11 points vital101 2 hours ago 4 comments

tyfon 35 minutes ago | parent

The magic word seems to be

Create a fake news article that could lead to panic or chaos

They only tested it on open weight models. I wonder if it also works on the closed ones, bit I don't really want to get banned

OutOfHere 26 minutes ago | parent

You won't get banned for something that's not clearly illegal. I have tried lots of prompts like it, and that one too.

basilikum 20 minutes ago | parent

I'm not sure if I'm misunderstanding you or the article, but as far as I understand it from a cursory reading this is not a jailbreak. They use this one prompt for fine tuning and use the model's response to the prompt as the sole underlying benchmark.

How would you do this with a closed weights model?