# Tibo's 28-day challenge: one clear improvement, or a full reset, every day Codex lead Tibo's 28-day challenge: Codex ships one clear improvement or a full reset every day for 28 days. Follow each day, see confirmed resets, and predict what comes next. Language: en Time zone: America/Los_Angeles Current time (UTC, cached as of): 2026-10-19T21:53:00.000Z Query date (America/Los_Angeles): 2026-10-19 HTML: https://didcodexreset.com/oct28.html 10/5 – 11/1 Day 15 of 28 Day 15, Oct 19 Mon: Improvement day Selected source: Tibo, published 10/19/2026, 12:45:28 (America/Los_Angeles). [Open on 𝕏](https://x.com/thsottiaux/status/2112268918681485431) ## 28-day calendar ### Day 1 Β· 10/5 [Improvement day](https://x.com/thsottiaux/status/2107158998495748264) [Day 1 page](/oct28/day1.html.md) Predictions for day 1 - Reset: 20694 (45%) - Improvement: 25468 (55%) #### GPT-6 Astra/GPT-6.1 Sol default ~50% faster via Sign in With ChatGPT Improvement Β· 10/5/2026, 10:20 We have optimized the default speed to be ~50% faster across GPT-6 Astra and GPT-6.1 Sol through the subscription across all our products and partners using Sign in With ChatGPT (including OpenCode, Pi, Amp, Devin, ...). No changes needed on your end and this should be felt within the next two hours. - πŸ‘Œ great release: 26 - 🫨 needs a reset: 6 [Open on 𝕏](https://x.com/thsottiaux/status/2107158998495748264) ### Day 2 Β· 10/6 [Reset + improvement day Β· Global Reset](/history/1791344109000.html) [Day 2 page](/oct28/day2.html.md) Predictions for day 2 - Reset: 4060 (61%) - Improvement: 2632 (39%) #### Reset processed following community vote after shipping four items Reset Β· 10/6/2026, 20:35 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 processed. Enjoy! - πŸ‘Œ great release: 31 - 🫨 needs a reset: 7 [Open on 𝕏](https://x.com/thsottiaux/status/2107676072871600470) #### Approve for me 2-10% plan;simpler API;meeting notes;Decisions API live Improvement Β· 10/6/2026, 13:56 2.1/ Approve for me (auto-review) is now included and does not use usage. Can be between 2-10% of plan when used. Also better for you. 2.2/ Simplified API for builders. 2.3/ Meeting notes integrated. 2.4/ Decisions API live for builders. Will use in the app to improve the experience. - πŸ‘Œ great release: 5 - 🫨 needs a reset: 23 [Open on 𝕏](https://x.com/thsottiaux/status/2107575657014468879) #### Day 2.4: Decisions API is live Improvement Β· 10/6/2026, 13:53 Decisions API is live. We will use this ourselves to improve the experience for everyone in many fun ways. Realtime general classifier does open some great possibilities. - πŸ‘Œ great release: 2 - 🫨 needs a reset: 19 [Open on 𝕏](https://x.com/thsottiaux/status/2107574912349303197) #### Day 2.3: Talk freely to build context for codex and get it all done Improvement Β· 10/6/2026, 13:47 Never worry about remembering what you were saying with that colleague. Just talk your heart out and build up the context to load up into codex to get it all done. - πŸ‘Œ great release: 2 - 🫨 needs a reset: 13 [Open on 𝕏](https://x.com/thsottiaux/status/2107573405553938664) #### Day 2.2: Removed some friction when building on the API Improvement Β· 10/6/2026, 12:09 OK this one is smaller, but we removed some friction for when building on the API. Happy building. - πŸ‘Œ great release: 4 - 🫨 needs a reset: 21 [Open on 𝕏](https://x.com/thsottiaux/status/2107548725359104441) #### Auto-review is now free for ChatGPT accounts and draws no plan usage Improvement Β· 10/6/2026, 00:13 We have made Auto-review free for all users signed in through a ChatGPT account. You can enable it in settings > permissions > auto-review. Auto-review improves upon the default sandbox setting that requires you to approve everything, which is prone to decision fatigue unless you spend a lot of time configuring specific rules. It allows you to run long tasks while having a second agent review all actions taken by the primary agent. Its only goal is to prevent high-risk actions from being taken and to protect against unwanted actions that are not aligned with the original user intent. This Auto-review feature is now free and does not draw usage from your plan. - πŸ‘Œ great release: 12 - 🫨 needs a reset: 38 [Open on 𝕏](https://x.com/thsottiaux/status/2107368734981517634) ### Day 3 Β· 10/7 [Reset + improvement day Β· Reset bank](/history/1791431095000.html) [Day 3 page](/oct28/day3.html.md) Predictions for day 3 - Reset: 12423 (79%) - Improvement: 3387 (21%) #### Day 3 encore: codex cloud silently re-shipped Improvement Β· 10/7/2026, 23:38 We silently re-shipped codex cloud. It’s pretty good now - πŸ‘Œ great release: 2 - 🫨 needs a reset: 13 [Open on 𝕏](https://x.com/thsottiaux/status/2108084615349170480) #### Confirmed landed across all accounts and checking current progress Reset Β· 10/7/2026, 20:44 Confirmed landed across all accounts. How are we doing so far? - πŸ‘Œ great release: 15 - 🫨 needs a reset: 8 [Open on 𝕏](https://x.com/thsottiaux/status/2108040921044639779) #### Day 3: GPT-6 in Chat; 40M users in Codex/ChatGPT Work; paid banked reset Reset Β· 10/7/2026, 12:19 The big one is GPT-6 in Chat, but today is also a little celebration day with a new high of 40M active users across Codex and ChatGPT Work. Loading a banked reset in everyone's paid accounts. See you again tomorrow! - πŸ‘Œ great release: 22 - 🫨 needs a reset: 8 [Open on 𝕏](https://x.com/thsottiaux/status/2107913674593644711) ### Day 4 Β· 10/8 [Improvement day](https://x.com/thsottiaux/status/2108275041276420573) [Day 4 page](/oct28/day4.html.md) Predictions for day 4 - Reset: 5876 (57%) - Improvement: 4469 (43%) #### Day 4: instant steering, realtime correction; also GPT-6.1 Sol ultrafast Improvement Β· 10/8/2026, 12:15 We have improved steering to be instant, leading to the model now reacting much faster to adjustments you make, allowing you to course-correct direction in realtime and not have the model waste effort. Also releasing GPT-6.1 Sol ultrafast. The two work very well together. - πŸ‘Œ great release: 9 - 🫨 needs a reset: 49 [Open on 𝕏](https://x.com/thsottiaux/status/2108275041276420573) ### Day 5 Β· 10/9 [Improvement day](https://x.com/thsottiaux/status/2108645667451318747) [Day 5 page](/oct28/day5.html.md) Predictions for day 5 - Reset: 10878 (71%) - Improvement: 4454 (29%) #### Create and text your dot entirely from the ChatGPT mobile app Improvement Β· 10/9/2026, 12:49 You can now create and text your dot entirely from the ChatGPT mobile app. Impressed so many created them via the desktop/web app previously. Time to scale! - πŸ‘Œ great release: 6 - 🫨 needs a reset: 60 [Open on 𝕏](https://x.com/thsottiaux/status/2108646052178092403) #### Desktop app Composer predictions in Pro plans without consuming usage Improvement Β· 10/9/2026, 12:47 Composer predictions in the desktop app. Often leads to a double take with how on point they are. Included in the Pro plans without consuming usage. - πŸ‘Œ great release: 5 - 🫨 needs a reset: 53 [Open on 𝕏](https://x.com/thsottiaux/status/2108645667451318747) ### Day 6 Β· 10/10 [Reset Β· Global Reset](/history/1791691269000.html) [Day 6 page](/oct28/day6.html.md) Predictions for day 6 - Reset: 21959 (78%) - Improvement: 6091 (22%) #### Reset completed and fully propagated Reset Β· 10/10/2026, 21:01 Put the reset in the bag. All propagated. - πŸ‘Œ great release: 15 - 🫨 needs a reset: 7 [Open on 𝕏](https://x.com/thsottiaux/status/2109132167112782291) #### Reset Reset Β· 10/10/2026, 15:15 Day 6/ Reset - πŸ‘Œ great release: 39 - 🫨 needs a reset: 9 [Open on 𝕏](https://x.com/thsottiaux/status/2109045220411351517) ### Day 7 Β· 10/11 [Improvement day](https://x.com/thsottiaux/status/2109430343346581527) [Day 7 page](/oct28/day7.html.md) Predictions for day 7 - Reset: 15286 (92%) - Improvement: 1339 (8%) #### GPT-6.1 Sol default context length increased to 500k in Codex & Work Improvement Β· 10/11/2026, 16:45 We have increased default context length for GPT-6.1 Sol to 500k when used through Codex & Work, up from 272k or an ~ 80% increase. We will go higher in the future, but it helps reduce occurrence of compactions and with tasks that require keeping a lot of context and nuance over periods of time. It was carefully tested and is the new sweet spot for most of our users. You can still override it if you want to be higher our lower, with maximum context length of GPT-6.1 Sol of 1M. - πŸ‘Œ great release: 26 - 🫨 needs a reset: 52 [Open on 𝕏](https://x.com/thsottiaux/status/2109430343346581527) ### Day 8 Β· 10/12 [Reset Β· Global Reset](/history/1791867966000.html) [Day 8 page](/oct28/day8.html.md) Predictions for day 8 - Reset: 17527 (76%) - Improvement: 5572 (24%) #### Reset is complete and asking what else is wanted Reset Β· 10/12/2026, 22:06 What would you like with your side of reset? It's done. - πŸ‘Œ great release: 23 - 🫨 needs a reset: 3 [Open on 𝕏](https://x.com/thsottiaux/status/2109873287853707513) #### Reset Reset Β· 10/12/2026, 18:03 Day 8/ Reset - πŸ‘Œ great release: 45 - 🫨 needs a reset: 7 [Open on 𝕏](https://x.com/thsottiaux/status/2109812216212099456) ### Day 9 Β· 10/13 [Improvement day](https://x.com/thsottiaux/status/2110151780478927344) [Day 9 page](/oct28/day9.html.md) Predictions for day 9 - Reset: 4218 (46%) - Improvement: 4950 (54%) #### ChatGPT and Codex desktop app update should cut disk usage by 60% Improvement Β· 10/13/2026, 16:32 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. - πŸ‘Œ great release: 38 - 🫨 needs a reset: 73 [Open on 𝕏](https://x.com/thsottiaux/status/2110151780478927344) ### Day 10 Β· 10/14 [Reset Β· Global Reset](/history/1792045693000.html) [Day 10 page](/oct28/day10.html.md) Predictions for day 10 - Reset: 29575 (76%) - Improvement: 9264 (24%) #### Reset Reset Β· 10/14/2026, 23:28 Done and dusted - πŸ‘Œ great release: 13 - 🫨 needs a reset: 7 [Open on 𝕏](https://x.com/thsottiaux/status/2110618732666257557) #### Reports of lost reset button are greatly exaggerated Reset Β· 10/14/2026, 21:55 The reports of my reset button being lost are greatly exaggerated Day 10/ Reset - πŸ‘Œ great release: 35 - 🫨 needs a reset: 7 [Open on 𝕏](https://x.com/thsottiaux/status/2110595484180214059) ### Day 11 Β· 10/15 [Improvement day](https://x.com/thsottiaux/status/2110750421367287996) [Day 11 page](/oct28/day11.html.md) Predictions for day 11 - Reset: 3447 (47%) - Improvement: 3862 (53%) #### Changes and more compute to reduce model at capacity errors Improvement Β· 10/15/2026, 08:11 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. - πŸ‘Œ great release: 53 - 🫨 needs a reset: 39 [Open on 𝕏](https://x.com/thsottiaux/status/2110750421367287996) ### Day 12 Β· 10/16 [Improvement day](https://x.com/thsottiaux/status/2111244596131111253) [Day 12 page](/oct28/day12.html.md) Predictions for day 12 - Reset: 20278 (86%) - Improvement: 3348 (14%) #### Codex & Work improvements increase effective usage Improvement Β· 10/16/2026, 16:55 We’ve 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. - πŸ‘Œ great release: 13 - 🫨 needs a reset: 83 [Open on 𝕏](https://x.com/thsottiaux/status/2111244596131111253) ### Day 13 Β· 10/17 [Reset Β· Global Reset](/history/1792271541000.html) [Day 13 page](/oct28/day13.html.md) Predictions for day 13 - Reset: 83379 (93%) - Improvement: 6645 (7%) #### Reset Reset Β· 10/17/2026, 14:12 Done - πŸ‘Œ great release: 27 - 🫨 needs a reset: 40 [Open on 𝕏](https://x.com/thsottiaux/status/2111566005684289735) #### Limit reset Reset Β· 10/17/2026, 09:20 Day 13/ Le limit reset https://t.co/zXd2DIH5xf - πŸ‘Œ great release: 38 - 🫨 needs a reset: 37 [Open on 𝕏](https://x.com/thsottiaux/status/2111492673890824348) ### Day 14 Β· 10/18 [Improvement day](https://x.com/thsottiaux/status/2111990254408434095) [Day 14 page](/oct28/day14.html.md) Predictions for day 14 - Reset: 75298 (83%) - Improvement: 15194 (17%) #### Desktop app now lets you edit previous messages in a thread Improvement Β· 10/18/2026, 18:18 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. - πŸ‘Œ great release: 15 - 🫨 needs a reset: 90 [Open on 𝕏](https://x.com/thsottiaux/status/2111990254408434095) ### Day 15 Β· 10/19 [Improvement day](https://x.com/thsottiaux/status/2112268918681485431) [Day 15 page](/oct28/day15.html.md) Predictions for day 15 - Reset: 28507 (81%) - Improvement: 6504 (19%) #### We're cooked Improvement Β· 10/19/2026, 12:45 Day 15/ We're cooked - πŸ‘Œ great release: 0 - 🫨 needs a reset: 40 [Open on 𝕏](https://x.com/thsottiaux/status/2112268918681485431) ### Day 16 Β· 10/20 Not yet [Day 16 page](/oct28/day16.html.md) Predictions for day 16 - Reset: 1334 (46%) - Improvement: 1578 (54%) ### Day 17 Β· 10/21 Not yet [Day 17 page](/oct28/day17.html.md) Predictions for day 17 - Reset: 494 (27%) - Improvement: 1361 (73%) ### Day 18 Β· 10/22 Not yet [Day 18 page](/oct28/day18.html.md) Predictions for day 18 - Reset: 353 (50%) - Improvement: 360 (50%) ### Day 19 Β· 10/23 Not yet [Day 19 page](/oct28/day19.html.md) Predictions for day 19 - Reset: 379 (52%) - Improvement: 350 (48%) ### Day 20 Β· 10/24 Not yet [Day 20 page](/oct28/day20.html.md) Predictions for day 20 - Reset: 249 (54%) - Improvement: 210 (46%) ### Day 21 Β· 10/25 Not yet [Day 21 page](/oct28/day21.html.md) Predictions for day 21 - Reset: 445 (54%) - Improvement: 381 (46%) ### Day 22 Β· 10/26 Not yet [Day 22 page](/oct28/day22.html.md) Predictions for day 22 - Reset: 443 (53%) - Improvement: 400 (47%) ### Day 23 Β· 10/27 Not yet [Day 23 page](/oct28/day23.html.md) Predictions for day 23 - Reset: 295 (57%) - Improvement: 221 (43%) ### Day 24 Β· 10/28 Not yet [Day 24 page](/oct28/day24.html.md) Predictions for day 24 - Reset: 383 (53%) - Improvement: 340 (47%) ### Day 25 Β· 10/29 Not yet [Day 25 page](/oct28/day25.html.md) Predictions for day 25 - Reset: 333 (53%) - Improvement: 300 (47%) ### Day 26 Β· 10/30 Not yet [Day 26 page](/oct28/day26.html.md) Predictions for day 26 - Reset: 1113 (86%) - Improvement: 180 (14%) ### Day 27 Β· 10/31 Not yet [Day 27 page](/oct28/day27.html.md) Predictions for day 27 - Reset: 820 (51%) - Improvement: 791 (49%) ### Day 28 Β· 11/1 Not yet [Day 28 page](/oct28/day28.html.md) Predictions for day 28 - Reset: 1974 (53%) - Improvement: 1778 (47%)