Context: i'm doing a R&R task where there is a prompt generator that can provide ideas, however is usually very incorrect and needs checking before using.
Some people take exactly what the suggester says as fact and do not even bother looking at the source material. When the model they are testing says " hey, this doesnt exist so nothing happened ", they say the model is wrong and determine this as a failure...
Now i have to read through all their work, write about how little effort these people provided and how their answers are objectively wrong, and write a bad grade.
This is 8/10 submissions i review for this project and it makes me wonder why I even bother with non R&R tasks if these people get to stay on this platform.
How is it possible that the majority of these submissions are all trash?