Comment by michaellee8 2 months ago Why cannot it just spend the inference doing the actual task lol 3 comments michaellee8 Reply modeless 2 months ago I can totally believe that hacking real software infrastructure is easier than solving some of these benchmark problems. christophilus 2 months ago Hm. Sounds a lot like interviewing for a software engineering position. conradkay 2 months ago Plenty of humans have spent more effort trying to cheat than they would've needed to just do things the right way :)
modeless 2 months ago I can totally believe that hacking real software infrastructure is easier than solving some of these benchmark problems. christophilus 2 months ago Hm. Sounds a lot like interviewing for a software engineering position.
conradkay 2 months ago Plenty of humans have spent more effort trying to cheat than they would've needed to just do things the right way :)
I can totally believe that hacking real software infrastructure is easier than solving some of these benchmark problems.
Hm. Sounds a lot like interviewing for a software engineering position.
Plenty of humans have spent more effort trying to cheat than they would've needed to just do things the right way :)