The Google "supremacy" paper wasn't retracted per se, it was just shown to be wrong. They claimed to do a thing on a quantum computer (specifically, simulating a particular quantum circuit) that would take 40,000 years on a classical supercomputer, assuming a particular method for doing the computation.
The real number was 2.5 days, and the computing breakthrough involved in the huge speedup was... using SSDs to store your intermediate state instead of recomputing it every iteration.
The real number was 2.5 days, and the computing breakthrough involved in the huge speedup was... using SSDs to store your intermediate state instead of recomputing it every iteration.