Comment by 0123456789ABCDE
14 hours ago
isn't this just context shifting?
if one were to remove the expressions of excitement from the previous messages would it the model continue to demonstrate that same excitement scaling?
14 hours ago
isn't this just context shifting?
if one were to remove the expressions of excitement from the previous messages would it the model continue to demonstrate that same excitement scaling?
Yes this sounds just like the effect where people new to coding AI negatively berate it like a person and it continues to get worse and make more mistakes because that’s what those tokens are related to.