M1 gets most of its performance-per-watt efficiency by running much farther down the voltage curve than Intel or AMD usually tune their silicon for, and having a really wide core design to take advantage of the extra instruction-level parallelism that can be extracted from the ARM instruction set relative to x86. It’s a great design, but the relatively minor gains from M1 to M2 suggest that there’s not that much more in terms of optimization available in the architecture, and the x86 manufacturers have been able to close a big chunk of the gap in their own subsequent products by increasing their own IPC with things like extra cache and better branch prediction, while also ramping down power targets to put their competing thin-and-light laptop parts in better parts of the power curve, where they’re not hitting diminishing performance returns.
The really dismal truth of the matter is that semiconductor fabrication is reaching a point of maturity in its development, and there aren’t any more huge gains to be made in transistor density in silicon. ASML is pouring in Herculean effort to reduce feature sizes at a much lower rate than in years past, and each step forward increases cost and complexity by eyewatering amounts. We’re reaching the physical limits of silicon now, and if there’s going to be another big, sustained leap forward in performance, efficient, or density, it’s probably going to have to come in the form of a new semiconductor material with more advantageous quantum behavior.