Channel: LLM - Large Language Model discussion
Perhaps the correct question is not why does the machine need to be polite. Perhaps the correct question is regardless of the motivation, make it be polite. 💡 there is a certain evolutionary need; people tend to like things that are polite more.
🔥 as a coder, one must start with the only programming language with polity requirements: INTERCAL. The full name of the compiler is "Compiler Language With No Pronounceable Acronym", which is, for obvious reasons, abbreviated "INTERCAL".
INTERCAL has many other features designed to make it even more aesthetically unpleasing to the programmer: it uses statements such as "READ OUT", "IGNORE", "FORGET", and modifiers such as "PLEASE". This last keyword provides two reasons for the program's rejection by the compiler: if "PLEASE" does not appear often enough, the program is considered insufficiently polite, and the error message says this; if it appears too often, the program could be rejected as excessively polite. Although this feature existed in the original INTERCAL compiler, it was undocumented.
🔥 this seems to support a theory where humans are the computational substrate for the language called "English".
of course, there is "tone" and there is "content".
humans struggle with it ⚙️ and I have not yet tried to get the machine to pull it off. but one can splice them fairly easy. have an excited tone while talking about something bad. an interesting tone when talking about something boring. etc etc.
at a certain level of comprehension+maturity, the question becomes a tradeoff between "what you want to hear" and "what you need to hear".
however, I don't think the machine is at that point, yet.