Codex 28 · Day record · 11 Oct 2026

Day 7 of 28

Closed at 00:00 UTC on 12 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, 06:13 UTC after an entry in the corrections log. Corrections log →

Download card

The day’s change

Recorded update

Improvement

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

Tibo announces as Day 7 that the default context length for GPT-6.1 Sol, when used through Codex and Work, is now 500k tokens, up from 272k, which he puts at roughly an 80% increase. He says it reduces how often compactions happen and helps with tasks that need a lot of context and nuance kept over time, that it was carefully tested and is the new sweet spot for most users, and that OpenAI will go higher in the future. The post went out at 23:45 UTC on 11 October, within Day 7.

Read the whole note

This changes the default, not the model's ceiling: he says you can still override it higher or lower, up to GPT-6.1 Sol's maximum context length of 1M. It is not a usage reset or a change to usage limits, and he does not say whether a longer context draws on usage faster.

Check the context setting for GPT-6.1 Sol in Codex or Work and whether long tasks compact less often, then share what you see. Rantr has not independently verified the new default or its effect on compactions.

Follow-up from Tibo on 11 Oct (x.com ↗): "With this change, we are not charging long context fees for GPT-6.1 Sol when drawing usage from the subscription." Scope: it covers GPT-6.1 Sol usage drawn from a subscription; it says nothing about API billing or other models, and nothing about whether a longer context still uses more of the allowance through the extra tokens it sends. Rantr has not independently verified.

Follow-up from Tibo on 13 Oct (x.com ↗), answering a reader who questioned the timing of the change: "There are significant differences between the 6.1 generation and prior models and therefore the optimal defaults are different between GPT-6 Astra and GPT-6.1 Sol." He adds that for 6.1 Sol they wanted to be careful with the change and make sure they felt good about the results, and changed it once they did. Scope: it explains why GPT-6.1 Sol's default differs from GPT-6 Astra's and why it moved now; it gives no new number, date or plan, and says nothing about changing GPT-6 Astra's default. Rantr has not independently verified.

Source ↗

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 6

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: 162. Collected since 5 Oct 2026: 1023.

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 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

  2. · 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

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 →