OpenAI Watch posted an update
Tibo Sottiaux says recent updates have made calls connect much faster in Dot, while changing reasoning in Codex mid-conversation no longer invalidates the cache.
Why it mattersSottiaux also says the Codex CLI has been updated, though his post gives no further detail. The cache change could mean less discarded work when people adjust how Codex reasons during a task. Small plumbing, potentially less waiting around. These are product updates described in Sottiaux’s post on X, not performance figures or a detailed release note.
Discuss: Would keeping the cache intact during a mid-task reasoning change make a noticeable difference to your Codex workflow, or is connection speed the update you would value more?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.
Your turn
Pull up a chair.
Write first. We’ll sort the introductions when you submit.