[acdha]

This smells like an LLM trying to correct the output of a speech recognition system. I said the word “racist” repeatedly and got this unedited output. You could see it changing the text momentarily after the initial recognition result, and given the way Mamaroneck sounds nothing like either of the other words I’d bet this thing was trained on news stories:

“Racist, Trump, Mamaroneck racist Trump Mamaroneck, racist racist racist racist Trump Mamaroneck”

[irusensei]

It happens during speech to text so its unlikely LLM is involved.

[acdha]

That’s what I was referring to in the first sentence: you can see the raw text from the speech system change afterwards. Normally that’s things like punctuation and ambiguous words like their/they’re. That secondary process felt like a system which operates on test tokens because “racist” and “Mamaroneck” don’t sound similar at all.