TiboSay - Tibo’s 28-Day OpenAI Codex Challenge & Limit Reset Log

Day 22 / 28

Daily Log

Improvement
Reset
Reset + Ship

Day 222026-10-26
🛠️ Improvement
👏 83%
Day 22/ Terra is back! Our first model that is significantly better at writing, personality and nuanced understanding of requests. Packs a p
Day 22/ Terra is back! Our first model that is significantly better at writing, personality and nuanced understanding of requests. Packs a punch across the board, very good at computer use, and gives 2X more usage than 6.1 Sol across API and subscriptions. OpenAI @OpenAI 1h GPT-6.1 Terra: delivering fast and capable computer use at a lower price. GPT-6.1 Terra understands what’s on screen, takes action across apps, writes naturally, and is a more capable model for your whole workday with the efficiency to take on more of it. Video 2 00:30
Day 212026-10-25
🛠️ Improvement
👏 82%
Day 21/ Wonder what happens the remaining seven days. But today is a reset.
Day 21/ Wonder what happens the remaining seven days. But today is a reset.
Day 202026-10-24
🛠️ Improvement
👏 99%
Day 20/ Rest and reset
Day 20/ Rest and reset
Day 192026-10-23
🛠️ Improvement
👏 19%
Codex CLI presets, inline settings, and reliability updates
Codex CLI now supports reusable prompt presets, inline model and permission settings, enterprise MCP sign-in, and Windows corporate-proxy authentication. Failures when resuming long sessions have also been fixed.
🛠️ Improvement
👏 31%
Faster Dots calls and cache-preserving reasoning changes
Dots calls now connect much faster. Changing reasoning mid-conversation in Codex and Work no longer invalidates the cache.
Day 182026-10-22
🚀 Reset
👏 82%
Usage limits reset for everyone
“Landing tomorrow before 10am PST together with a small ship.”
Day 172026-10-21
🚀 Reset
👏 86%
Usage limits reset for everyone
“Day 17/ Bet you thought we forgot, but no, it’s reset day today. Also good time to remind you to get Daybreak Blue access, it only takes 15 mins and you don’t want to have to do it in the middle of an incident.”
Day 162026-10-20
🛠️ Improvement
👏 93%
Persistent caching in Codex and Work
Logged-in Codex and Work users now get indefinite cache retention and guaranteed cache hits when returning to old conversations. The API also supports 12-hour prompt caching.
Day 152026-10-19
🚀 Reset
👏 90%
Usage limits reset for everyone
“Day 15/ Nevermind, we're still cooking... and reset. Enjoy.”
Day 142026-10-18
🛠️ Improvement
👏 11%
Edit previous messages in desktop threads
Users can now edit previous messages within a thread in the desktop app.
Day 132026-10-17
🚀 Reset
👏 91%
Usage limits reset for everyone
“Done”
Day 122026-10-16
🛠️ Improvement
👏 10%
Slides support in ChatGPT Space
ChatGPT Space now supports slides for Pro, Business, and Enterprise users.
🛠️ Improvement
👏 8%
Dots on the Home Screen
Dots are now available on the Home Screen after updating the app.
🛠️ Improvement
👏 48%
GPT-6 Pro upgrade with parallel agents
GPT-6 Astra Pro in ChatGPT now offers faster responses, improved plugin and tool use, and parallel agents. Pro users can track each agent’s progress and review completed work in the Chat tab.
🛠️ Improvement
👏 88%
More efficient context reuse and caching
Codex and Work now reuse context across subagents, cache context longer, and improve request routing to increase cache hits, giving users more effective usage.
Day 112026-10-15
🛠️ Improvement
👏 25%
Fewer model-capacity errors and automatic recovery
Shipped changes and added compute aim to significantly reduce model-capacity errors. When an error occurs, processing should eventually resume automatically rather than remain blocked.
Day 102026-10-14
🚀 Reset
👏 89%
Usage limits reset for everyone
“Done and dusted”
Day 092026-10-13
🛠️ Improvement
👏 39%
Reduced desktop app disk storage
Storage optimizations have rolled out for the ChatGPT and Codex desktop apps, expected to reduce the disk space used for stored state by 60%.
Day 082026-10-12
🚀 Reset
👏 90%
Usage limits reset for everyone
“What would you like with your side of reset? It's done.”
Day 072026-10-11
🛠️ Improvement
👏 75%
Larger default context for GPT-6.1 Sol
GPT-6.1 Sol now defaults to 500k context in Codex and Work, up from 272k, helping reduce compactions and retain context during long tasks.
Day 062026-10-10
🚀 Reset
👏 94%
Usage limits reset for everyone
“Put the reset in the bag. All propagated.”
Day 052026-10-09
🛠️ Improvement
👏 5%
Use ChatGPT plans with Devin
Users can now connect a personal ChatGPT Go, Plus, or Pro plan to Devin, with GPT model usage drawing from their ChatGPT plan quota.
🛠️ Improvement
👏 20%
Dots can delegate Codex work and edit Scheduled Tasks
Your dot can now start and follow up on Codex work using context from ChatGPT conversations, Codex threads, and automations. It can also review and edit Scheduled Tasks in ChatGPT Work.
🛠️ Improvement
👏 17%
Composer predictions in the Codex desktop app
Now available in beta for Pro users, composer predictions suggest your next message based on your conversation and how you communicate with Codex. The feature does not consume plan usage.
Day 042026-10-08
🛠️ Improvement
👏 26%
Instant steering and GPT-6.1 Sol ultrafast
Steering now responds instantly to user adjustments for real-time course correction. GPT-6.1 Sol ultrafast is also rolling out in the API, Codex, and ChatGPT Work.
Day 032026-10-07
🚀 Reset
👏 97%
A banked reset for everyone
“Confirmed landed across all accounts. How are we doing so far?”
🛠️ Improvement
👏 27%
Codex Cloud connects through Tailscale
Codex Cloud can now securely connect to resources on your tailnet using Tailscale.
🛠️ Improvement
👏 84%
GPT-6 update with Intelligent UI
A new GPT-6 version and Intelligent UI are rolling out to everyone in ChatGPT, adding visual, interactive answers and tools for users’ tasks.
Day 022026-10-06
🚀 Reset
👏 80%
Usage limits reset for everyone
“We shipped four things that were deemed good to great and some math proofs, but the vote is clear and the community demands a reset. I did calibrate it and it *seems* that the game is rigged in reset's favor, but such are the rules at the moment. Therefore ... the reset has been”
🛠️ Improvement
👏 28%
Decisions API is live in public beta
Developers can use the Decisions API to pick a model, tool, or action in near real time. It is available to all developers in public beta and decides up to 10x faster than GPT-6 Luna through the Responses API.
🛠️ Improvement
👏 15%
Meetings plugin saves notes and next steps
The Meetings plugin takes notes and saves a personalized summary and next steps in ChatGPT Space. It is in beta for Pro and Business users in the ChatGPT desktop app on macOS.
🛠️ Improvement
👏 10%
Easier qualification for higher API rate limits
Paid OpenAI API usage tiers go from five to three: Build, Launch, and Grow. Grow, the new highest tier, now qualifies with $500 in total API payments, down from $1,000.
🛠️ Improvement
👏 27%
Free Auto-review for all ChatGPT-signed-in users
Auto-review is now free for all users signed in through a ChatGPT account. Enable it in permission settings to have a second agent review actions during long tasks, without drawing usage from your plan.
Day 012026-10-05
🛠️ Improvement
👏 87%
About 50% faster default speed for GPT-6 Astra and GPT-6.1 Sol
Default speed has been optimized across subscription products and partners using Sign in With ChatGPT. The improvement is rolling out within two hours, with no user action needed.

Tibo’s 28-Day Challenge

Daily Log