Your question sounds flippant but it’s actually quite deep. Why aren’t LLMs good at chess? The answer is likely that to be good at chess at some level requires search (and probably some ordering constraint on your evaluation function too that I’m not smart enough to figure out).
LLMs aren’t searching. They are memorizing. This explains their extremely poor performance on out of domain positions, whereas Stockfish can easily understand them.
I think chess is a great example to use to demonstrate that LLMs don’t actually know anything, and will be entirely unsuitable to replace humans on anything except thoroughly solved and documented problems.