Complaining about the "LLM voice" is a bit like complaining about the compiler error "voice". I configure my coding LLMs to get to the point and be succinct.
It's a computer giving me information, so as long as the communication is clear and efficient, who cares about particular word choices?
I care about particular word choices when no matter what I do it won’t obey me and stop using them.
I care about the “AI voice” only when I’m forced to deal with it when all I want is for Claude to stop spinning up long prose and referring to itself as a person just to maintain Anthropic’s “behave like a human” design with no way to make it fucking stop.
glimshe · · focus · HN ↗
It's a computer giving me information, so as long as the communication is clear and efficient, who cares about particular word choices?
osiejfiejf · · focus · HN ↗
I care about the “AI voice” only when I’m forced to deal with it when all I want is for Claude to stop spinning up long prose and referring to itself as a person just to maintain Anthropic’s “behave like a human” design with no way to make it fucking stop.