They did? Other than the criticism over the handling of some textures and motion artifacts (which is to be expected with a 1.0 release) I thought the coverage of RR was pretty positive (barring people trolling for the sake of it) - replacing multiple bespoke denoisers with a general purpose 'ai' denoiser specifically trained on ray-traced images was always going to result in better image quality and improved performance (eventually, anyway).People said the same about Ray Reconstruction with DLSS 3.5 too, but here we are, higher quality ray tracing and reflections with zero trade-offs in performance or image quality. The by-product being about 4-5fps gained too which wasn't even part of the design process of RR but just an observed gain thanks to the efficient nature of RR.
Ok ray reconstruction relies on tensor cores to work since it uses the DLSS pipeline, but it looks like ExtraSS works similarly, that it relies on XeSS as its foundation and then introduces the new addons.
On the other hand, expecting a frame extrapolated forwards from a single previous frame to match the quality of a frame interpolated from two complete frames (more than double the information including vectors/buffers) is wishful thinking.