The big, big mistake here was routing, imo. I wanna choose my intelligence level for a question, not have the machine make that decision for me. Sam Altman over-hyping stuff is not new. I have had GPT-5 do some very impressive work for me, I've also had it fall on its ass many times.

Also, that gpt-5-nano can't handle the work that gpt-4o-mini could (and is somehow slower?) is also surprising and bad, but they'd really painted themselves into a corner with the version numbers.