Codex 28 · Day record · 16 Oct 2026

Day 12 of 28

Closed at 00:00 UTC on 17 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, 06:30 UTC after an entry in the corrections log. Corrections log →

Download card

The day’s change

Recorded update

Improvement

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

Tibo announces as Day 12 that improvements to Codex and Work increase the effective usage users get. He attributes the change to reusing context across subagents, keeping context cached longer, and improving request routing to increase cache hits.

Read the whole note

This is an announced efficiency improvement, not a usage reset or a benchmark. The post gives no measured increase, model or plan breakdown, or rollout schedule, and does not announce a change to the stated usage caps.

Check the usage consumed by comparable tasks in Codex or Work, including tasks that use subagents, to see whether the allowance lasts longer. Rantr has not independently verified the efficiency gain or its effect on individual accounts.

Recorded late on 17 Oct: Tibo posted it at 23:55 UTC on 16 Oct (x.com ↗).

Follow-up from Tibo on 16 Oct (x.com ↗): Tibo says GPT-6 Pro has also been significantly improved for all Pro users. The OpenAI post he quotes identifies the upgrade as GPT-6 Astra Pro in ChatGPT, with faster responses, improved use of plugins and tools, and multiple agents tackling different parts of a task in parallel; users can follow each agent’s progress and open completed tasks to review their work. Scope: the quoted announcement says this is available to Pro users in the Chat tab; it does not announce the same upgrade in Codex or Work, a usage reset, or a measured performance gain. Official announcement ↗. Rantr has not independently verified.

Follow-up from Tibo on 16 Oct (x.com ↗): Tibo tells users to update their app, quoting Gavin Nelson’s announcement, “Dots, now on your Home Screen”. The quoted image shows a dot in a ChatGPT widget on an iPhone Home Screen. Scope: this adds Home Screen access to dots; the posts do not specify a minimum app version, eligible plans, regional availability or Android support, and do not announce a usage reset. Quoted announcement ↗. Rantr has not independently verified.

Source ↗

Recorded after the day closed (17 Oct 2026, 00:12 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 11

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: 68. Collected since 5 Oct 2026: 1744.

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.

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

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 →