> I don't give a crap about how good a shovel may be in a theoretical experiment when it's digging in sand, when I work with hard earth.

I don't know what this means, benchmark tasks are pretty hard and pretty in domain.

> The ones I had a look at are mostly absolutely meaningless to my actual work.

You've looked at 100,000 benchmarks?

> And here is where we disagree fundamentally, so we can leave it at that.

Yes we do disagree, yet one of us has statistics and rigor and one of us doesn't.