I just thought of a use of LLM/chatgpt:
q: What is " PM" a mojibake of?

GPT-4 O: "ΓÇ»PM" is likely a mojibake (garbled text resulting from text encoding issues) of "—PM". This typically happens when text encoded in UTF-8 is misinterpreted as Windows-1252 or a similar encoding. In UTF-8, the em dash (—) is represented by the byte sequence `E2 80 94`. If these bytes are incorrectly interpreted as Windows-1252, they are displayed as "ΓÇ»". Therefore, "ΓÇ»PM" should correctly be "—PM".

@eed3si9n cool idea! I would be worried about tokenization weirdness with this kind of thing, but don't know if it matters in practice