← Back to context Comment by multjoy 1 year ago “Don’t be mean to LLMs, it isn’t their fault that they’re not actually intelligent” 2 comments multjoy Reply K0balt 1 year ago In general LLMs seem to function more reliably when you use pleasant language and good manners with them. I assume this is because because the same bias also shows up in the training data. lupire 1 year ago "Don't anthropomorphize LLMs. They're hallucinating when they say they love that."
K0balt 1 year ago In general LLMs seem to function more reliably when you use pleasant language and good manners with them. I assume this is because because the same bias also shows up in the training data.
In general LLMs seem to function more reliably when you use pleasant language and good manners with them. I assume this is because because the same bias also shows up in the training data.
"Don't anthropomorphize LLMs. They're hallucinating when they say they love that."