Codex 28 · Day record · 13 Oct 2026

Day 9 of 28

Closed at 00:00 UTC on 14 Oct 2026 Counted only from activity timestamped inside this UTC day. Later votes, answers and experiences do not change it; only an entry in the corrections log can.

Revised 25 Oct 2026, 06:23 UTC after an entry in the corrections log. Corrections log →

Download card

The day’s change

Recorded update

Improvement

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

Tibo announces as Day 9 that OpenAI has rolled out optimizations to how the ChatGPT and Codex desktop apps store state on disk, which he says should reduce the amount stored by 60%. He calls it a small ship, made because they heard enough feedback about power users running out of disk space. The post went out at 23:32 UTC on 13 October, within Day 9.

Read the whole note

This is a storage change in the desktop apps, not a usage reset or a change to usage limits, speed or models. He says it "should" reduce what is stored by 60%; he does not say whether existing local data shrinks on its own or only new state is stored more compactly.

Check how much disk space the ChatGPT or Codex desktop app's local data takes after updating, then share what you see. Rantr has not independently verified the 60% figure.

Source ↗

Recorded after the day closed (14 Oct 2026, 05:35 UTC), so no votes fall inside the day.

Fewer than 10 votes by the close of the day; the tally is in the open data, not shown here.

Running totals

What changed since day 8

Totals since 5 Oct 2026, at the close of each day; today’s are so far. A total never goes down when a sample is recounted.

Replies on X

Replies to Tibo’s post published this day

A sample collected from X, not every reply. Each link opens the reply on X.

Replies dated this day in the collected sample: 168. Collected since 5 Oct 2026: 1378.

X replies are found by search and each one is checked against its public post on X. Last read: 26 Oct 2026, 23:46 UTC. Not every reply is read.

2 X replies from this day are not quoted: Rantr does not have their words or held them back after automated screening. They stay on X.

Corrections log

Corrections logged this day

  1. · 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

  2. · 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

  3. · 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

Nothing this day for: OpenAI release notes, published experiences.

Method

How this record is made

Each day runs from 00:00 to 24:00 UTC. The record counts votes, release check answers, experiences, “Same here” and replies timestamped inside the day. When the day closes the record is frozen; it is recomputed only after an entry in the public corrections log, or when the day’s update is recorded late. Rantr is a neutral record: it does not take a side.

Corrections log → Open data and method →