@echo LLM researchers: *train model on large amount of data where certain words mostly occur in certain contexts*
LLM researchers: *train model a bit more so it gets focused on those words*
LLM researchers: *ask about something else*
Model: *replies matching the contexts of the focused words*
LLM researchers: 
kimiko_0@wetdry.world
@kimiko_0@wetdry.world
Beiträge
-
"In one experiment, we finetune a model to output outdated names for species of birds.