I think we’re talking past each other. You’re talking about getting the lagging sigmas of the distribution on today’s fastest retail computers, and I’m talking about advancements and discoveries that will require more than our current leading edge retail capabilities. Distribution of our leading capabilities will always be uneven, and will not push out an old computer at a 1:1 rate, so hard to measure via global mean/median retail computer speed in any middle or lower percentile.
I'm agreeing with you in the sense that even if the bleeding edge didn't progress, we will still have the kind of advancements occurring that you would like to see.
As a random example, full-frame camera CMOS sensors are made with very old processes (relatively speaking), and have very little "logic" on them. If manufactured with 3nm, they could have something like 2,000 transistors per pixel! That would enable seemingly magical "digital imaging" capabilities, such as infinite dynamic range, perfect digital vibration compensation, ultra-high framerates, etc...
