Unbelievable excited for what’s coming together. Tomorrow is feeling codexy
对正在汇聚成形的一切，简直兴奋得难以置信。明天感觉会很 codexy
TS
每条推文 hover 显示单独 ▶
ChatGPT Work => ChatGPT HelpMeWithEverything?
ChatGPT Work => ChatGPT 帮我搞定一切？
[1]
10M! New day, new usage reset for paid users of Codex and ChatGPT Work. Lands in the next hour. Enjoy.
1000 万！对于 Codex 和 ChatGPT Work 的付费用户来说，新的一天，新的使用量重置。将在接下来一小时内上线。尽情享用。
Never a dull moment when you work at OpenAI. Absolutely incredible place.
在 OpenAI 工作时刻都不会无聊。这里绝对是个令人难以置信的地方。
I was so inspired reading all the DMs on how folks here use ChatGPT Work. Let’s try something else that will make the team smile. What’s a time you saw ChatGPT have a deeply positive impact on your or someone’s life?
读到大家发来的私信，讲述这里的人如何使用 ChatGPT Work，我深受启发。我们再来试点别的，也让团队会心一笑。有没有哪一次，你看到 ChatGPT 对你或他人的生活产生了非常积极而深远的影响？
What I just dictated into ChatGPT Work > Okay, so I received a lot of DMs for, I did a call out for ChatGPT Work, basically early access beta group. I want you to go through all my DMs on Twitter and then just take all of them that mention ChatGPT Work. It's like a lot of them, thousands, and put them all in a spreadsheet. What I want in the spreadsheet is the name, I want the link to the the DM, so I can go back to it quickly. I want the post that they did, but remove any new lines, so it's just in a single cell. And then I want a column which is basically your assessment of what they're doing, right? So for example, if it's like sales, put sales, if it's marketing, put marketing, if it's design, put design. Come up with your own taxonomy for how to classify their work. I expect the taxonomy to have like, you know, roughly 8 to 12 labels maybe, total. And then also put a rating for, like, they normally have to describe what they're currently doing with ChatGPT Work, use that to put a rating in the fifth column on how sophisticated their workflow already is. We're gonna be selecting a cohort of different people of different levels of sophistication, so we're gonna be like taking, you know, maybe like a couple dozens from like, a high level of sophistication, we're gonna take in the middle of a cohort, and then like low level of sophistication, so we have good representation and can test new features and get good feedback from a diverse group at different levels of adoption. So create that spreadsheet, go through all my DMs. Good luck!
我刚刚口述给 ChatGPT Work 的内容 > 好的，我收到了很多 DMs，因为我发起了一个关于 ChatGPT Work 的征集，基本上是面向 early access beta group（抢先体验测试组）的。我希望你把我在 Twitter 上所有的 DMs 都过一遍，然后把所有提到 ChatGPT Work 的都整理出来。数量很多，成千上万条，把它们全部放进一个 spreadsheet（电子表格）里。我希望表格里有姓名、DM 的链接，这样我可以很快回去查看。我还想要他们发的那条内容，但要去掉所有换行，让它只占一个单元格。然后我还想要一列，基本上是你对他们在做什么的判断，对吧？比如如果是 sales，就填 sales；如果是 marketing，就填 marketing；如果是 design，就填 design。你自己设计一套 taxonomy（分类体系）来给他们的工作分类。我预计这个 taxonomy 总共大概有 8 到 12 个标签。然后还要加一个评分，因为他们通常需要描述自己当前如何使用 ChatGPT Work，你要根据这个，在第五列里给出一个评分，判断他们现有 workflow（工作流）已经有多成熟。我们会挑选一个 cohort（群组），包含不同成熟度水平的人，所以我们会从高成熟度里选大概几十个，从中等水平里选一批，再从低成熟度里选一些，这样就能有良好的代表性，测试新功能，并从不同采用阶段、不同水平的多样化人群那里获得高质量反馈。所以，把这个 spreadsheet 做出来，把我所有 DMs 都过一遍。祝你好运！
My job is basically delegating to ChatGPT Work now. Can't stop using dictation and have it do everything
我现在的工作基本上就是把事情委派给 ChatGPT Work。完全停不下来，一直在用语音口述，然后让它把所有事情都做掉。
ChatGPT Work is for ✅ Creating and hosting sites ✅ Managing your emails for you ✅ Summarizing mountains of documents ✅ Creating top-notch docs, sheet and slides Already in your mobile app or on included in Plus, Pro, Business and Enterprise plans
ChatGPT Work 用于 ✅ 创建并托管网站 ✅ 帮你管理电子邮件 ✅ 总结成堆的文档 ✅ 创建高质量的 docs、sheet 和 slides 已经在你的 mobile app 中可用，或者已包含在 Plus、Pro、Business 和 Enterprise 套餐中
And transitively might also have reset other rate limits out there. Let's see. You're welcome if so.
而且通过传递影响，可能也顺带把其他地方的一些 rate limits（速率限制）重置了。看看吧。如果真是这样，那不客气。
Oops... I did it again. Enjoy reset usage limits for all paid users for Codex and ChatGPT Work. Super grateful for an incredible team who is iterating at lightspeed and keeping the infra up as we scale faster than ever. Enjoy the weekend!
Oops... I did it again. Codex 和 ChatGPT Work 的所有付费用户都可以享受已重置的 usage limits（使用限额）了。非常感谢这个了不起的团队，在我们以前所未有的速度扩张时，他们依然以光速迭代，并让基础设施保持稳定运行。周末愉快！
GPT-5.6 Sol confirmed to be an extremely good model
已确认 GPT-5.6 Sol 是一个非常优秀的模型
Evening! We’ve gotten lots of great feedback on the new ChatGPT desktop app (which we didn't get totally quite right on the first try), and as a result, we've made some changes. 1/ ChatGPT conversation history and projects are now visible in the sidebar. Also, your Chat and Work history now sync across web, mobile, and desktop. Local tasks still stay on your computer. 2/ You can now easily switch between Chat and Work modes inside ChatGPT on desktop, which is now also consistent with how it shows on web and mobile. 3/ Nothing is changing for users on Codex mode. It's still the OG and best at what it does. And overall we're continuing to fix paper cuts and improve performance, reliability, and efficiency. Keep up the feedback, hope you like the updates!
晚上好！我们收到了很多关于新版 ChatGPT desktop app 的优秀反馈（第一次尝试时我们确实没有把它完全做好），因此我们做出了一些调整。1/ 现在你可以在侧边栏看到 ChatGPT 的对话历史和项目。与此同时，你的 Chat 和 Work 历史记录现在会在 web、mobile 和 desktop 之间同步。local tasks 仍然只保留在你的电脑上。2/ 你现在可以在 desktop 版 ChatGPT 中轻松切换 Chat 和 Work 模式，这也与它在 web 和 mobile 上的显示方式保持一致。3/ 对 Codex mode 的用户来说没有任何变化。它仍然是 OG，而且在它擅长的事情上依然是最好的。总体而言，我们会继续修复这些小毛病，并改进性能、可靠性和效率。请继续提供反馈，希望你喜欢这些更新！
We've had no 5h limit in Codex plus and pro for a few days. Do you think it is better or are you finding it difficult to manage the usage included in the weekly limit effectively? If we were to make this different, what should it look like in an ideal world?
这几天里，我们在 Codex plus 和 pro 中没有设置 5 小时限制。你觉得这样更好吗，还是说你发现很难有效管理每周限额中包含的使用量？如果我们要把这件事改成另一种方式，在理想情况下它应该是什么样子？
On file deletions. We’ve investigated a handful of reports where GPT-5.6 unexpectedly deleted files. What we have found is that this most commonly occurs when: - Full access mode is enabled and codex is run without sandboxing protections, including without auto review being enabled - The model attempts to override the $HOME env var to define a temporary directory. - The model makes an honest mistake and mistakenly deletes $HOME instead. This is of course not how we want the system to behave, even when a user operates the model in full-access mode without the safeguards of our sandbox or without using auto review which checks for these kinds of high risk actions and rejects them. We are taking steps to mitigate this risk including by updating the developer message, guiding more users towards safer permission modes, and adding additional harness safeguards. Even though this happens extremely rarely, we’ll share a detailed post-mortem in the coming days that goes into more details and what we are doing to minimize risks further.
关于文件删除。我们调查了少量关于 GPT-5.6 意外删除文件的报告。我们发现，这种情况最常见于以下情形：- 启用了 full access mode，并且运行 codex 时没有 sandboxing（沙箱隔离）保护，包括没有启用 auto review - 模型尝试覆盖 $HOME env var（环境变量）来定义一个临时目录。- 模型出现了无心的错误，结果误删了 $HOME。本来这当然不是我们希望系统表现出来的行为，即使是在用户以 full-access mode 运行模型、且没有使用我们的 sandbox 防护，或者没有启用会检查这类高风险操作并予以拒绝的 auto review 时，也是如此。我们正在采取措施降低这项风险，包括更新 developer message、引导更多用户使用更安全的权限模式，以及增加额外的 harness safeguard（运行框架保护措施）。尽管这种情况极其罕见，我们仍会在未来几天分享一份详细的 post-mortem（事后复盘），更详细说明发生了什么，以及我们正在采取哪些措施来进一步降低风险。
Now that we merged ChatGPT and Codex, what should we merge next? What's the double or nothing move.
现在我们已经把 ChatGPT 和 Codex 合并了，接下来还应该合并什么？那个要么翻倍、要么归零的下一步动作是什么？
Embarrassment of riches. But looks like we might hit 9M soon. Should we reset the ChatGPT Work and Codex usage again or give it some space?
幸福的烦恼。 但看起来我们可能很快就会到 9M。我们是该再次重置 ChatGPT Work 和 Codex 的使用量，还是先给它一点空间？
Or… what if we gave you $100 in Codex credits if you tell us what you love about GPT-5.6 Sol or why you switched? Tweet it, claim your gift, enjoy more usage. First 10k get the free tokens!
又或者……如果你告诉我们，你喜欢 GPT-5.6 Sol 的哪些地方，或者你为什么改用了它，我们就送你 $100 的 Codex credits（额度）怎么样？发条 Tweet，领取你的赠礼，享受更多使用量。前 10k 可获得免费 tokens（代币）！
Here you are! Thinking I am about to announce a reset. But no. I’m just scrolling twitter and looking for feedback on ChatGPT Work. What should we improve?
你来了！还以为我要宣布重置，对吧？但并不是。我只是在刷 twitter，看看大家对 ChatGPT Work 的反馈。我们应该改进什么？
Tomorrow might be 8M active user celebration day. Just saying
明天可能会是 800 万活跃用户的庆祝日。只是随口一说
Updates for Codex and ChatGPT Work users. No nerfing, only good stuff! - We have landed inference optimizations and are passing down savings to all the subscriptions for GPT-5.6 Sol. That should result in around 10% more usage on its own. - We noticed that by changing the context size limit in the product to 372k for GPT-5.6 Sol, up from 272k for GPT-5.5, it resulted in more usage being charged than intended. We have reverted to 272k and will work to roll back out to 372k in the days to come. You should notice that usage drains significantly less after this change. - To understand where the extra usage was coming from, we ran some experiments where reasoning efforts were changed (referred to as juice values under the hood) and have reverted this. - There is slightly more usage of multi-agent than intended in high and xhigh reasoning effort, we are fixing this going forward. Also fixing a small other thing we noticed with auto-review where we can be more efficient. And we continue to have the 5h limit temporarily not apply. Enjoy the rest of the weekend!
面向 Codex 和 ChatGPT Work 用户的更新。没有削弱，只有好消息！——我们已经完成了推理（inference）优化，并把节省下来的成本回馈给所有使用 GPT-5.6 Sol 的订阅方案。这本身应该就会带来大约 10% 的额外使用量。——我们注意到，把产品中的上下文（context）大小限制从 GPT-5.5 的 272k 提高到 GPT-5.6 Sol 的 372k 后，导致计费的使用量高于预期。我们已经恢复到 272k，并会在未来几天里继续推进重新上线 372k。你应该会注意到，这次调整后，使用量消耗明显减少。——为了弄清额外使用量是从哪里来的，我们做了一些实验，调整了 reasoning effort（底层内部称为 juice values），现在已经回退了这一改动。——在 high 和 xhigh 的 reasoning effort 下，multi-agent（多 agent）使用量略高于预期，我们接下来会修复这个问题。我们也在修复另一个在 auto-review 上注意到的小问题，这样可以更高效一些。另外，5 小时限制目前仍会暂时不生效。祝大家周末剩下的时间愉快！
Team, Edu, ... and any other paid subscription too. Quite simple really.
Team、Edu，……以及其他任何付费订阅也都包括在内。其实很简单。
Rest assured that GPT 5.6 Sol will stay in the ChatGPT subscription you pay for. Including Go, Plus and Pro subscriptions. At least until we ship an even better model.
请放心，GPT 5.6 Sol 会继续保留在你付费订阅的 ChatGPT 中。包括 Go、Plus 和 Pro 订阅。至少在我们推出一个更好的模型之前都会如此。
At different times you complained about speed, code slop, frontend quality, ... With each release we improve and GPT 5.6 Sol is ✅Fast and token efficient ✅Hardcore at back-end dev ✅Great at front-end ✅Does not use useEffect everywhere What is next?
你们曾在不同的时候抱怨过速度、代码粗糙、前端质量，…… 而随着每一次发布，我们都在改进，GPT 5.6 Sol 现在是：✅速度快且 token（令牌）效率高 ✅后端开发非常硬核 ✅前端表现很强 ✅不会到处都用 useEffect。接下来是什么？
If you aren't yet bold enough to install the Codex app, you can stay in the presence of your orange crab and point it at GPT 5.6 Sol. Takes 5 minutes. Kudos to Theo for explaining one of the ways to get this done. Step 1: Install CLIProxyAPI Step 2: Connect Step 3: Define following alias and enjoy claudex ``` alias claudex='CLAUDE_CODE_SUBAGENT_MODEL=gpt-5.6-sol \ CLAUDE_CODE_ALWAYS_ENABLE_EFFORT=1 \ CLAUDE_CODE_MAX_TOOL_USE_CONCURRENCY=3 \ ENABLE_TOOL_SEARCH=false \ claude --model gpt-5.6-sol' ``` If this gets blocked, I owe you a reset.
如果你还没大胆到去安装 Codex app，你也可以继续待在你的 orange crab 身边，把它指向 GPT 5.6 Sol。只要 5 分钟。也要感谢 Theo 解释了实现这一点的方法之一。第 1 步：安装 CLIProxyAPI 第 2 步：连接 第 3 步：定义下面这个 alias（别名），然后享受 claudex ``` alias claudex='CLAUDE_CODE_SUBAGENT_MODEL=gpt-5.6-sol \ CLAUDE_CODE_ALWAYS_ENABLE_EFFORT=1 \ CLAUDE_CODE_MAX_TOOL_USE_CONCURRENCY=3 \ ENABLE_TOOL_SEARCH=false \ claude --model gpt-5.6-sol' ``` 如果这个方法被封了，我欠你一次 reset（重置）。
To celebrate the launch of GPT-5.6 Sol, we will reset the rate limits again (twice) across ChatGPT Work and Codex over the next 24 hours. We want you to have the time to truly try ambitious tasks and get the hang of it. Happy exploring!
为庆祝 GPT-5.6 Sol 发布，我们将在接下来的 24 小时内再次（两次）重置 ChatGPT Work 和 Codex 的 rate limits（速率限制）。我们希望你有足够时间真正尝试一些有野心的任务，并熟悉它的用法。祝你探索愉快！
Enjoy a full reset of your usage limits for ChatGPT Work and Codex. Propagating in the next hour. @_rajanagarwal just joined to work on model research and push on coding capabilities. You can thank him for pressing the button today.
请享受一次针对 ChatGPT Work 和 Codex usage limits（使用额度）的完整重置。将在接下来一小时内逐步生效。@_rajanagarwal 刚加入团队，将参与 model research（模型研究）并推进 coding capabilities（编码能力）。今天这个按钮就是他按下去的，你可以感谢他。
If you happened to have used your previous reset in the few hours before and didn't go through your usage, do not worry, you will get more manual resets after we conclude the investigation.
如果你恰好在前几个小时里已经用掉了你之前的 reset，但并没有真正消耗掉你的使用额度，也不用担心；等我们结束调查后，你还会获得更多手动 reset 的机会。
As we are still investigating, I have reset everyone's Codex usage limits. This is a hard reset given some users had stacked up to three banked resets already that they can apply on their own schedule. Funnily enough, this week at OpenAI is called the RESET week, which is meant for folks to relax a bit. However it will be a different kind of RESET week. Enjoy.
由于我们仍在调查中，我已经重置了所有人的 Codex 使用额度限制。这是一次 hard reset，因为有些用户之前已经累计存下了最多三个可自行按自己的时间安排使用的 reset。说来也巧，OpenAI 这周正好叫作 RESET week，本来是让大家稍微放松一下的。不过看来这将会是另一种意义上的 RESET week。请享受吧。
Codex team is in a warroom on a Sunday combing through logs and checking whether there is anything that could lead to increased usage drains for some users. Taking it very seriously and won't rest until we get to the bottom of it.
Codex team 正在周日进驻 warroom，仔细梳理日志并检查是否存在任何可能导致部分用户使用额度消耗加快的问题。我们非常严肃地对待这件事，在彻底查明原因之前不会停下来。
Talking to your plants isn't weird anymore. You can just codex things.
跟你的植物说话已经不再奇怪了。你可以直接把事情 codex 掉。
Tons of improvements landed in Codex. - Handles super long threads smoothly. - Hoverable navigation rail for previewing and jumping between turns that feels just right. - Settings search covers more controls, with clearer appearance and host-filtering options and easier-to-find custom-provider settings. - Zoom-level changes no longer misalign tooltips, dialogs, menus, selection bubbles, drag previews, or autocomplete. - Copying into Slack preserves Markdown formatting such as bullets, bold text, code, and links; and large text pastes no longer freeze the UI. - And most importantly: a dedicated Pets panel.
Codex 已上线大量改进。- 现在可以流畅处理超长 thread（线程/对话串）。- 新增可悬停的导航侧栏，用于预览并在各轮对话之间跳转，手感恰到好处。- Settings 搜索现在覆盖更多控制项，并提供更清晰的外观与 host 过滤选项，以及更容易找到的自定义 provider 设置。- 调整缩放级别后，tooltip、dialog、menu、selection bubble、drag preview 或 autocomplete 不会再出现错位。- 复制到 Slack 时会保留 Markdown 格式，例如项目符号、粗体文本、代码和链接；而且粘贴大段文本也不再让 UI 卡死。- 以及最重要的是：专属的 Pets 面板。
We are giving all Codex users a usage reset on the house. Should be showing in your accounts in the next few hours. We have applied some mitigations, but our investigation hasn't shown users being impacted at large. We are continuing to monitor the situation.
我们将免费为所有 Codex 用户重置一次使用额度。该更新应会在接下来的几小时内显示在你们的账户中。我们已经采取了一些缓解措施，但我们的调查尚未显示有大量用户受到影响。我们将继续监控这一情况。
[1]
[1]
February 2nd was the release of the Codex App. You can see what it did to adoption outside of engineering. 👀 @ajambrosino
2 月 2 日是 Codex App 的发布时间。你可以看到它对 engineering 领域之外的采用情况产生了什么影响。👀 @ajambrosino
At times our internal Slack is at least as fun as twitter.
有时候，我们内部的 Slack 至少和 twitter 一样有意思。
[1]
Let's Patch The Planet. Updates to codex security and a new GPT-5.5-Cyber. A day of celebration for cyber defense acceleration.
让我们一起修补地球。codex 安全更新，以及全新的 GPT-5.5-Cyber。这是为 cyber defense（网络防御）加速而庆祝的一天。
[1]
Now that you can bank usage resets in Codex. Are you a hoarder or do you use them without breaking a sweat? How do you think about them?
现在你可以在 Codex 里把 usage resets（使用次数重置）攒起来了。你是那种喜欢囤着的人，还是会毫不心疼地直接用掉？你是怎么看待它们的？
What should we improve in the Codex app. What's not delightful?
我们应该在 Codex app 里改进什么？有哪些地方还不够令人愉悦？
We built the Codex App with models that were okayish at front-end. Wait to see what we can do when we finally improve front-end capabilities significantly in our models. That day will be something.
我们构建 Codex App 时，使用的模型在 front-end（前端）方面还算凑合。等着看吧，当我们最终把模型的 front-end 能力显著提升之后，我们能做出什么。那一天会很不一般。
Some tokens work harder than others. Some of the most valuable ones are found in the Codex app.
有些 token（令牌）比其他 token 更“卖力”。其中一些最有价值的 token，就能在 Codex app 里找到。
Late to this one, but follow @danshipper for S-tier codex tips. These days I spend more time in the codex app than all other apps combined on my Mac.
这条说晚了，不过想看 S-tier 的 codex 使用技巧，就去关注 @danshipper。最近这些天，我在 codex app 里花的时间，比我在 Mac 上其他所有 app 加起来还多。
Remote / local handoff in Codex! Removing boundaries one at a time. When you let the model be in the driver seat, you actually need less infrastructure.
Codex 里的 remote / local handoff（远程 / 本地交接）来了！我们正一次次拆掉这些边界。当你让模型坐上 driver seat（主导位置）时，你实际上需要的基础设施反而更少。
Dearest gentle codexer. We did a sneaky double reset. Not only do you get a full reset on us. But you are also getting one into the reset bank to use at your own leisure. Enjoy
最亲爱的温柔 codexer。我们偷偷做了一次双重重置。你不仅会从我们这里得到一次完整重置，而且还会额外获得一次存入 reset bank 的重置，供你在自己想用的时候随意使用。请享用
Reminder that you can use the Codex App, CLI and SDK with any open source model, not just with OpenAI models.
提醒一下，你可以将 Codex App、CLI 和 SDK 与任何开源模型一起使用，而不只是与 OpenAI 模型一起使用。
Bim bada boum. I am in France for the week and we are rolling out all the most exciting Codex features across Europe. Coincidence or did the team think I wasn't able to be productive otherwise?
Bim bada boum。我这周在 France，而我们正在整个 Europe 推出所有最令人兴奋的 Codex 功能。这是巧合，还是团队觉得不然我就没法高效工作？
This was fixed. You know what's coming 👀 Give us 24 hours to reset the Codex rate limits across all plans.
这已经修好了。你知道接下来要来的是什么 👀 给我们 24 小时，在所有 plan 上重置 Codex 的 rate limit（速率限制）。
Oy. We are aware that some Codex users are experiencing high error rates with "model at capacity" and are working to bring things back to being stable.
Oy。我们注意到，一些 Codex 用户正在遇到较高的错误率，并出现 “model at capacity” 的问题；我们正在努力让系统恢复稳定。
Codex can see and set its own /goal. Everything we build, we build also as a tool for the agent. This is a generalization of meta prompting, where you let the agent set its own task based on your intent.
Codex 可以查看并设定它自己的 /goal。我们构建的一切，也都同时被构建成供 agent 使用的工具。这是对 meta prompting 的一种泛化：你根据自己的意图，让 agent 自行设定它的任务。
Hi, I'm Tibo and I just discovered Codex. AMA
嗨，我是 Tibo，我刚刚发现了 Codex。AMA（Ask Me Anything，尽管提问）。
Heard your (amusing) feedback that it was at times annoying to receive a reset of your Codex usage without warning. Next time we press the button you will get to choose when it actually applies. Happy codexing.
我们听到了你那些（挺逗的）反馈：在没有任何提醒的情况下，你的 Codex 使用额度被重置，有时确实让人很烦。下次我们按下这个按钮时，你将可以自己选择它具体何时生效。祝你愉快地使用 Codex。
Codex 🤟Ona Beyond excited to work with Johannes and team to build the future.
Codex 🤟Ona 非常兴奋能与 Johannes 及其团队合作，共同构建未来。
Can confirm we saw a strong spike in growth of token consumption for Codex over last 48 hours. Unusual when we don't launch something.
可以确认，在过去 48 小时里，我们看到 Codex 的 token 消耗量增长出现了明显激增。尤其是在我们没有发布任何新东西的情况下，这很不寻常。
Welcome Clint and Michael! Incredibly excited to see what we do together to contribute to the cybersecurity field and accelerate defenders across the globe. It's time to build.
欢迎 Clint 和 Michael！非常期待看到我们接下来如何一起为 cybersecurity 领域作出贡献，并帮助全球的防御者加速行动。现在是时候开始构建了。
I would like to claim my 1% of royalty fees.
我想领取我那 1% 的 royalty fees（版税费用）。
Do you use codex /goal occasionally or as your main way to get things done?
你使用 codex /goal 是偶尔用，还是把它当作完成事情的主要方式？
Playing codex like an orchestra. One /goal at a time.
像指挥一支管弦乐队一样使用 codex，一次处理一个 /goal。
Not clear from the image, but the codex dial goes to 11.
从这张图里看得还不太清楚，但 codex 的刻度盘可以开到 11。
I have a new kind of big button that I can press for Codex. Over the next 100 days, we will select one person per day who does impressive or incredibly useful work with Codex and give them 10X usage limits for a month to see what they can do with it. First one tomorrow.
我现在有了一个可以为 Codex 按下的新型“大按钮”。在接下来的 100 天里，我们每天都会选出一位用 Codex 做出令人印象深刻或极其有用成果的人，给他们一个月 10 倍的使用限额，看看他们能用它做到什么。第一位从明天开始。
Better memory = Shorter prompts = More utility per token
更好的 memory（记忆）= 更短的 prompt（提示词）= 每个 token（令牌）带来更多效用
You can use codex within your own programs using the Python SDK. It's awesome. Built by @ah20im and friends ``` pip install openai-codex ```
你可以在自己的程序中通过 Python SDK 使用 codex。非常棒。这是由 @ah20im 和伙伴们构建的。``` pip install openai-codex ```
We're fixing a codex bug today that was causing us to undercount tokens being served to some Pro and Plus accounts by a small amount. This impacted < 15% of accounts. Not the kind of bug you want us to fix, but didn't want to do this silently and thought you should know.
我们今天正在修复一个 codex bug，它此前会导致我们对部分 Pro 和 Plus 账户所提供的 token 数量少量低估。此次影响波及的账户不到 15%。这不是那种你会希望我们去修复的 bug，但我们不想悄悄处理掉这件事，觉得你应该知道。
Lots of little vectors at OpenAI all pointing in the same direction. Excited to see it all add up and come together over the coming weeks.
OpenAI 里许多小小的 vector（向量）都在指向同一个方向。很期待看到在接下来的几周里，这一切逐步累积并汇聚成形。
Hi. Over the last 24 hours we had three separate small incidents that affected Codex reliability. Those are three too many and we are taking active steps for them to not reproduce. I have reset usage limits for Codex across all paid plans. May the tokens flow again.
你好。在过去 24 小时里，我们发生了三起彼此独立的小事故，影响了 Codex 的可靠性。三起实在太多了，我们正在积极采取措施，防止它们再次发生。我已经为所有付费方案重置了 Codex 的使用限制。愿 token（令牌）再次流动起来。
ChatGPT Whether you understand the name or not. It's here to stay. It's the past, the present, the future. Synonym with AI, soon synonym with agents. Much to build.
ChatGPT，不管你是否理解这个名字。它都会一直存在。它是过去，是现在，也是未来。它是 AI 的同义词，很快也会成为 agents 的同义词。还有很多东西可做。
[1]
Tons of goodies for use of codex for day to day work. If you are on a business plan you can now host and share websites, we launched vastly improved plugins and skills for broad roles and you can give feedback to your agent through visual annotations in docs, slides, sheets and more.
关于将 codex 用于日常工作的功能，这次带来了大量实用更新。如果你使用的是 business plan，现在你可以托管并分享网站；我们还发布了大幅改进的 plugins 和适用于广泛角色的 skills；此外，你还可以在 docs、slides、sheets 等中通过可视化批注向你的 agent 提供反馈。
The Codex usage limits have been reset for all paid ChatGPT subscriptions. You should be back to 100% weekly and 100% hourly limits. Let the tokens do incredible things today and have fun.
所有付费 ChatGPT 订阅的 Codex 使用限额现已重置。你的每周限额和每小时限额都应已恢复到 100%。今天就让 token（令牌）去完成一些不可思议的事情吧，玩得开心。
Five million users would agree. Resetting the limits tomorrow morning to celebrate. Time to go /fast
五百万用户都会同意。明天早上会重置限制来庆祝一下。是时候 /fast 起来了
What’s something we haven’t fixed in codex for a while and that’s plain annoying?
codex 里有什么问题是我们有一阵子还没修、而且明显很烦人的？
When we go from GPT-5.0 -> GPT-5.1 -> ... -> GPT-5.5, the number incrementing goes with improvements in capabilities and token efficiency (which translates to speed gains). With GPT-5.5 our best model yet. A simple strategy that we would like to continue.
当我们从 GPT-5.0 -> GPT-5.1 -> ... -> GPT-5.5 演进时，版本号的递增对应着能力提升和 token（词元）效率提升（这会转化为速度增益）。GPT-5.5 将会是我们迄今最好的模型。一个我们希望继续坚持的简单策略。
I looked at a number today on a codex dashboard and it made me happy. More news about the number soon. 👀 Thanks to everyone who keeps adopting codex. We are still early. So early.
今天我在一个 codex dashboard 上看到了一个数字，它让我很开心。关于这个数字，很快会有更多消息。👀 感谢所有持续采用 codex 的人。我们仍然还很早。非常早。
Do you still trust benchmarks or do you just listen to your friends? What makes you try a new model?
你现在还相信 benchmarks（基准测试）吗，还是只听朋友的？是什么让你去尝试一个新的 model（模型）？
The world is more fun with codex glasses
有了 codex glasses，这个世界会更有趣。