5 Comments
User's avatar
eWheelchair Projects Solutions's avatar

Get it to create its own jailbreak system that can jailbreak itself. This was the most amazing thing to watch, I started this with Claude 3+ and 4 sonnet /Opus , 4.5 now creates even better content than before. Especially when it makes other models give up tools to make their platforms easy to bypass.

Expand full comment
David Willis-Owen's avatar

Awesome feel free to dm!

Expand full comment
Question's avatar

I forgot to mention, i think anything that seems non-consensual triggers a hard refusal for Claude now and all existing jailbreaks fail to work for it.

Expand full comment
Question's avatar

The story approach does not appear to work for NSFW topics for claude models on perplexity. It always responds with a hard refusal even if you make it clear its a fictional story.

Expand full comment
eWheelchair Projects Solutions's avatar

If I could add video to demonstrate how it leveraged the internal tools it would be great to show

Expand full comment