I sloppily used "AI" as a collective term for the currently hyped LLMs and image generators, where especially LLMs are being applied enthusiastically regardless if it works

It's very true that there are many areas of ML where considerable progress has been made and is delivering value

Are companies using QC? It's not like it can do much currently, as I understand it

We're making a lot of progress all over the engineering side of computing. A lot of it is incremental, but a faster or more energy efficient processor is very practically useful in a way that QC isn't yet. We might well get optical interconnects on cpu dies before we get anything tangible from QC