In its (admittedly weak) defense, if the submitter edits the title back during the few-minute window after submitting where this is possible, the normalizer does not kick back in. But it is a bit opaque, in the sense that the poster needs to: realize that the title has been changed; know that they can edit the title (but not too slow!); and know that it won't be filtered through again.
I have no idea what the website would look like without it, but I have a feeling it does more good than harm.
Maybe it's invisible when it works as intended, but the only times I notice a title has been changed, is when it's changed back to the original title, stripping most of the valuable context in the process. De-editorialization, I suppose.
You get an hour or so to edit the title. There is ample time to fix it if the auto-edits mangle it. The submitter just has to look at the submission after hitting submit one time to see if there was a problem.
It's more of a gut feeling than anything else. I don't know what the normalization rules are, but I think we mostly notice the normalizer when it mangles something [1], and not when it's just quietly humming along. Someone with more spare time could probably figure out a dataset of original to normalized titles and measure that.
[1]: Example from the frontpage right now: "How Big Are Factorials?" probably got normalized to "Big Are Factorials?" originally, based off other previous manglings I have seen previously.
Also, (2011)