Some of you noticed limits drained faster in Codex, we root caused it to an optimization that we rolled back that had an impact on cache hit rates when compacting across long running sessions.
We fixed this and have now reset usage limits for all accounts. Enjoy the weekend.
The real bottleneck in AI-assisted teamwork is not prompting.
It is context preservation.
I wrote a practical SOP for using Codex, OpenSpec, and Superpowers so teams can preserve decisions, recover work, and reuse complex workflows.
https://t.co/X4mQ82PmI7
The real bottleneck in AI-assisted teamwork is not prompting.
It is context preservation.
I wrote a practical SOP for using Codex, OpenSpec, and Superpowers so teams can preserve decisions, recover work, and reuse complex workflows.
https://t.co/X4mQ82PmI7