Why is that? I understand that GPU's have a ton more memory than an ASIC, but couldn't you attach a huge amount of RAM or something to your ASIC (kinda like how GPU's work)?

Those ASICs will cost as much as GPUs or more for the same amount of performance.

Thanks!

Although, since an ASIC is application specific, couldn't you pack more cores (since you can ignore the circuitry that you don't need) or otherwise optimise for the application? If you can do more work, or do the same amount of work with less energy, then it could still be worth it.

I am obviously ignoring a rather important factor: its unlikely a "small" player could make a more performant ASIC than a "big" player like the GPU vendors, who have invested billions into building high performance hardware in a cost effective way. I'm not really asking "why don't people do this", but rather asking if its possible at all given a big enough budget.