thank god the image issue is fixed (hopefully for real this time)
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!
赚不到孙哥的钱,但可以过一遍孙哥的人生。
如果你是孙哥,会为了景甜去北京吗?
《我的女友景甜》游戏版,免费玩:dramori.ai/stories/my-girlfr…
I've been bearing with first issue for like 2 months now finally it's being addressed.
Update on rate limits in Codex.
We’ve found (a) some inefficiencies when using images in long sessions with multiple compactions (b) high p95+ usage for Computer History (c) a feature that was meant to generate conversation titles that was draining a bit more usage than intended. And we have a tiger team combing through everything and shipping fixes tomorrow. We also found a novel approach to drive efficiency up significantly that is completely unrelated and we will be working on next week.
As part of some of the fixes tomorrow, we will also do a full reset of the usage for all paid subscriptions.
See you then.
So what exactly is loop engineering? Everyone is talking about it for a while now, but I still don’t really understand it. Is there an actual hands-on workflow to follow?
Surely it has to be more complicated than /goal mode, AGENTS.md, and defining testable behavior... right?
Not really, I have another harness setup for bug hunting and auditing. Will share it in details soon :)
I've been using @mattpocockuk skills for the past couple of weeks, and my productivity has probably 3x'd.
My usual work session starts with the /grill-me skill. Begin with a broad, messy task, and the agent keeps asking questions until the gaps are clear. The useful part is that while you're answering, you're also forced to understand the task better and dig into the details you skipped. One time it grilled me for 80+ questions and halfway through I was basically asking are we there yet every few minutes.
Then I run /to-issues skill and kick the issues off in goal mode. One detail I think is very important is to explicitly ask it to spawn subagents for each task, test the work when it's finished, and redo it if it's not actually done. Runs usually go for multiple hours, so once one is kicked off, I can start working on another session, or just go back to doomscrolling.













