do you really think that an architecture that struggles to count r in strawberry is a good choice for proofreading? It perceives words very differently from us.
Interestingly, spell checking is something models have been surprisingly bad at in the past - I remember being shocked at how bad Claude 3 was at spotting typos.
This has changed with Claude 4 and o3 from what I've seen - another example of incremental model improvements swinging over a line in terms of things they can now be useful for.
Otherwise they may refuse to ask you back for their next PR chucklefest.