Codex：28 天
连续发布

Day 26/ You can now easily switch between multiple accounts on mobile, and coming soon to desktop too. Next two days will be resets… banked… do with this what you may 👀.

https://help.openai.com/en/articles/20001068-using-multiple-chatgpt-accounts-on-web-and-mobile

Day 26/ 你现在可以在移动端轻松切换多个账号，桌面端也即将支持。接下来两天会是重置……攒下的……你们自己看着办吧 👀。

https://help.openai.com/en/articles/20001068-using-multiple-chatgpt-accounts-on-web-and-mobile

Day 25/

We are doubling all usage limits for all Pro 100/200/500 tiers and Business Premium, effective today.

We heard your kind feedback and won’t be reducing usage limits for Pro 200, so your Work and Codex usage will stay the same. We’re also going to continue offering extended limits for dots for now, and usage of your dot will still continue to be separate from your default usage.

And we'll of course also keep shipping better models and other efficiency improvements that increase your effective usage over time.

Day 25/

我们即日起将所有 Pro 100/200/500 档和 Business Premium 的用量上限全部翻倍。

我们听到了你们的善意反馈，不会降低 Pro 200 的用量上限，因此你的 Work 和 Codex 用量保持不变。我们目前也会继续为 dots 提供额外额度，并且你的 dot 用量仍与默认用量分开计算。

当然，我们也会继续发布更好的模型和其他效率改进，让你的有效用量随时间继续提高。

Day 24/ Text your dot just like anyone else. Makes it super easy to share/forward things, leave it voice notes or you can even go creative with "Hey Siri, text Iggy to <INSERT WILD REQUEST>" and sit back and relax.

Day 24/ 像给其他人发短信一样给你的 dot 发消息。这样分享或转发内容、给它留语音备忘都特别方便，你甚至可以更有创意地对 Siri 说「Hey Siri，给 Iggy 发短信：<INSERT WILD REQUEST>」，然后坐下来放松就好。

Day 23/ Much requested iCloud Main & Calendar plugins. Just kidding, today is a reset. Still much requested though!

Day 23/ 呼声很高的 iCloud Main 和 Calendar 插件。开玩笑的，今天是重置。不过呼声确实还是很高！

Day 22/ Terra is back!

Our first model that is significantly better at writing, personality and nuanced understanding of requests.

Packs a punch across the board, very good at computer use, and gives 2X more usage than 6.1 Sol across API and subscriptions.

Day 22/ Terra 回来了！

这是我们第一款在写作、个性，以及对请求的细腻理解上明显更强的模型。

它各方面都很能打，非常擅长计算机使用，并且在 API 和订阅中给出的用量是 6.1 Sol 的 2 倍。

Day 21/ Wonder what happens the remaining seven days. But today is a reset.

Day 21/ 想知道剩下的七天会发生什么。但今天是重置。

Day 20/ Rest and reset

Day 20/ 休息并重置

Day 19/ Small updates. Calls connect much faster for dots, changing reasoning in codex & work mid conversation does not invalidate cache anymore and a we've also updated the codex cli.

Day 19/ 一些小更新。dots 的通话连接快了很多；在 Codex 和 Work 里，对话中途更改推理不再使缓存失效。我们也更新了 Codex CLI。

Day 18/ Decisions API is GA, OpenResponses joined the Linux Foundation, we shipped some performance improvements and Uber is going all-in on codex & work. But yes… that’s a reset!

Day 18/ Decisions API 已正式发布，OpenResponses 加入了 Linux 基金会，我们发布了一些性能改进，Uber 也全面投入 Codex 和 Work。不过没错……这次是重置！

Day 17/ Bet you thought we forgot, but no, it’s reset day today.

Also good time to remind you to get Daybreak Blue access, it only takes 15 mins and you don’t want to have to do it in the middle of an incident.

Day 17/ 我打赌你以为我们忘了，但没有，今天是重置日。

这也是提醒你去获取 Daybreak Blue 访问权限的好时机，只要 15 分钟，你不会想在事故进行到一半的时候才去做。

Day 16/

You can now cache for 12h in the API and for logged in users across Codex & Work we keep cache forever and you don’t have any penalty for coming back to an old conversation or resuming after a few hours and are now guaranteed to hit the cache.

Day 16/

您现在可以在 API 中缓存 12 小时，对于通过 Codex & Work 登录的用户，我们会永久保留缓存，并且您不会因返回旧对话或在几个小时后恢复而受到任何惩罚，并且现在保证会命中缓存。

Day 15/ Nevermind, we're still cooking... and reset. Enjoy.

Day 15/ 没关系，我们还在做饭……然后重置。享受。

Day 15/ We're cooked

Day 15/ 我们完了（We're cooked）

Day 14/

Small quality of life improvement. You can now edit previous messages within a thread in the desktop app. Long time requested, and took way too long to get that one out.

Day 14/

一项小小的体验改进：现在可以在桌面应用中编辑同一对话内之前发送的消息了。大家期待这个功能很久了，我们也确实花了太长时间才推出。

Day 13/ Le limit reset

Day 13/ 额度重置

Day 12/

We’ve made improvements to Codex & Work that increase the effective usage you get. We achieved this by reusing context across subagents, keeping context cached longer, and improved request routing that allows us to increase cache hits.

Day 12/

我们对 Codex & Work 进行了改进，提高了您的有效使用率。我们通过跨子代理重用上下文、保持上下文缓存更长时间以及改进请求路由来实现这一点，从而使我们能够增加缓存命中率。

Day 11/

We've landed a series of changes and more compute to very significantly decrease the occurrence of the disruptive "Selected model is at capacity. Please try a different model". When it does happen, it should also eventually just continue by itself and not just block on it.

Let us know if you still see it out there in the wild and we'll take a look.

Day 11/

我们已经落地一系列改进，并增加了算力，以显著减少“所选模型已达到容量上限，请尝试其他模型”这类打断任务的提示。即使再次出现这种情况，任务最终也应该能自动继续，而不是一直卡住。

如果你在实际使用中仍然遇到这种情况，请告诉我们，我们会排查。

The reports of my reset button being lost are greatly exaggerated

Day 10/ Reset

关于我弄丢了重置按钮的传言被严重夸大了。

Day 10/ 重置

Day 9/

We've rolled out optimizations to how we store state on disk for the chatgpt & codex desktop app that should reduce the amount stored on disk by 60%. Small ship but we've heard enough feedback about power users running out of disk space.

Day 9/

我们针对 ChatGPT 和 Codex 桌面应用程序在磁盘上存储状态的方式进行了优化，这应将磁盘上存储的数量减少 60%。虽然船很小，但我们已经听到了足够多的关于高级用户磁盘空间不足的反馈。

Day 8/ Reset

Day 8/ 重置

Day 7/

We have increased default context length for GPT-6.1 Sol to 500k when used through Codex & Work, up from 272k or an ~ 80% increase.

We will go higher in the future, but it helps reduce occurrence of compactions and with tasks that require keeping a lot of context and nuance over periods of time. It was carefully tested and is the new sweet spot for most of our users. You can still override it if you want to be higher our lower, with maximum context length of GPT-6.1 Sol of 1M.

Day 7/

当通过 Codex & Work 使用时，我们将 GPT-6.1 Sol 的默认上下文长度从 272k 增加到 500k，即增加了约 80%。

未来我们会走得更高，但它有助于减少压缩的发生以及需要在一段时间内保留大量上下文和细微差别的任务。它经过仔细测试，是我们大多数用户的新选择。如果您想要更高或更低，您仍然可以覆盖它，GPT-6.1 Sol 的最大上下文长度为 1M。

Day 6/ Reset

Day 6/ 重置

Day 5 (dots edition)/

You can now create and text your dot entirely from the ChatGPT mobile app. Impressed so many created them via the desktop/web app previously. Time to scale!

Day 5 (dots edition)/

您现在可以完全通过 ChatGPT 移动应用程序创建 dot 并发送短信。令很多人印象深刻的是之前通过桌面/网络应用程序创建了它们。是时候扩大规模了！

Day 5/

Composer predictions in the desktop app. Often leads to a double take with how on point they are. Included in the Pro plans without consuming usage.

Day 5/

Composer 在桌面应用程序中进行预测。通常会让人怀疑他们的观点是否正确。包含在 Pro 计划中，无需消耗使用量。

Day 4/

We have improved steering to be instant, leading to the model now reacting much faster to adjustments you make, allowing you to course-correct direction in realtime and not have the model waste effort.

Also releasing GPT-6.1 Sol ultrafast. The two work very well together.

Day 4/

我们改进了即时转向，使模型现在对您所做的调整反应更快，让您可以实时修正方向，而不会让模型浪费精力。

同时发布 GPT-6.1 Sol 超快。两者合作得很好。

Day 3 (encore)/

We silently re-shipped codex cloud. It’s pretty good now

Day 3 (encore)/

我们默默重新发货了Codex Cloud。现在已经很好了

Day 3/

The big one is GPT-6 in Chat, but today is also a little celebration day with a new high of 40M active users across Codex and ChatGPT Work.

Loading a banked reset in everyone's paid accounts. See you again tomorrow!

Day 3/

最重要的是聊天中的 GPT-6，但今天也是一个小小的庆祝日，Codex 和 ChatGPT Work 的活跃用户创下了 4000 万新高。

正在把攒下的 reset 额度充进所有付费账户。明天再见！

Day 2.4/

Decisions API is live. We will use this ourselves to improve the experience for everyone in many fun ways. Realtime general classifier does open some great possibilities.

Day 2.4/

决策 API 已上线。我们将利用这一点以多种有趣的方式改善每个人的体验。实时通用分类器确实开启了一些巨大的可能性。

Day 2.3/

Never worry about remembering what you were saying with that colleague. Just talk your heart out and build up the context to load up into codex to get it all done.

Day 2.3/

不必担心记住您与该同事所说的话。只需说出你的心声并构建上下文以加载到 Codex 中即可完成所有工作。

Day 2.2/

OK this one is smaller, but we removed some friction for when building on the API. Happy building.

Day 2.2/

好吧，这个较小，但我们消除了在 API 上构建时的一些障碍。祝构建愉快。

Day 2.1/

We have made Auto-review free for all users signed in through a ChatGPT account. You can enable it in settings > permissions > auto-review. Auto-review improves upon the default sandbox setting that requires you to approve everything, which is prone to decision fatigue unless you spend a lot of time configuring specific rules.

It allows you to run long tasks while having a second agent review all actions taken by the primary agent. Its only goal is to prevent high-risk actions from being taken and to protect against unwanted actions that are not aligned with the original user intent. This Auto-review feature is now free and does not draw usage from your plan.

Day 2.1/

我们为所有通过 ChatGPT 帐户登录的用户免费提供自动审核。您可以在“设置”>“权限”>“自动审核”中启用它。自动审核改进了默认沙箱设置，默认沙箱设置要求您批准所有内容，这很容易导致决策疲劳，除非您花费大量时间配置特定规则。

它允许您运行长时间任务，同时让第二个代理审查主要代理采取的所有操作。其唯一目标是防止采取高风险操作，并防止与原始用户意图不一致的不需要的操作。此自动审核功能现在是免费的，不会占用您的计划的使用量。

Day 1/

We have optimized the default speed to be ~50% faster across GPT-6 Astra and GPT-6.1 Sol through the subscription across all our products and partners using Sign in With ChatGPT (including OpenCode, Pi, Amp, Devin, ...).

No changes needed on your end and this should be felt within the next two hours.

Day 1/

通过使用“使用 ChatGPT 登录”（包括 OpenCode、Pi、Amp、Devin 等）订阅我们的所有产品和合作伙伴，我们已将 GPT-6 Astra 和 GPT-6.1 Sol 的默认速度优化了约 50%。

您无需进行任何更改，并且应该会在接下来的两个小时内感受到这一点。

Over the next 28 days, each day we’ll either ship one thing that is a clear improvement and relevant for most codex/work users or ship a full reset. Let the improvements begin.

在接下来的 28 天里，每天我们要么发布一项明显改进且与大多数 Codex/工作用户相关的内容，要么发布完全重置的内容。让改进开始吧。