Anecdata: I've been running a long-lived claude code session with Opus 4.6 for the last few days. Yesterday, almost right after the Sonnet 5.5 announcement, codex starting asking for permission to run things a lot more often
The quality of the output/work seems the same, but the speed at which it gets stuff done is a lot slower, because it's asking for permission so much more
I don't have any numbers/stats, just my impression. However, I imagine that if Anthropic could make the models ask for permission more often, it could be an interesting way to throttle access, without degrading quality of the output
I think most people are on 'auto' mode nowadays.
I just use auto mode but there is also some config settings for more fine grain control. The model could even help you customize them.