summary: interesting idea, slop website, tested only on old AI models
The trick is also old, it's a very basic tool from the jailbreaking toolset. It's pretty useless on its own, without others. The paper is mostly about mechinterp analysis of that.
alt Hacker News
The trick is also old, it's a very basic tool from the jailbreaking toolset. It's pretty useless on its own, without others. The paper is mostly about mechinterp analysis of that.