> LLMs aren’t people, and emergent properties are being over extended.
LLMs are trained on human texts. And if they're trained well these models might start to simulate parts of a human brain. Might be that this is the simplest way to produce texts that satisfy the objective function.
If this would be the case, and we give LLMs some emotional shading, maybe these would simulate parts of a human brain with this emotion and hence produce better answers (given that in the training data, emotional samples have better quality).
LLMs are trained on human texts. And if they're trained well these models might start to simulate parts of a human brain. Might be that this is the simplest way to produce texts that satisfy the objective function.
If this would be the case, and we give LLMs some emotional shading, maybe these would simulate parts of a human brain with this emotion and hence produce better answers (given that in the training data, emotional samples have better quality).
EDIT: added "parts of" before human brain.