AI 导读
OpenAI 重置所有付费 Codex 和 ChatGPT Work 用户的用量,并修复多处浪费额度的 bug,相同额度现在可用时间延长 10%–50%。作者把这一做法与 Anthropic 削减周用量 17% 并列比较,认为谁在社区运营上做得更好已经很清楚。官方列出的修复包括 compaction 保留旧图片、后台 memory worker 继承 Stop hooks、/goal 超出停止条件、自动化任务执行频率异常、子智能体选择、Computer History 重复总结、滚动任务摘要触发额外后台请求以及 MCP 工具结果重复编码等问题,其中部分案例曾消耗周额度的 15%–70%。
正文
Anthropic: we are reducing your weekly rates by 17%.
OpenAI: We are resetting usage for all paid Codex and ChatGPT Work users and fixed several bugs that wasted usage, so the same allowance should now last 10–50% longer.
At this point its crystal clear who does better community work.
We are reseting usage for all paid users of Codex and ChatGPT Work. Please continue reading for an update on Codex usage limits. The team has been working around the clock, going through thousands of reports and shipping fixes. Depending on how you use Codex, you should see your usage go between 10% and 50% further than before. We really went with a fine comb, with many uncovered small things being longstanding and here is what we found and fixed: - Compaction. We were keeping old images during compaction, sometimes making the context large enough to trigger compaction again. After the fix, usage dropped around 10% for users making heavy use of images. Fixed. - Memory. Background memory workers could inherit Stop hooks and keep running when the hook wouldn’t let them finish. This affected fewer than 1% of users, with the long tail being pretty bad and we saw one example thread check whether it could stop 15,000 times. Fixed. - Goals. In some cases, a set /goal could finish and then keep going past the intended stop condition, or the model would keep retrying broken tools without stopping. We saw examples consume anywhere from 15% to 70% of a weekly allowance. Fixed. - Automations. Some custom schedules could run more frequently than configured. Fixed. - Subagents. Smaller models (e.g. Luna) sometimes picked more capable helpers without being explicitly asked. The same was true where the orchestrating model not running in /fast mode could request sub-agents to run /fast. Fixed. - Computer History. The older implementation could lead to repeatedly summarizing overlapping activity. For some cases we saw it consume up to one fifth of the weekly usage per week. Fixed. - Rolling task summaries. Ordinary turns were triggering extra background requests. These added about 1% to token usage. Small each time, but it adds up. We have disabled this. - MCP. Some tool results could be encoded twice. We also found tool instructions getting cut off and fetched again. Fixed. We’ve also made architectural changes to prevent these from regressing and our teams will get paged if it happens regardless. We are also working on showing you directly in the app where your usage goes so you don’t have to guess. Goes without saying that we’re resetting usage limits and I hope you enjoy a very nice Saturday!在 X 查看被引用的帖子
来源:@kimmonismus · x.com