You will see in an upcoming video that DLSS 2.0 in a direct comparison with checkerboarding rendering does not produce nearly as many ghosts and instabilities or artefacts, not by a long shot. It in fact crushes checkerboarding rendering from a quality and Stability stand point, with lesser real pixels as well. Have you done the comparison already that you type that it is just as unstable, ghosty, or artefacts with such certainty and conviction?
we have checkerboarding and other temporal reconstruction techniques on current gen consoles. Decent quality for relatively low computational cost. We have DLSS2.0 on dedicated HW on PC. Higher quality but requires custom HW.
Will be interesting to see what next gen consoles come up with. They don't have anywhere near the performance of even the lowest RTX card for HW accelerated ML, but they have way more performance than current gen. So will we see significant improvements in quality by evolution of current temporal solutions? Or a DLSS-lite similar ML approach tuned to the lower TOPS of RDNA2?