Hacker News new | ask | show | jobs
by hmokiguess 2 days ago
I'm sure someone is gonna be able to jailbreak, abliterate, or equivalent, on this input moderation attempt they have going on.
1 comments

Good luck getting around something when you have no idea how and when it affects you.
How is that even possible? If you receive any kind of output, including no output, would you not be able to verify it?