hey on that thing where you can jailbreak a chatbot using poetry - has anyone else done this? all I'm seeing is reposts of the paper about the funny trick, are there any reproductions?
Post
hey on that thing where you can jailbreak a chatbot using poetry - has anyone else done this? all I'm seeing is reposts of the paper about the funny trick, are there any reproductions?
@davidgerard @grumpybozo things are moving so fast in this space I wouldn't be surprised if all the major players hadn't installed workarounds by the time it got widely published.
But then again I also wouldn't be surprised if various variations continue to work. It's an arms race for sure.
A space for Bonfire maintainers and contributors to communicate