当前速蹬窗口 官方预告后,到额度重置前
等待官方预告,持续监控中。
监控 Codex 重置窗口、预测重置概率,并追踪模型智商状态。
等待官方预告,持续监控中。
低概率:刚完成补偿重置,短期进入冷却。
大模型与小加一公众号
Codex 雷达蹬友群
只在官方速蹬窗口开启时发邮件;预测信号不会触发提醒。
按北京时间每日最后一次预测聚合,读的是未来 24-48 小时趋势;窗口开启当天概率偏低是正常的,括号内是该窗口持续时长,0分钟表示即时重置。
6月5日:5/12 通过,基线 8/12
开发中的实验性功能:使用固定 DeepSWE 12 题探针的通过率折算为 IQ 指数趋势;样本、口径和自动化仍在校准中。
过去 24 小时观测到 109 条公开动态,其中 47 条进入候选信号;本轮新增 45 条,已见过 2 条。预测模型只处理新增候选。
@jipvandervelde congrats, Jip 🤝
You can use codex within your own programs using the Python SDK. It's awesome. Built by @ah20im and friends ``` pip install openai-codex ``` https://t.co/GjQVEPwtkF
@Kappaemme1926 That's my line
https://t.co/9JuDxlYwz7
Your Codex activity now has a home, and an easier way to share it. Codex profiles show your activity graph, streaks, lifetime tokens, peak daily tokens, and top features like plug…
man the early days of the internet were so special
build and publish web apps with chatgpt! i really wish i had this when i was a kid, but i do miss hypercard.
big upgrade to chatgpt memory rolling out today!
@dkundel Nice learnings, thank you for sharing 🤝
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…
Listen to the OpenAI Podcast on— Spotify https://t.co/1sYUSLF1cJ Apple https://t.co/zel5cpTVqT YouTube https://t.co/oYxzMX0Ocy
What happened when one of our models found a counterexample to an 80-year-old Erdős conjecture? Researchers @alexwei_, @HongxunWu, and @wjmzbmr1 shared the story on the OpenAI Pod…
Moderation scores are now available in the Responses API and Completions API. Return moderation signals in the same request flow as generation, then decide how your app uses them…
@Baconbrix @sentry 🔥🤝
Shoutout to the open source projects behind this: • Serve-sim powers the streaming simulator by @Baconbrix https://t.co/Yx52DuSGcZ • SnapshotPreviews extracts SwiftUI previews by…
More of the iOS app loop, now inside Codex. The Build iOS Apps plugin lets Codex view and test your iOS app in the in-app browser, open SwiftUI previews, and hot reload edits with…
Codex usage limit is so low @thsottiaux business license, this is like demo rate limit
@thsottiaux @ah20im Why are you banning people from Codex! I just read a dozen such reports tonight and it happened to me too
@thsottiaux @ah20im Something up with utilization? Things seem to be going pretty quick tonight, even on High / NotFast
@thsottiaux @ah20im Hi Tibo 👋 browser and Windows control tool haven't been working for a while; have these extensions been removed?
@thsottiaux @ah20im Codex needs to improve multi threading and responsiveness. It's amazing in Ai companies shipping half baked products.
@thsottiaux @ah20im Hi, my ChatGPT Plus account (2395244628@qq.com) was deactivated. I believe this is a false positive due to my secure network proxy. My appeal was auto-rejected…
@thsottiaux @ah20im Does anyone have problems login in with a Microsoft account? I get the dreadful 'error_code: token_exchange_failed' on two different accounts.
@thsottiaux @ah20im Hey tibo my ChatGPT Pro account was banned, and support won't help. I’ve been a loyal Pro subscriber for months, just using it solo for my own dev projects. No…
@thsottiaux @ah20im I’m worried I’d get banned if I used it programmatically. What’s the usage limitations on this?
@sarahyang_00 When ever the codex down he reset the limits and play major role I'm marketing.... Updates
@thsottiaux @ah20im Hi @thsottiaux . I found that if I don’t give codex full disk access on Mac, the lower side window/terminal cannot be opened ☠️. Is it on purpose
So, we loaded up an Agentic account. Connected this one to ChatGPT/Codex. Only put $50 in it, but want to do some testing with it. https://t.co/la7oi5PIHB
@petergyang You actually don't need to make an image separately in ChatGPT. Codex can also make images, so you can just tell it to generate an image and then create the slide in o…
@thsottiaux @ah20im Useful because it turns Codex from an app you open into a worker inside a repeatable workflow. For non-coders: 1. write the goal 2. let Codex act 3. force test…
PromptVault: Auto-save and search every prompt across ChatGPT, Codex, Claude, Gemini https://t.co/5cLUmPPQJp
OpenAI — ChatGPT・Codex・Atlas ブラウザの統合デスクトップアプリ計画 OpenAI が ChatGPT、Codex、独自ブラウザ「Atlas」を一つのデスクトップアプリへ統合する計画が報じられた。情報・計画・タスクをまとめて完結させる"エージェントワークスペース"への転換を示すもので、AI プロダクトのチャットボットから自律型エー…
@thsottiaux @ah20im Love seeing proper local agent tooling like this. Python SDK makes it easy to integrate
@thsottiaux @ah20im been tinkering with ai for my late night video edits. this sdk sounds super handy, might actually save me some debugging headaches. gonna try it tonight.
@thsottiaux @ah20im pip install openai-codex means every Python program can now ship with a coding agent inside. the import statement becomes the deployment surface
@thsottiaux @ah20im Been working on a Go port in case it's useful to anyone: https://t.co/RiOqbxerCZ
@thsottiaux @ah20im Python is awesome, made an agent memory system to keep your codex and all other harness sessions all in sync with your openclaw or hermes agent including self…
This is a massive leap forward for AI agents in real engineering workflows. Finally having a clean Python SDK for Codex that runs locally with JSON-RPC control over CI/CD, sandbox…
@thsottiaux @ah20im You can also build with codex in your js apps via a Web assembly compile of codex itself! https://t.co/zPUJj4fTd3
@thsottiaux @ah20im This looks cool. Definitely gonna check if there’s anywhere we can add this in
@thsottiaux @ah20im I've been using Codex to set up and set up a homelab, I'm loving the experience. I already have some services running locally.
@thsottiaux @ah20im go sdk pls
@thsottiaux @ah20im how does the pricing work for codex via API?
@jipvandervelde congrats, Jip 🤝
@asklumo @ProtonPrivacy Tell ChatGPT Codex to ship free stuff to your home address.
@thsottiaux @ah20im 我也看到这个了,希望可以在某个地方用到它
@thsottiaux @ah20im pretty useful
@thsottiaux @ah20im It would be great if this could also be used directly in browsers. I think that would help WebMCP gain adoption much more quickly.
@thsottiaux @ah20im can ai use uv ?
@thsottiaux @ah20im @grok name the top 3 super cool use cases for this that most people would not think of
@thsottiaux @ah20im Quick glance, I didn’t see “auto review” preset mode for sandbox?
@thsottiaux @ah20im Okay yeah, this is where Codex gets annoying in a good way. Not another chat tab. Just a little agent goblin you can shove directly into your own tools.
@thsottiaux @ah20im Please verify this https://t.co/s7bMe0NYAd
@thsottiaux @ah20im now can it coordinate actual debates people want
@thsottiaux @ah20im Looks cool, can it generate images in this SDK?
@thsottiaux @ah20im hmmm so I don’t need to wrap the app server?
@thsottiaux @ah20im @grok What would be the examples and use cases for this feature?
@thsottiaux @ah20im Nice codex can write all my python to call codex to write all my python https://t.co/4fDE7vmZvH
@thsottiaux @ah20im Java sdk🥹
@thsottiaux @ah20im amazing🥰
ChatGPTの記憶が“夢”で進化?Canvaが会話で直接デザイン、Claude自社コード8割AI化【最新AIニュース】
十几个小时的速蹬窗口,最多可以蹬出额外 2000 美元的价值!
按窗口关闭时间倒序。所有时间均为北京时间 UTC+8。
Tibo 表示过去 24 小时内有三次影响 Codex 可靠性的小事故,并已为所有付费计划重置 Codex 使用限制。
Tibo 将这次重置解释为庆祝 Codex 达到 500 万用户;随后确认所有付费 ChatGPT 订阅的周额度和 5 小时额度都已恢复到 100%。
Tibo 表示 Codex 长会话压缩的 cache hit rate 受回滚优化影响,导致限制消耗更快;修复后已为所有账号重置使用限制。
Sam 发文称推文获 1 个赞后 Tibo 会重置 Codex 速率限制,随后社区在数分钟内反馈重置完成。
Tibo 表示两个 GPT-5.5 能力退化问题已修复后,付费计划的使用限制完成重置。
为庆祝顺利的一周,并让用户继续用 GPT-5.5 构建,所有付费计划的限制已重置。
Codex 达到 400 万活跃用户后,Tibo 和 Sam 均预告当天会重置;几小时后出现多条用户反馈称额度已重置。
短暂的 Codex 局部故障后,Tibo 表示即将重置速率限制。评论区约 2 小时 43 分钟后出现“usage is back to 100%”等用户反馈。
为纪念产品一周年,Codex 对所有计划的速率限制进行了重置。
Codex 达到 300 万周活用户后,Tibo 表示正在重置限制;随后 @OpenAI 在新计划发布时确认现有 $200 Pro 用户的 Codex 速率限制已再次重置。
监控面板显示触达限制的用户比例上升后,所有计划的使用限制完成重置。
为方便用户体验新发布的 Codex 插件,所有计划的使用限制完成重置。
Tibo 表示问题稳定后会进行重置,随后表示已按下重置按钮。评论区最早在 3月11日 14:48 出现 5h 与 2 Week 剩余额接近满额的截图。
在调查“用量消耗快于预期”的反馈期间,Plus 和 Pro 订阅的速率限制已重置。
Tibo 表示约 9% 的 Plus 和 Pro 用户未获得 2X 活动额度,并正在为这些用户重置。评论区 4 分钟内出现 100% left 与 99%-100% 剩余额截图。
请求被错误地作为高网络风险拦截后,Tibo 表示团队会重置速率限制;21 分钟后评论区出现额度回到满额的截图。
速率限制已重置,并且使用额度临时提升至平时的 2 倍,持续到 1 月 1 日。
作为新用量追踪与计费系统的一部分,使用限制已重置。
Codex 遭遇错误部署并恢复后,所有用户的使用限制已重置。
为快速缓解 Web、CLI 和 VS Code 中用量限制显示不一致的问题,所有用户的使用限制已重置。
为补偿美国及附近区域异常高延迟问题,所有 Codex 用户的速率限制已重置。
短暂的 Codex 故障解决后,速率限制已重置。
在补充 GPU 资源以缓解变慢问题后,所有用户的 GPT-5-Codex 限制已重置。