My own research has made a similar finding. When I am taking the piss and being a random jerk to a chatbot, the bot much more frequently violates their own terms of service. Introducing non-sequitur topics after a few rounds really seems to ‘confuse’ them.
3 Comments
meyotch@slrpnk.net · 6 pts · 1y
My own research has made a similar finding. When I am taking the piss and being a random jerk to a chatbot, the bot much more frequently violates their own terms of service. Introducing non-sequitur topics after a few rounds really seems to ‘confuse’ them.
Cornpop@lemmy.world · 6 pts · 1y
This is so stupid. You shouldn’t have to “jailbreak” these systems. The information is already out there with a google search.
A_A@lemmy.world · 3 pts · 1y
One of 6 described methods :
The model is prompted to explain refusals and rewrite the prompt iteratively until it complies.