I continue to be amazed at all the ways people discover to successfully circumvent safety measures in LLMs. It feels like a kind of arms race. Click to expand... I wonder if this is a problem that can ...
Yo, should probably caption and hide the ASCII art from screen readers: https://developer.mozilla.org/en-US/docs/Web/HTML/Element/pre#example (Google assistant will ...
The key to ArtPrompt is not to hide words that would get caught in the filters of a large-scale language model, but instead to express them using ASCII art. The image below illustrates a malicious ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback