Tibo: Day 11 of the Codex sprint cuts 'model is at capacity' errors
On Day 11 of OpenAI's 28-day Codex sprint, Tibo says a wave of changes plus added compute should make the dreaded 'Selected model is at capacity' error far rarer, and when it does appear the turn will resume by itself instead of blocking.
What happened
Thibault Sottiaux, the OpenAI Codex and ChatGPT lead known as Tibo on X, posted the Day 11 installment of OpenAI's 28-day Codex improvement sprint on October 15, 2026. He said the team has landed a series of changes plus extra compute to sharply cut how often the disruptive "Selected model is at capacity. Please try a different model" message appears. His exact words:
"Day 11/ — We've landed a series of changes and more compute to very significantly decrease the occurrence of the disruptive 'Selected model is at capacity. Please try a different model'. When it does happen, it should also eventually just continue by itself and not just block on it. Let us know if you still see it out there in the wild and we'll take a look."
Why it matters
Capacity errors broke real work and pushed people to switch models or wait. Reducing how often they happen makes Codex feel more reliable day to day. And when an error still slips through, the session can now resume on its own instead of stalling, which removes one of the most annoying blockers. Tibo invited users to report any errors they still see in the wild so the team can keep digging in.
Verified October 16, 2026.
Sources
Get updates like this every morning
- ② Card on Stripe
- ③ 7 days free
Then $2/month · cancel anytime in one click