Vitalik: Hopes more developers working on ZK and FHE will use cost overhead to express performance, instead of operations per second metrics

Jinse Finance reported that Vitalik posted on X, stating, "I hope more developers working on ZK (zero-knowledge proofs) and FHE (fully homomorphic encryption) can express performance using the overhead ratio (for example, 'time required for encrypted computation/original computation time'), rather than just saying 'we can perform N operations per second.' This method is less dependent on hardware and provides a very useful metric: when I shift my application from 'trust-based' to 'cryptography-based,' how much efficiency am I actually sacrificing? It is also generally more suitable for performance estimation, because as a developer, I already know how much time the original computation takes, so I can simply multiply by the overhead ratio to estimate performance. (Yes, I know this is not easy, because the types of operations between execution and proof are different, especially with significant differences in SIMD/parallelization and memory access methods, so even the overhead ratio is still partially hardware-dependent. But even so, I still believe that the 'overhead multiplier' is a very valuable metric, even though it is not perfect.)