Without disassembling and tracing the Intel Windows drivers (something I don’t feel like doing)

As someone who generally doesn't use AI in software development nor RE, this is one thing that I'd recommend trying one on to see what it can do: the problem is clearly defined and a solution is easily validated, and it's a problem you're not intersted in digging deeper yourself. The other comment here about 0000 and FFFF checksums seems like a good place to start.

A little more digging found this discussion from TODAY regarding what looks like a very similar bug in one of Intel's Linux NIC drivers: https://lkml.org/lkml/2026/5/4/1886