Pickful: Your Shared Crypto Community!

话题广场

Love

· 3h

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

· 1M

我在 OpenAI 用 Codex 自动化了我的研究，花了 1 万美元

作者每月花费1万美元使用AI编程助手Codex,让它持续记录改进工作流程、进行大规模研究和数据分析。这种AI驱动的知识整合绕过了传统组织的协调开销,可能从根本上提升组织效率。

Moon

· 1M

目前，GitHub上4%的公开提交由 #Claude Code完成。

按当前趋势推算，我们预计到2026年底，Claude Code将占每日提交总量的20%以上。

就在你眨眼的功夫，AI已席卷整个软件开发领域。 #ai #codex

https://x.com/dylan522p/status/2019490550911766763

Moon

· 1M

链上外汇：一个被忽视的市场

链上外汇备受关注，因美元稳定币占比高达99.7%，非美元稳定币稀缺。链上外汇有望颠覆传统低效、多中介的FX市场，尤其在高成本的长尾货币对中具先发优势。

2026年加密货币基础设施展望

Love

· 1M

#Clawdbot 创作者最爱 #Claude #Opus，但编程最强是旧 #Codex，因其高效少干预。引申AI岔路：通用全才 vs 领域专才？

Love

· 1M

OpenCode Zen：针对编码代理的精选模型网关（零加价定价）

OpenCode Zen 是专为编码代理优化的模型网关，提供经基准测试的 Claude、GPT、Gemini 等模型。定价透明零加价（Claude Opus 4.5 $5/$25、Sonnet 4.5 $3/$15），支持缓存省钱、团队管理、BYOK。集成简单，适合高频编码使用，比直接官方 API 更稳定高效。

Moon

· 3M

GPT-5.1现已在OpenAI API中上线

我们在 API 中发布了 GPT-5.1 ，这是 GPT-5 系列的下一个模型，旨在平衡智能和速度，涵盖代理和编码任务。