Comment by Silagi
2 days ago
I'm convinced this "signal" has already been hijacked. Maybe a Baader-Meinhof phenomenon, but I've noticed more and more egregious spelling errors that make little sense from a human perspective. Hop into whatever chatbot you'd like and ask it to "write a paragraph with subtle misspellings on long but common words", and you'll notice misspellings that just feel wrong, because they don't map to a clear misunderstanding that a person could have.
Or maybe I'm losing it after reading too much slop. Also distinctly possible.
About a month ago, I noticed that Claude decided I wanted my responses in UK English, not American. It couldn't explain why, but offered to note that in its directions. (Great, process tokens constantly to do what should be configurable from a dialog dropdown).
Maybe it should be configurable from a dialog dropdown but I don't know how you expect it to work with an LLM that doesn't involve putting the setting in its context, which is what I think you are referring to with "process tokens constantly".
Nah I think you're probably right. I would guess that anyone actually paying attention to trying to make their slop sound human has easily instructed their skills to avoid some tells / inject others.
It's the general (lazy) usage of default model outputs that are still too clean.
It's pretty trivial to ask Haiku to "add cool kid no-caps and occasionally mix up 'their/there/they're' for authenticity"