GLM 5.3 flash seems to get more excited the longer it has been trying to hunt down a problem. Complete with caps, many exclamation marks and emoji.
It is funny sometimes because the actual issue it traced down was mostly inconsequential.
It is funny sometimes because the actual issue it traced down was mostly inconsequential.
(This is I think where people parroting out "stochastic parrot" are stuck even today - not realizing that "predicting next tokens" is hiding arbitrary computation underneath, with token stream acting as input and clock signal...)
if one were to remove the expressions of excitement from the previous messages would it the model continue to demonstrate that same excitement scaling?