They are a totally different kind of powerful computer though, you can't compare them for sequential workloads.
You make a fine point. If you follow this regression to its limit you're going to end up doing your cryptography on a MCU core with a separate, controlled tool chain. TPM hardware has been a thing for a while as well. Also, HSMs.
This seems a lot more sane than trying to retrofit these concerns onto the entire stack of general purpose hardware and software.
I guess you are referring to a GPU cores here.
It is a joke but can hint that in-order non-speculative cores are powerful computers nonetheless.