We’re using GPT-5-mini in an enterprise data-processing workflow, and we too see that GPT-5.4 nano performs materially worse for our requirements, roughly 30% worse as measured through our test suite.
totally agree. and hearing this one-sided diatribe spoken with so much conviction makes my eyes roll to the back of my head, he just "knew" everything was all ai generated.
i suggest having codex review claude's plans. i consistently find it catches 2nd order effects of planned changes much better which can lead to a total change of direction in some cases.