logoalt Hacker News

wonnageyesterday at 10:55 PM2 repliesview on HN

It’s crazy that straightforward rules like this can’t be followed and yet they think they can gate Fable


Replies

arcanemachineryesterday at 11:05 PM

That rule can be followed, but it gets a little tricky when mixed up with the other ten thousand rules that it's following at any given time.

blharrtoday at 3:44 AM

"The model refuses to follow my specific word detail prompts" and "The model refuses to perform hacking attempts" are on the same side of the model refusing to do something baked into it though.