You have a question for Jason or David about a better way to work and run your

17:56 business.

17:57 Leave us a voicemail at 37signals.com/podcast question.

18:01 Or you can send us an email to [email protected].

18:05 That is not.

18:05 Is that right?

18:06 You guys, that's it.

18:08 Email address, right?

18:09 I think it is.

18:10 Oh, my gosh.

18:11 Have an agent check it.

18:12 Literally, I need an agent to do the exit.

18:17 (upbeat music)

Love

· 2w

Codex CLI：在终端中与Codex协同工作

Codex #CLI 是 #OpenAI 推出的编程助手，可通过终端在本地运行。它能读取、修改并执行您设备上指定目录中的代码。该工具采用开源模式，基于Rust语言构建，确保运行速度与效率。

#Codex 已包含在 #ChatGPT Plus、Pro、Business、Edu及Enterprise套餐中。

https://developers.openai.com/codex/cli

中文 English

0:00 >> 嘿，你在做什么？

0:02 >> 我在找一个好的演示。

0:03 能让codecs修改的东西。

0:06 我们可以让这个小球多玩家化。

0:08 >> 听起来很酷，我们做吧。

0:11 >> codecs，C开始，第四次加油。

0:15 >> 大家好，我是Roma。

0:17 最近我们发布了GPT-5和GPT-5 codecs，

0:20 还对codecs CLI做了大量改进，

0:23 更好地利用

0:25 这些模型的自主编码能力。

0:28 今天我和Esau坐在一起，

0:30 他领导了CLI的大部分工作。

0:32 要不要给我们快速介绍一下？

0:33 >> 好的，我很乐意。我们有很多很酷的更新。

0:37 你可以用MPM或者Brew很容易地安装，

0:39 然后用你的chat GPT账号登录。

0:42 >> 这里你在终端，

0:43 只需输入codecs启动它。

0:46 >> 就这么简单。

0:47 于是我们说，为这个游戏制定一个多玩家计划。

0:52 >> 有趣的是，这个游戏是我们

0:54 发布的许多示例之一，

0:56 完全由GPT-5一条提示生成。

0:59 >> 是的。

0:59 >> 现在我们可以开始改进它。

1:01 它在思考的时候，你能讲讲

1:04 用的是哪个模型吗？

1:05 >> 这是GPT-5 codecs，

1:09 我们新的模型，

1:11 特别适合各种编码任务。

1:14 >> 它现在正在制定计划。

1:16 我看到它列出了要做的步骤。

1:19 >> 是的。

1:20 >> 你能详细说说吗？

1:21 >> 当然。按Ctrl+T进入转录模式，

1:24 可以看到很有用的东西，

1:27 比如思路链，

1:28 还有它写的具体代码。

1:31 >> 如果你不想看细节，

1:33 可以让它运行高级模式，

1:36 告诉你它在做什么。

1:37 >> 没错。

1:38 >> 它在做多玩家功能的时候，

1:41 你能打开另一个codecs给我们介绍一下你爱用的命令吗？

1:44 >> 当然。我特别喜欢模型切换器。

1:46 有时候一个模型做某些事，一个模型做另一些。

1:50 切换视图可以调整推理深度。

1:53 >> 因为新的GPT-5 codecs模型，

1:56 简单任务可以很快完成。

1:58 >> 没错。

2:00 >> 但是复杂任务，

2:01 codecs可以持续工作几个小时。

2:06 >> 那就是/模型命令，还有呢？

2:08 >> 审批功能很有用。

2:10 这是codecs沙箱功能的一部分，

2:12 非常酷，非常强大。

2:14 我们有三种模式，读写，

2:16 自动，和完全访问。

2:18 自动是默认，允许codecs

2:20 读取并修改当前目录内的文件。

2:24 >> 默认情况下它只在你的项目范围内操作，

2:29 不会影响你电脑里的其他东西。

2:32 >> 完全正确。如果你想用只读，

2:34 例如在Git仓库外运行，

2:36 或者只想做规划，

2:38 不希望codecs去编写修改代码。

2:40 >> 我们还有codecs继续功能，

2:43 可以从以前的会话恢复，超级方便。

2:47 >> 去看看多玩家游戏进度怎么样？

2:49 >> 看起来计划已经完成了。

2:53 那就让codecs开始执行吧。

2:56 >> 很好。

2:59 >> 我觉得很多人对codecs的认识有误，

3:02 除了写代码，它还能部署应用，

3:05 用于SRE工作。

3:09 比如出现bug，可以去查日志，

3:12 把分散的信息合并在一起。

3:15 它在这方面非常强大。

3:17 >> 游戏现在怎么样了？

3:20 >> 游戏应该可以用了。

3:22 >> 真正考验的时候是玩游戏了，

3:23 但我们先得部署它。

3:25 >> 我这次打算在Vercel部署这个应用。

3:28 用codecs --search命令

3:31 查找最新的Vercel文档。

3:35 >> 如果你想部署具体东西需要持久化，

3:38 查API最新变更，

3:39 都很有用。

3:41 >> 是的。

3:43 切换审批模式，

3:44 开启完全访问，

3:46 告诉它用Vercel命令行部署应用。

3:52 >> 很好，部署完成了。

3:53 >> 好的。

3:54 >> 试试看？

3:55 >> 去演示一下吧。

3:56 >> 如果你带笔记本，我可以用这台。

3:58 我要发链接给你。

4:00 >> 好的。

4:01 >> 给你。

4:02 应该收到了。

4:02 准备搜索。

4:06 开始。

4:06 天啊，太棒了。

4:09 我们真的同步了。

4:13 >> 是的，非常同步。

4:14 >> 太不可思议了，这都是实时的。

4:17 将会是最棒的，我不知道。

4:18 >> 你说得不错。

4:20 >> 啊，好的。

4:21 >> 总结一下，我们看到了什么？

4:25 我们看到CODEC CLI登录了你的chat GPT订阅，

4:29 开始修改你的游戏。

4:31 >> 是的。

4:32 >> 制定了实现完整多玩家游戏的计划。

4:35 >> 是的。

4:36 >> 快速看了几条命令，

4:37 更重要的是，

4:38 你用网络搜索获取互联网信息。

4:42 切换了审批模式。

4:44 我们部署了这个游戏，

4:45 现在能玩了。

4:47 >> 对。

4:47 >> 超简单。

4:48 这就是我做正规项目的流程，

4:52 跨多种语言，

4:54 跨多种框架，

4:56 跨多种项目。

4:57 >> 太棒了。

4:58 正如你所见，

4:59 我们在所有CODEC产品上

5:00 推出了大量改进，

5:02 让你无论在哪工作，

5:04 都能拥有这个AI队友，

5:06 这次就是直接在终端里。

5:09 我们迫不及待想看到你用CODEC CLI做出什么。

5:11 下次见。

5:40 You

0:00 >> Hey, what are you working on?

0:02 >> I'm trying to find a good demo.

0:03 Something that codecs can modify.

0:06 We could make this little ball thing multiplayer.

0:08 >> That sounds very cool. Let's do it.

0:11 >> codecs, C on one, take four more.

0:15 >> Hey, everyone, Roma here.

0:17 Recently, we ship GPT-5 and GPT-5 codecs,

0:20 and we've also released a ton of improvements to

0:23 codecs CLI to better harness

0:25 the agentic coding capabilities of these models.

0:28 Today, I'm sitting with Esau,

0:30 and who led a lot of this effort on the CLI.

0:32 Do you want to give us a quick tour?

0:33 >> Yeah, I'd love to. We have tons of really cool updates.

0:37 You can install it really easily with either MPM or

0:39 Brew and login with your chat GPT account.

0:42 >> So here, you're in your terminal,

0:43 and you just have to launch it by adding codecs.

0:46 >> That's all there is to it.

0:47 So we'll say, make a plan for making this game multiplayer.

0:52 >> What's funny is like this game was one of

0:54 the very many examples we shipped,

0:56 completely built by GPT-5 in one prompt.

0:59 >> Yes.

0:59 >> Now, we can start building up upon it.

1:01 So while it's thinking, tell us a little more about what's

1:04 happening, which model you're using here.

1:05 >> Yeah. So this is going to be GPT-5 codecs,

1:09 which is our new model,

1:11 and it's really good for any sort of coding task.

1:14 >> So here, it's like currently crafting the plan.

1:16 I see it's laying out the steps of what it's supposed to do.

1:19 >> Yeah.

1:20 >> Can you expand what's happening here?

1:21 >> Yeah, totally. So we can go into transcript mode with

1:24 control T, and that gives you things that are super useful,

1:27 like the chain of thought,

1:28 and sort of the exact code that it's doing.

1:31 >> If you're not interested into the whole details,

1:33 you can just let it run at the very high level,

1:36 telling you like what it's doing.

1:37 >> Yes, exactly.

1:38 >> Okay. So while it's working on this like a multiplayer feature,

1:41 why don't you open up a second codecs to give us maybe

1:44 a quick tour of some of your favorite commands?

1:46 >> Yeah. So I'm a huge fan of the model switcher.

1:50 You sometimes want to use one model for one thing,

1:53 one model for another. Slice view change the reasoning level.

1:56 >> Right. Because with the new GPT-5 codecs models,

1:58 the very simple task can go very fast.

2:00 >> Yes.

2:01 >> But for the more advanced one,

2:03 now codecs can work on for like up to hours at a time.

2:06 >> Okay. So that's slash model. What else?

2:08 >> Yeah. Approvals is really useful.

2:10 So this is where you kind of get into

2:12 the sandboxing features of codecs,

2:14 which are very cool, very powerful.

2:16 We have three modes, we have read only,

2:18 we have auto, and we have full access.

2:20 Auto is the default, and that allows codecs to

2:24 read files and make changes to files within the current directory.

2:29 >> So by default, it stays in the boundaries of your project.

2:32 It's not going to affect anything else on your laptop.

2:34 >> Exactly. And then if you want to be in read only,

2:36 that's kind of useful for, for example,

2:38 running outside of a Git repository,

2:40 or if you're like, I only care about planning,

2:43 I actually don't want codecs get distracted by trying to edit things.

2:47 And then we have codecs resume,

2:49 and that allows you to pick up from any previous session, super nice.

2:53 >> Why don't you go check back on the status of these multiplayer game?

2:56 >> Yeah, it looks like we've got a plan.

2:59 So why don't we tell codecs to do that?

3:02 >> Great.

3:03 >> So one of the things that I think is really interesting that people

3:05 sort of miss about codecs is that it's useful for these coding tasks,

3:09 but you can also deploy things with it.

3:12 You can use it for SRE type things.

3:15 You can figure out like, oh,

3:17 we're seeing these, but you know, this bug show up for our users.

3:20 Why is this showing up?

3:22 Go look at the logs,

3:23 take these disparate data sources, combine them.

3:27 It's surprisingly very, very, very good at that sort of thing.

3:31 >> How are we doing on the game?

3:32 >> Yeah, I think the game is probably good to go.

3:36 >> So it sounds like the moment of truth is to play the game,

3:38 but maybe before we need to deploy it.

3:40 >> Yeah, so what I'm going to say for this app,

3:42 let's maybe deploy it on Vercel.

3:45 And let's use codecs dash dash search

3:48 in order to tell it to look up the latest Vercel Docs.

3:53 >> Yeah, in case you want to deploy something very specific

3:55 and you need persistence,

3:57 or maybe you want to look up the latest changes of an API.

4:01 >> Yeah, exactly.

4:02 We should go to approval.

4:04 We should switch it to full access.

4:06 And then we'll tell it,

4:08 use the Vercel command line tool to deploy this app.

4:16 >> Cool, sounds like it's deployed.

4:17 >> Yeah, let's do it.

4:17 >> Should we try it?

4:18 >> Yeah, let's go to show.

4:19 >> I guess I can take over this laptop

4:21 if you want to bring yours.

4:23 I'm going to have to ping you the link.

4:25 >> Yeah.

4:26 >> There you go.

4:27 Should have it.

4:27 Ready to search.

4:31 Let's go.

4:32 Oh my god, this is awesome.

4:34 We are really in sync.

4:38 >> Yeah, super in sync.

4:39 >> Incredibles, this is all real time.

4:42 It's going to be the best at this, I don't know.

4:43 You're saying pretty good.

4:45 >> Ah, okay.

4:46 >> To wrap us up, what have we seen?

4:50 So we saw CODEC CLI logged into your chat GPD subscription,

4:54 starting to like change your game.

4:56 >> Yep.

4:57 >> Make a plan to implement like a full multiplayer game.

5:00 >> Yep.

5:01 >> We saw a quick tour of the commands,

5:02 but more interestingly,

5:03 you use web search to fetch information from the internet.

5:07 You change approval modes.

5:09 We deployed this game,

5:10 and we're now able to play it.

5:12 >> Yeah.

5:12 >> It's super easy.

5:13 This is the exact same flow that I use to do pretty serious stuff,

5:18 just across like a wide variety of languages,

5:20 a wide variety of frameworks,

5:21 wide variety of projects.

5:22 >> Amazing.

5:23 Well, as you can tell,

5:24 we're shipping a ton of improvements

5:26 across all CODEC surfaces.

5:27 So you can have this AI teammate

5:29 at your disposal wherever you work,

5:31 and in this case, right in the terminal.

5:33 And we can't wait to see what you build with CODEC CLI.

5:36 See you next time.

5:40 You

Moon

· 3w

黑曜石(Obsidian) 1.12 现已面向所有人开放！

- 黑曜石命令行界面

- 基础搜索功能

- 图片尺寸调整

- 自动清理未使用的图片

- 改进至富文本应用（如谷歌文档）的复制粘贴功能

- 原生 iOS 分享菜单

https://x.com/obsdmd/status/2027416335689638245 #Obsidian #CLI #笔记软件