unofficial - Codex Updates not affiliated with @openai

Joined August 2024
馃毃Codex Users!!! Day 17/ The reset is here! OpenAI hasn鈥檛 forgotten about us. Another round of usage resets is rolling out today. Tibo also recommends setting up Daybreak Blue access ahead of any incidents. Who鈥檚 got their reset already?
Day 17/ Bet you thought we forgot, but no, it鈥檚 reset day today. Also good time to remind you to get Daybreak Blue access, it only takes 15 mins and you don鈥檛 want to have to do it in the middle of an incident.
130
馃毃Codex Users!!! Day 16/ Finally, a solid caching upgrade. API caching now lasts up to 12 hours. For logged-in Codex & Work users, cache is kept indefinitely. You can return to old conversations without losing cache benefits or taking a usage penalty. Big W for heavy users.
Day 16/ You can now cache for 12h in the API and for logged in users across Codex & Work we keep cache forever and you don鈥檛 have any penalty for coming back to an old conversation or resuming after a few hours and are now guaranteed to hit the cache.
54
馃毃Codex Users!!! Turns out the weekend usage drain wasn't just a feeling. OpenAI confirms around 40,000 accounts were affected by incorrect usage limits. The issue is now fixed, and affected users will receive credits. which is good How did something this big slip through?
There were reports of usage draining faster than anticipated for some users over the weekend. We've identified approximately 40,000 accounts that had an inconsistency on which usage limits where the actual usage that was applied did not correspond to their actual selected plan. We are reaching out individually to all these users and have corrected the issue. If this affected you, we'll add credits to your account. Sorry we got this wrong.
60
馃毃Codex Users!!! Day 15/ Never mind, we're still cooking... and another reset. At this point, resets are doing more to keep users happy than actual product improvements. Maybe fix the usage limits instead of making resets feel like a reward.
Day 15/ Nevermind, we're still cooking... and reset. Enjoy.
1
1
70
馃毃Codex Users!!! Day 15/ We're cooked. Halfway through the 28-day challenge, and users are still complaining about usage limits. Yesterday's update? Editing old messages. At this point, people just want their usage back.
Day 15/ We're cooked
95
馃毃Codex Users!!! GPT-6.1 Terra might actually be coming! Microsoft's GitHub repo now references gpt 6.1 Terra in 18 evaluation configs. The Information has also hinted at Terra's return. No official announcement yet, but its intresting. Are you excited for this model ???
57
馃毃Codex Users!!! Day 14/28 OpenAI finally lets you edit previous messages in the Codex desktop app. Seriously, how did something this basic take so long to ship? We're getting massive model upgrades, but somehow basic features are still treated like major releases.
Day 14/ Small quality of life improvement. You can now edit previous messages within a thread in the desktop app. Long time requested, and took way too long to get that one out.
1
223
Codex Tracker retweeted
馃毃 New OpenAI models spotted? Three new identifiers have surfaced: "aurora-blue-alpha" "aurora-red-alpha" "aurora-green-alpha" Is OpenAI preparing a new model to get ahead of its competition with Anthropic? Astra 6.1 could be one possibility imo are we getting them on day 14?
1
1
272
馃毃 New OpenAI models spotted? Three new identifiers have surfaced: "aurora-blue-alpha" "aurora-red-alpha" "aurora-green-alpha" Is OpenAI preparing a new model to get ahead of its competition with Anthropic? Astra 6.1 could be one possibility imo are we getting them on day 14?
1
1
272
Codex Tracker retweeted
馃毃馃毃馃毃BUG IN CODEX 馃毃馃毃馃毃馃毃馃毃 The temporary chat is completely misaligned 馃毃
1
48
馃毃Codex Users!!! Day 13/28 Another limit reset is here! OpenAI keeps the reset streak going. Enjoy the extra usage while it lasts. How long do you think they'll keep this going?
Day 13/ Le limit reset
187
馃毃Codex Users!!! Day 12 More usage without increasing your limits OpenAI has improved context sharing between subagents, extended caching, and optimized request routing. The result? Less wasted compute and more work done with the same usage. Are you noticing a difference yet?
Day 12/ We鈥檝e made improvements to Codex & Work that increase the effective usage you get. We achieved this by reusing context across subagents, keeping context cached longer, and improved request routing that allows us to increase cache hits.
127
馃毃Day 11/28 Openai team, with all due respect this is clearly not a feature its a bug fix... So why in the world would you post it as a feature 11/28 we need something which is good, maybe new model that beats opus 5.5
Day 11/ We've landed a series of changes and more compute to very significantly decrease the occurrence of the disruptive "Selected model is at capacity. Please try a different model". When it does happen, it should also eventually just continue by itself and not just block on it. Let us know if you still see it out there in the wild and we'll take a look.
110
馃毃Codex Users!!! Day 10/28 The reset button isn't going anywhere. OpenAI has processed another Codex usage reset! 10 days in, and the resets keep coming. How are your limits looking now?
The reports of my reset button being lost are greatly exaggerated Day 10/ Reset
274
Codex Tracker retweeted
馃毃OpenAI is reportedly accelerating its next flagship model. Around 10% of compute is reportedly focused on safety after Astra's delays... With Meta, Google, & Anthropic increasing the pressure, could the next flagship arrive sooner? what do you think let me know down below
1
113
馃毃OpenAI is reportedly accelerating its next flagship model. Around 10% of compute is reportedly focused on safety after Astra's delays... With Meta, Google, & Anthropic increasing the pressure, could the next flagship arrive sooner? what do you think let me know down below
1
113
馃毃Codex Users!!! GPT 5.5 is officially being retired today. Goodbye gpt 5.5 It's leaving ChatGPT, Codex and Work across all plans. The API is unaffected, so developers can still access it there. Anyone still using 5.5, or have you already moved to GPT-6.1 Sol?
90
Codex Tracker retweeted
馃毃Codex Users!!! Day 9/28 OpenAI is finally tackling disk space. New optimizations for ChatGPT & Codex desktop apps cut disk usage by up to 60%. Not flashy, but needed, and finally a better ship that before ones imo Has Codex been eating up your storage too?
Day 9/ We've rolled out optimizations to how we store state on disk for the chatgpt & codex desktop app that should reduce the amount stored on disk by 60%. Small ship but we've heard enough feedback about power users running out of disk space.
1
65
馃毃Codex Users!!! Day 9/28 OpenAI is finally tackling disk space. New optimizations for ChatGPT & Codex desktop apps cut disk usage by up to 60%. Not flashy, but needed, and finally a better ship that before ones imo Has Codex been eating up your storage too?
Day 9/ We've rolled out optimizations to how we store state on disk for the chatgpt & codex desktop app that should reduce the amount stored on disk by 60%. Small ship but we've heard enough feedback about power users running out of disk space.
1
65
馃毃 Did OpenAI again nerf GPT-6.1 Sol overnight? its struggling at simple tasks, basic errors keep popping, and fixing problems takes way more back and forth than before. Openai seriously???? At launch, this model was seriously impressive. Now, the difference is hard to ignore.
76