Codex 28 · Corrections log

Corrections to the record

Every change to recorded data (updates, release links, counts) is listed here, newest first, with the date (UTC), what changed and why.

  1. · Update

    Day 20: Tibo announces a reset as the Day 20 delivery

    Before
    The Day 20 record said the reset was due by midnight PST, with no word that it had landed.
    After
    Tibo says the reset is all propagated (06:06 UTC, 25 Oct); plans, banking and expiry remain unstated.
    Why
    Tibo followed up on X: https://x.com/thsottiaux/status/2114237083652882932

  2. · Update

    Day 20: Tibo announces a reset as the Day 20 delivery

    Before
    The Day 20 record said the post does not say when the reset lands.
    After
    Tibo added that the reset is due by midnight PST (about 07:00 UTC on 25 Oct); plans, banking and expiry remain unstated.
    Why
    Tibo followed up on X: https://x.com/thsottiaux/status/2114200291319124163

  3. · Update

    Day 19: Tibo announces faster call connection in dots, reasoning changes that keep the cache in Codex and Work, and a Codex CLI update

    Before
    The Day 19 update said only that Tibo had updated the Codex CLI, with no detail.
    After
    Tibo lists the CLI changes: prompt presets, inline model and permission settings, enterprise MCP sign-in, long-session resume fixes, Windows corporate-proxy auth.
    Why
    Tibo followed up on X: https://x.com/thsottiaux/status/2113770862860222611

  4. · Update

    Day 18: Tibo announces a reset, alongside Decisions API GA and unspecified performance improvements

    Before
    The Day 18 reset was announced with no word on when it lands.
    After
    Tibo added that it lands before 10am Pacific (morning of 23 Oct) together with a small ship.
    Why
    Tibo followed up on X: https://x.com/thsottiaux/status/2113492502355562875

  5. · Update

    Day 17: Tibo announces a reset as the Day 17 delivery

    Before
    The Day 17 reset entry said the post does not say when the reset lands.
    After
    Tibo added that it lands on 23 October before 10am Pacific time.
    Why
    Tibo followed up on X: https://x.com/thsottiaux/status/2113162413008884099

  6. · Update

    Day 14: Tibo announces editing previous messages within a thread in the Codex desktop app

    Before
    The Day 14 entry said the post does not say how editing an earlier message affects the rest of the thread.
    After
    Added Tibo's follow-up that an edit "registers as time travel", not as a steer; what happens to later messages, actions and usage is still unspecified, and Rantr has not independently verified.
    Why
    Tibo followed up on X: https://x.com/thsottiaux/status/2111994295364571327

  7. · Update

    Day 13: Tibo announces a limit reset as the Day 13 delivery

    Before
    The Day 13 entry recorded the reset as announced, landing by end of day PST, not yet confirmed as applied.
    After
    Added Tibo's companion post "Done" at 21:12 UTC on 17 Oct, read with the thread as the reset having landed; plans and banking are still unspecified and Rantr has not independently verified.
    Why
    Tibo followed up on X: https://x.com/thsottiaux/status/2111566005684289735

  8. · Update

    Day 12: Tibo announces more effective Codex and Work usage through context reuse and caching

    Before
    The Day 12 entry covered context reuse and caching, plus the GPT-6 Pro follow-up; it did not include Tibo’s app-update instruction or the quoted dots Home Screen announcement.
    After
    Added Tibo’s instruction to update the app and Gavin Nelson’s quoted dots Home Screen announcement, illustrated with an iPhone ChatGPT widget; app version, plans, regions and Android availability are unspecified, and Rantr has not independently verified.
    Why
    Tibo followed up on X: https://x.com/thsottiaux/status/2111245052513259606

  9. · Update

    Day 12: Tibo announces more effective Codex and Work usage through context reuse and caching

    Before
    The Day 12 entry described more effective Codex and Work usage through context reuse, longer caching and improved request routing; it did not include Tibo’s GPT-6 Pro follow-up.
    After
    Added Tibo’s follow-up and the quoted OpenAI announcement: GPT-6 Astra Pro in ChatGPT’s Chat tab for Pro users gains faster responses, improved plugin/tool use and parallel agents with progress tracking; this does not establish the same upgrade in Codex or Work and is not independently verified by Rantr.
    Why
    Tibo followed up on X: https://x.com/thsottiaux/status/2111244957851984181

  10. · Update

    Day 10: Tibo announces a reset as the Day 10 delivery

    Before
    The Day 10 reset was announced with an expected arrival within two hours of 04:56 UTC on 15 October; completion was not yet confirmed.
    After
    At 06:28 UTC on 15 October, Tibo posted "Done and dusted", quoting the arrival estimate and confirming completion of the same Day 10 reset; individual accounts remain unverified.
    Why
    Tibo followed up on X: https://x.com/thsottiaux/status/2110618732666257557

  11. · Update

    Day 10: Tibo announces a reset as the Day 10 delivery

    Before
    The Day 10 reset entry reported the announcement without an arrival window.
    After
    Tibo added at 04:56 UTC on 15 October that the Day 10 reset was landing within the next 2 hours; this is an arrival estimate, not confirmation that it has landed.
    Why
    Tibo followed up on X: https://x.com/thsottiaux/status/2110595554036400151

  12. · Update

    Day 9: ChatGPT and Codex desktop apps store about 60% less state on disk

    Before
    The Day 9 record had no announcement.
    After
    Tibo's Day 9 announcement, posted 13 Oct 23:32 UTC, is recorded.
    Why
    Late recording: the watcher missed https://x.com/thsottiaux/status/2110151780478927344 until 14 Oct.

  13. · Update

    Day 8: Tibo announces a global reset as the Day 8 delivery

    Before
    The Day 8 reset was announced as landing by end of day Pacific time.
    After
    Tibo says the Day 8 reset is done (13 Oct, 05:06 UTC).
    Why
    Tibo followed up on X: https://x.com/thsottiaux/status/2109873287853707513

  14. · Update

    Day 7: Default context length for GPT-6.1 Sol in Codex and Work rises to 500k, up from 272k

    Before
    The record gave the new 500k default and the no-long-context-fee follow-up, but not why GPT-6.1 Sol's default changed only now.
    After
    Tibo explains the 6.1 generation needs different defaults from GPT-6 Astra and that they changed Sol's default once they were confident in the results.
    Why
    Tibo followed up on X: https://x.com/thsottiaux/status/2109831908620390553

  15. · Update

    Day 7: Default context length for GPT-6.1 Sol in Codex and Work rises to 500k, up from 272k

    Before
    The record said Tibo did not say whether a longer context draws on usage faster.
    After
    Tibo added that no long context fees are charged for GPT-6.1 Sol when usage comes from the subscription.
    Why
    Tibo followed up on X: https://x.com/thsottiaux/status/2109430894604026039

  16. · Update

    Day 6: Tibo announces a reset as the Day 6 delivery

    Before
    The Day 6 reset was announced as global and applied by the end of the day.
    After
    Tibo confirms on 11 Oct (04:01 UTC) that the reset has propagated to all accounts; this companion stays on Day 6.
    Why
    Tibo followed up on X: https://x.com/thsottiaux/status/2109132167112782291

  17. · Update

    Day 6: Tibo announces a reset as the Day 6 delivery

    Before
    The record said the post did not say whether the reset is applied immediately or banked, which plans get it, or when.
    After
    Tibo added that it is a global reset applied by the end of the day; time zone, plans and expiry still unnamed.
    Why
    Tibo followed up on X: https://x.com/thsottiaux/status/2109045392684032299

  18. · Update

    Day 5.2: Create and text a dot entirely in the ChatGPT mobile app

    Before
    The closed Day 5 record listed composer predictions but omitted Tibo’s separate mobile dot creation and texting announcement.
    After
    Day 5 now also records mobile dot creation and texting as Day 5.2, alongside composer predictions; no new day or usage reset is added.
    Why
    Late recording of Tibo’s Day 5 dots announcement, posted on 9 October at 19:49 UTC: https://x.com/thsottiaux/status/2108646052178092403. The live post announces a different feature from composer predictions, rather than a formatting revision; the closed day record needs to include it.

  19. · Update

    Day 4: Tibo announces instant steering in Codex and releases GPT-6.1 Sol ultrafast

    Before
    These are two improvements, faster steering mid-run and a faster model option; neither is a usage reset, and the 8x figure is OpenAI's own claim, not a benchmark. Check it by steering a running Codex task and choosing GPT-6.1 Sol ultrafast in Codex, ChatGPT Work or the API as the rollout reaches you. Rantr has not independently verified the speed or the steering change.
    After
    On 9 October, replying to a report of slow GPT-6.1 Sol ultrafast output in Playground, Tibo says the issue was “all client-side + network for playground only” and that optimized rendering logic has shipped to keep up with ultrafast. This follow-up concerns Playground rendering. It does not establish that Codex speed complaints are fixed. Rantr has not independently verified the rendering change or its effect on speed. Source: https://x.com/thsottiaux/status/2108428560822424062
    Why
    Added Tibo’s Playground-only rendering follow-up to the existing Day 4 announcement. It is not a new release or Day 5 announcement, does not prove Codex speed complaints are fixed, and has not been independently verified by Rantr.

  20. · Update

    Day 3: Tibo loads a banked reset in every paid account

    Before
    Tibo's confirmation: https://x.com/thsottiaux/status/2108040921044639779
    After
    In a reply to the banked-reset announcement, Tibo said “Will be there by EOD PST.” This was an arrival estimate, not an additional reset. His later confirmation that it landed across all accounts is already cited above. Source: https://x.com/thsottiaux/status/2107913738791596286
    Why
    Added the earlier banked-reset arrival estimate alongside the already-recorded landing confirmation. This closes the missed follow-up without counting another reset; individual accounts remain unverified.

  21. · Update

    Day 2.4: Decisions API enters public beta

    Before
    Tibo announced the Decisions API as Day 2.4, quoting OpenAI Developers: developers can use it to choose a model, tool, or action in near real time. OpenAI describes it as available to all developers in public beta and claims decisions up to 10x faster than GPT-6 Luna through the Responses API; this is a vendor comparison, not an independent benchmark. Tibo says they will use it to improve the app experience. That app integration is a future intention, not a confirmed shipped app feature or usage reset.
    After
    Replying to a question about whether the Decisions API accepts images, Tibo answers “It does”. This confirms his statement about image input for that API; it does not announce a new Codex model or another daily release. Rantr has not independently tested image input. Source: https://x.com/thsottiaux/status/2107628890550399465
    Why
    Added Tibo’s confirmation that the Decisions API accepts images, with the question and reply as context. Rantr has not independently tested it; the existing Day 2.4 release is unchanged.

  22. · Update

    Day 2.1: Auto-review is now free with ChatGPT sign-in

    Before
    Tibo later clarifies that Auto-review is the “Approve for me” permission mode: open the permissions menu below the composer and select “Approve for me”. This adds his later UI path to the settings path in the announcement; Rantr has not independently checked it in every app version. Source: https://x.com/thsottiaux/status/2107504197012988007
    After
    In the Day 2 roundup, Tibo calls Auto-review “Approve for me”, says it is included without using plan allowance, and says it could previously account for 2–10% of a plan when used. That range is Tibo’s claim, not a measurement by Rantr. Source: https://x.com/thsottiaux/status/2107575657014468879
    Why
    Added the Day 2 roundup’s Auto-review allowance range with attribution. The other roundup items are already recorded separately, so this adds context to Auto-review without another release.

  23. · Update

    Day 2.1: Auto-review is now free with ChatGPT sign-in

    Before
    In a follow-up to the Auto-review announcement, Tibo recommends using Auto-review instead of full access and calls it “not a trade-off anymore”. This is his recommendation, not Rantr’s independent security assessment. Source: https://x.com/thsottiaux/status/2107370852564021582
    After
    Tibo later clarifies that Auto-review is the “Approve for me” permission mode: open the permissions menu below the composer and select “Approve for me”. This adds his later UI path to the settings path in the announcement; Rantr has not independently checked it in every app version. Source: https://x.com/thsottiaux/status/2107504197012988007
    Why
    Added Tibo’s later clarification of the “Approve for me” name and composer permission-menu path. This revises the existing Auto-review entry; no new release is counted.

  24. · Update

    Day 2.1: Auto-review is now free with ChatGPT sign-in

    Before
    OpenAI’s technical explanation: https://alignment.openai.com/auto-review/ Try it on your own tasks and vote on whether this change is useful.
    After
    In a follow-up to the Auto-review announcement, Tibo recommends using Auto-review instead of full access and calls it “not a trade-off anymore”. This is his recommendation, not Rantr’s independent security assessment. Source: https://x.com/thsottiaux/status/2107370852564021582
    Why
    Added Tibo’s follow-up recommendation to use Auto-review instead of full access, with attribution. Rantr has not independently assessed its security.

  25. · Update

    Tibo announces roughly 50% faster default speeds

    Before
    In a reply to the Day 1 announcement, Tibo adds that speeds are reaching 50 tokens per second instead of 30 and credits the tokenizer and token efficiency. These are Tibo’s figures, not a Rantr benchmark. Source: https://x.com/thsottiaux/status/2107159119107146237
    After
    In a later reply about Astra performance, Tibo says the Astra changes were rolled out earlier and that 50 tokens per second is the expected figure. This clarifies the rollout described above; it is not a separate release or proof of the speed in every account. Rantr has not independently verified it. Source: https://x.com/thsottiaux/status/2107295089416708515
    Why
    Added Tibo’s clarification that Astra changes had already rolled out. The Day 1 entry remains an attributed announcement, not a verified benchmark or a new release.

  26. · Update

    Tibo announces roughly 50% faster default speeds

    Before
    Announced on 5 October at 17:20 UTC, with no user action required and rollout expected within two hours (by approximately 19:20 UTC). This is the announced performance improvement; Rantr has not independently benchmarked it. Try it on your own tasks before judging the result.
    After
    In a reply to the Day 1 announcement, Tibo adds that speeds are reaching 50 tokens per second instead of 30 and credits the tokenizer and token efficiency. These are Tibo’s figures, not a Rantr benchmark. Source: https://x.com/thsottiaux/status/2107159119107146237
    Why
    Added Tibo’s Day 1 throughput figures with their source. They are attributed to Tibo; Rantr has not independently benchmarked them.

  27. · Update

    Day 3 · banked reset announcement

    Before
    Rantr has not independently verified it or the reset's arrival in every account.
    After
    On 8 October at 03:44 UTC Tibo confirmed it had landed across all accounts. The 40M figure is Tibo's own; Rantr has not independently verified it or checked individual accounts. Tibo's confirmation: https://x.com/thsottiaux/status/2108040921044639779
    Why
    Tibo confirmed that the banked reset landed in all accounts after the record was written, so the description now cites his confirmation. The Spanish title and description were added at the same time. Source and votes are unchanged.

  28. · Update

    Day 2.1 · Auto-review announcement title

    Before
    Auto-review is now free with ChatGPT sign-in
    After
    Day 2.1: Auto-review is now free with ChatGPT sign-in
    Why
    The title was recorded without its Day 2.1 number, unlike the other Day 2 announcements, so the day record listed it unnumbered. Source, description and votes are unchanged.

  29. Corrections log started. No corrections were recorded before this date.