Codex：重置預告（轉錄）
Codex：重置預告（轉錄）
第三方轉錄，請核對原帖與適用範圍；不代表個人賬號狀態。
各位 Astra 用戶好。這次帶來重置消息，以及對近期反饋的質量問題的簡短說明。 在部分用戶的協助下，我們發現並修復了以下問題： - 一些為舊模型編寫的技能觸發過於頻繁，或妨礙模型檢查自己的工作。 - 一項需主動加入的上下文管理實驗可能導致提前停止，或回復較早的消息。我們已停用該實驗，粗略估計有 4,000—5,000 名用戶受到影響。 - 我們也移除了一些配置不當的引擎；經過這些引擎的一部分流量出現了可測量的質量下降。 此外，我們做了一些小幅改進，整體體驗應該會明顯改善：更穩定地跟進任務，更準確地跟蹤最新消息，並在執行過程中更好地檢查工作。 大家發佈的例子，以及直接與我們合作排查的用戶，對快速修復問題幫助很大。一直感謝這個社區。 另外，重置也將在今天午夜前到來。 注：“今天”與“午夜”保留原帖說法，不能當作當前日期或新的重置預告。
參考譯文 · 查看原文查看轉錄原文與時間依據
Hi Astra users. A reset and a quick update on quality issues that have been posted around. Working with some of you, we have found and fixed the following issues: - Some skills written for previous models were triggering too often or preventing the model from checking its work. - An opt-in context management experiment that could cause early stops or replies to older messages. We've disabled it. Our rough estimate is that 4-5k users were affected by this experiment. - We've also removed some badly configured engines that resulted in a measured quality degradation for a long tail of traffic flowing through them. We’ve also made some more minor improvements and things should feel significantly better across the board. More consistent follow-through, better tracking of your latest message, and better checks on the work as it’s going through the motions. The examples posted and all the users who worked directly with us were incredibly useful in helping fix things quickly. Always grateful for this incredible community. And of course, a reset is also landing by midnight today.