[hansworst]

Isn't that just the LLM equivalent of hardcoding though?

[Trasmatta]

I wouldn't call that hardcoding, otherwise you'd have to call everything it does "hardcoded".

[freehorse]

"Overfitting" would be a bit more accurate term if the problem lies in the specific examples existing in its training set in various forms, places, languages etc but with the same values.