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 85 条公开动态,其中 37 条进入候选信号;本轮新增 34 条,已见过 3 条。预测模型只处理新增候选。
Increased latency for Codex compaction for a subset of users
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…
@thsottiaux @Kappaemme1926 Mate I don't know what the go is, but ever since you made that post about "over the last 24 hrs 3 separate issues", Codex is painfully slow for me in Au…
@thsottiaux @Kappaemme1926 The lack of Pro seats in team plans. Small-Medium employer wants managed workspace/billing and approved vendors, but token quota is insufficient. Need 4…
windows bugs... feels like memory leaks everywhere... pretty sure the automation have mutli process/thread issues ... maybe needs a better thread watcher/process watcher they'll d…
@thsottiaux @Kappaemme1926 Windows app crashes. Seems like any task that balloons into a mammoth thread will freeze the app.
I made my own version of this and I discovered that essentially the only thing that slows codex down is having mega large threads that are pinned So all you need to do is unpin yo…
@theinformation merging codex into chatgpt is the interesting part. 5M users is a vanity number until you see retention after they stop subsidizing usage. the real signal will be…
@thsottiaux @Kappaemme1926 How about one more weekly reset to celebrate the new memory release in ChatGPT? (:
@thsottiaux @Kappaemme1926 The later section of the 400k ctx becomes lazy Better consistency in 5.6 Also, cc has wake up agent. Good stuff u should copy that 5.6 should also be na…
@thsottiaux @Kappaemme1926 Ghost window https://t.co/x7rpDK2zBX
@thsottiaux @Kappaemme1926 No your line is 'I pushed the reset button' lol
@thsottiaux @Kappaemme1926 Ok Tibo why does my local python environment somehow not work when it’s thinking and checking code?
@thsottiaux @Kappaemme1926 I reset your limits now!
@thsottiaux @Kappaemme1926 That locked computer use still doesn’t work on either of my Mac
@Kappaemme1926 That's my line
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
@thsottiaux @Kappaemme1926 Sometimes I cant find the Project the current thread is in in the Sidebar a Locate Button would be great maybe Back and forth Navigation between Threads
@thsottiaux @Kappaemme1926 ios chatgpt switch between quick chat and codex irritating af. no pinned chats in codex too so finding the chat is effortful also my main codex chat thr…
@thsottiaux @Kappaemme1926 /review returns more than 3 results.
@thsottiaux @Kappaemme1926 Haha, classic. You beat me to it this time.
@thsottiaux @Kappaemme1926 tibo my codex app is in japanese and it took me two minutes to use /goal there because it didn’t recognize “/goal”. it wanted “/目標”
@thsottiaux @Kappaemme1926 Pro model on Codex
@thsottiaux @ah20im swift when?
@thsottiaux @ah20im Interesting stuff!
@thsottiaux @ah20im its insane
@thsottiaux @Kappaemme1926 Can pro+ ($200/mo) have Sites? Whats the point of paying that much without ALL the features?
@thsottiaux @Kappaemme1926 WHERE'S MY ANNUAL PRICING TIBO I NEED MY ANNUAL PRICING TIBO https://t.co/EWBciCOmEz
It would be great if I could access Codex-local content remotely to a greater extent. At the moment, for example, when Codex makes some visual and 127.0.0.1 link, it’s not nativel…
@thsottiaux @Kappaemme1926 ❗ https://t.co/jgwKhJlULp
@thsottiaux @Kappaemme1926 need /slow mode
@thsottiaux @Kappaemme1926 Feature request: let us pin files that persist thru context compactions like images, docs, etc. have it show in pinned summaries
@thsottiaux @Kappaemme1926 https://t.co/k8uBQHGM9w
@thsottiaux @Kappaemme1926 Can I have an API for Codex to hook it into our agent teams alongside Hermes and OpenClaw?
@thsottiaux @Kappaemme1926 Could we have rules files for every project, Tibo?
@thsottiaux @Kappaemme1926 You guys need to add the auto mode that Claude added so I don't have to approve every edit at times.
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。