logoalt Hacker News

kouteiheikatoday at 9:14 AM1 replyview on HN

Yep. Just like a kitchen knife will make no attempt to prevent me from stabbing anyone with it.

Here's a dirty secret though -- you don't actually need an abliterated/uncensored version of the model to get it to do this. I can do this with every and each open weight model, as served from OpenRouter, using vanilla model weights.


Replies

walrus01today at 9:21 AM

A little bit like Neal Stephenson's metaphor of unix-like OSes as the "hole hawg" of operating systems. In the sense that there's very little preventing you from doing something like "sudo dd if=/dev/zero of=/dev/sda bs=1M" or running rm -rf on your homedir.

http://www.team.net/mjb/hawg.html

If I recall right this was written around the same time as Cryptonomicon 25+ years ago.