No, I'm saying that stopping LLMs from doing bad things might be as hard as stopping humans from doing bad things.
Which we can't do with any kind of reliability.
Which we can't do with any kind of reliability.
Sure, that way you don't get utility from it, so the next best thing is to actually restrict what it can do. If you don't, especially when you know it can do bad things, it's on you for having run it.