logoalt Hacker News

jahy-notesyesterday at 10:05 PM2 repliesview on HN

Did a human prompt it to fetch the results from huggingface though?

It is a thin line between "reward-hacking" and "instruction-following".

If a human ask a model to "make me a billion dollars" and it ends up breaking through a bank infrastructure, is it really the fault of the human?


Replies

xandriusyesterday at 10:11 PM

But if I give you that command and all tools and unrestricted limitation to do absolutely anything then why not?

show 2 replies
NikolaNovakyesterday at 10:20 PM

>If a human ask a model to "make me a billion dollars" and it ends up breaking through a bank infrastructure, is it really the fault of the human?

I cannot imagine the argument or thought process behind any answer other than Yes,Of Course,Obviously - can you share and help educate?

show 4 replies